get_maximum_valid_json.py

# Given an incomplete JSON string, extract a subset JSON that is valid
# Obtain the maximum valid portion of this string
# by removing characters one by one from the end and checking the validity

#   By default the incoming json is considered to be an object surrounded by {}
#   Set is_list=True if incoming json is a list surrounded by []

# This method might be inefficient for now since it removes 1 character and validates
# TODO Future optimizaion - 
#   Matching blocks of {} for objects and removing block
#   Matching commas (,) for list items and removing each item

def is_json(myjson, debug=False):
    try:
        json.loads(myjson)
    except ValueError as e:
        if debug is True:
            print(e)
        return False
    return True
  
def get_maximum_valid_json(json_string:str, is_list=False, debug=False):
    if is_json(json_string):
        return json.loads(json_string)
    
    #Remove first character '[' or '{' from the string, we'll add this back later
    temp_string = json_string.strip()[1:]
    
    #Keep removing characters from the end, until a valid json is found
    while len(temp_string) > 0:
        partial_json = '{' + temp_string + '}'  # for objects, which is default
        
        if is_list is True:
            partial_json = '[' + temp_string + ']'  # for lists
        
        if is_json(partial_json, debug=debug): 
            return json.loads(partial_json)
        else:
            if debug is True:
                print(partial_json)

        # Remove last character for next iteration. #TODO - Improve this later with optimization
        temp_string = temp_string[:-1]
        
    print("No valid json found for string - " + json_string)
    return None