from utils.s3 import read_from_s3

from backend.app.config import get_settings
import msgpack


def get_cleaned():
    """
    This function will retrieve the cleaned dataset from s3 which has the cleaned
    descriptions for the epc dataset

    This data is stored in MessagePack format and therefore needs to be decoded
    :return:
    """

    cleaned = read_from_s3(
        s3_file_name="cleaned_epc_data/cleaned.bson",
        bucket_name="retrofit-data-{environment}".format(environment=get_settings().ENVIRONMENT)
    )

    cleaned = msgpack.unpackb(cleaned, raw=False)

    return cleaned