Model/model_data/epc_attributes/RoofAttributes.py

import re
from typing import Dict, Union
from model_data.BaseUtility import Definitions
from model_data.epc_attributes.attribute_utils import extract_component_types, extract_thermal_transmittance


class RoofAttributes(Definitions):
    ROOF_TYPES = ['pitched', 'roof room', 'loft', 'flat', 'thatched', 'at rafters', 'assumed']
    DWELLING_ABOVE = ["another dwelling above", "other premises above"]

    WELSH_TEXT = {
        "ar oleddf, dim inswleiddio": "pitched, no insulation",
    }

    def __init__(self, description: str):
        """
        :param description: Description of the roof.
        """

        self.description: str = description.lower()
        self.nodata = not description or description in self.DATA_ANOMALY_MATCHES

        translation = self.WELSH_TEXT.get(self.description)
        if translation:
            self.nodata = False
            self.description = translation

        if not self.nodata and not any(
            rt in self.description for rt in self.ROOF_TYPES + self.DWELLING_ABOVE + ["average thermal transmittance"]
        ):
            raise ValueError('Invalid description')

    def process(self) -> Dict[str, Union[float, str, bool, None]]:

        result: Dict[str, Union[float, str, bool, None]] = {}

        if self.nodata:
            return result

        description = self.description

        # thermal transmittance
        result, description = extract_thermal_transmittance(result, description)

        # roof type
        result, description = extract_component_types(result, description, list_of_components=self.ROOF_TYPES)

        result["has_dwelling_above"] = (
            "another dwelling above" in description or "other premises above" in description
        )
        for dwelling_above in self.DWELLING_ABOVE:
            description = description.replace(dwelling_above, "")

        result["is_valid"] = "invalid" not in description
        description = description.replace("invalid", "")

        # insulation thickness
        thickness_map = {
            "ceiling insulated": "average",
            "insulated": "average",
            "limited": "below average",
            "no insulation": "none",
            "limited insulation": "below average",
            "additional insulation": "above average",
        }
        for key, value in thickness_map.items():
            if key in description:
                result['insulation_thickness'] = value
                # Remove the match from the description
                # description = description.replace(key, "")
                break
        else:
            # Extract insulation thickness in mm, if present
            match = re.search(r'(\d+\+?)\s*mm', description)
            if match:
                result['insulation_thickness'] = match.group(1)

        if "insulation_thickness" not in result:
            result['insulation_thickness'] = None

        return result