PrivacyScanData/Target/Pseudonym/dataset_pseudonymizer_4.py

def _pseudonymize_identifier_and_measure(
    input_csv_path: str,
    identifier_unit_id_type: str,
    measure_unit_id_type: str,
    job_id: str
) -> str:
    unique_idents = set()
    unique_measure_values = set()
    with open(input_csv_path, newline='', encoding='utf-8') as csv_file:
        for line in csv_file:
            row = line.strip().split(';')
            unit_id = row[1]
            value = row[2]
            unique_idents.add(unit_id)
            unique_measure_values.add(value)
    identifier_to_pseudonym = pseudonym_service.pseudonymize(
        list(unique_idents), identifier_unit_id_type, job_id
    )
    value_to_pseudonym = pseudonym_service.pseudonymize(
        list(unique_measure_values), measure_unit_id_type, job_id
    )
    output_csv_path = input_csv_path.replace('.csv', '_pseudonymized.csv')
    target_file = open(output_csv_path, 'w', newline='', encoding='utf-8')
    with open(input_csv_path, newline='', encoding='utf-8') as csv_file:
        for line in csv_file:
            row = line.strip().split(';')
            line_number: int = row[0]
            unit_id: str = row[1]
            value: str = row[2]
            start_date: str = row[3]
            stop_date: str = row[4]
            target_file.write(
                ';'.join([
                    str(line_number),
                    str(identifier_to_pseudonym[unit_id]),
                    str(value_to_pseudonym[value]),
                    start_date, stop_date
                ]) + '\n'
            )
    target_file.close()
    return output_csv_path