Find duplicate values in a nested JSON structure

duplicate_values_json.py

def find_duplicates(data, seen=None, duplicates=None):
    """
    Recursively finds and returns duplicate values in a nested JSON-like structure.

    This function traverses through the given data (which can be a dictionary, a list, 
    or a single value) and identifies values that appear more than once.

    Parameters:
    data (dict or list): The JSON-like structure (dict or list) to be checked for duplicates.
    seen (set, optional): A set to keep track of values already encountered.
    duplicates (set, optional): A set to accumulate the duplicate values found.

    Returns:
    set: A set of duplicate values identified in the data.
    """

    # Initialize sets for tracking seen values and duplicates
    if seen is None:
        seen = set()
    if duplicates is None:
        duplicates = set()

    if isinstance(data, dict):
        for value in data.values():
            find_duplicates(value, seen, duplicates)
    elif isinstance(data, list):
        for item in data:
            find_duplicates(item, seen, duplicates)
    else:
        if data in seen:
            duplicates.add(data)
        else:
            seen.add(data)

    return duplicates

# Example usage
json_data = {
    'a': 1,
    'b': 2,
    'c': {
        'd': 3,
        'e': 1,  # Duplicate
        'f': {
            'g': 2,  # Duplicate
            'h': 4
        }
    }
}

duplicates = find_duplicates(json_data)
print(duplicates)  # Output: {1, 2}