Model/epc_data/attributes/WindowAttributes.py

from typing import Dict, List, Union


class WindowAttributes:
    GLAZING_KEYWORDS = ["glazing", "glazed", "glaze"]
    GLAZING_COVERAGE = ["fully", "mostly", "partial", "some"]
    GLAZING_TYPES = ["double", "triple", "secondary", "multiple", "high performance"]

    def __init__(self, description: str):
        self.description: str = self._clean_description(description.lower())

        if not description or not any(
            rt in self.description for rt in
            self.GLAZING_KEYWORDS + self.GLAZING_COVERAGE + self.GLAZING_TYPES
        ):
            raise ValueError('Invalid description')

    def process(self) -> Dict[str, Union[str, bool]]:
        result: Dict[str, Union[str, bool]] = {f'has_{wt.replace(" ", "_")}': False for wt in self.WINDOW_TYPES}

        description = self.description.split(',')

        # Process each part separately
        for part in description:
            part = part.strip()  # remove leading/trailing white spaces
            self._process_part(result, part, self.WINDOW_TYPES, 'has_')

        return result

    @staticmethod
    def _process_part(result: Dict[str, Union[str, bool]], part: str, attr_list: List[str], prefix: str):
        """
        Process a part of the description with a given list of attributes
        and update the result dictionary.
        """
        part_words = part.split()
        for attr in attr_list:
            attr_words = attr.split()
            if set(attr_words).issubset(set(part_words)):
                result[f'{prefix}{attr.replace(" ", "_")}'] = True

        return result