import pandas as pd
import hashlib

pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', 128)

_SENSITIVE_COL_NAMES = ['FIRST', 'LAST', 'DOB', 'POSTCODE']


def __hash_sensitive_data(first, last, dob, post_code):
    to_hash = __prep_hash(dob, first, last, post_code)
    return __hash_generic_string(to_hash)


def __hash_generic_string(user_uuid):
    salt = 'SALT_VALUE'
    m = hashlib.sha256()
    m.update(salt.encode('utf-8'))
    m.update(user_uuid.encode('utf-8'))
    return m.hexdigest()


def __prep_hash(dob, first, last, post_code):
    s_first = __fix_char_length(first)
    s_last = __fix_char_length(last)
    blob = "{}::{}::{}::{}".format(s_first, s_last, dob, post_code.replace(" ", ""))
    return blob


def __fix_char_length(generic_str):
    configured_length = 5
    if len(generic_str) > configured_length:
        return generic_str[:configured_length]
    else:
        return generic_str


def __do_pii_hash(df_row):
    return __hash_sensitive_data(df_row[_SENSITIVE_COL_NAMES[0]].upper(), df_row[_SENSITIVE_COL_NAMES[1]].upper(),
                                 df_row[_SENSITIVE_COL_NAMES[2]].upper(), df_row[_SENSITIVE_COL_NAMES[3]].upper())


def __do_uuid_hash(df_row):
    return __hash_generic_string(df_row['USER_ID'].upper())


def main() -> None:
    file_name = 'retro/resources/SENSITIVE-OUTPUT-FULL.csv'
    csv_df = pd.read_csv(file_name)

    csv_df['HASHED_UUID'] = csv_df.apply(__do_uuid_hash, axis=1)
    csv_df['HASHED_PII'] = csv_df.apply(__do_pii_hash, axis=1)
    pii_stripped = csv_df.drop(_SENSITIVE_COL_NAMES, axis=1).copy(deep=True)
    print(pii_stripped.head())
    pii_stripped.to_csv('retro/resources/AVIVA-RETRO-10K-CLEARSCORE-VERSION.csv', index=False)
    uuid_stripped = pii_stripped.drop('USER_ID', axis=1).copy(deep=True)
    uuid_stripped.to_csv('retro/resources/AVIVA-RETRO-10K-AVIVA-VERSION.csv', index=False)


main()