Model/backend/ecmk_fetcher/address_list.py

import re
from dataclasses import dataclass
from typing import Any, Dict, Optional
from openpyxl import Workbook, load_workbook
from openpyxl.worksheet.worksheet import Worksheet


@dataclass
class PropertyRow:
    row_index: int
    address: str


def extract_addresses_from_spreadsheet(
    filepath: str,
) -> Dict[str, PropertyRow]:
    wb: Workbook = load_workbook(filepath, data_only=True)
    ws: Worksheet = wb["Southern RA-Lite Programme 3103"]

    header_row: int = 1
    id_col: Optional[int] = None
    deal_name_col: Optional[int] = None

    # find columns
    for col in range(1, ws.max_column + 1):
        raw_value: Any = ws.cell(row=header_row, column=col).value
        value: str = str(raw_value).strip().lower() if raw_value else ""

        if value == "id":
            id_col = col
        elif value == "deal name":
            deal_name_col = col

    if id_col is None or deal_name_col is None:
        raise Exception("Missing required columns")

    properties: Dict[str, PropertyRow] = {}

    for row in range(2, ws.max_row + 1):
        id_val: Any = ws.cell(row=row, column=id_col).value
        deal_name: Any = ws.cell(row=row, column=deal_name_col).value

        if not id_val or not deal_name:
            continue

        property_id: str = str(id_val).strip()

        properties[property_id] = PropertyRow(
            row_index=row,
            address=extract_succinct_address(str(deal_name)),
        )

    return properties


def extract_succinct_address(deal_name: str) -> str:
    left_part = deal_name.split("|")[0].strip()

    postcode_match: Optional[re.Match[str]] = re.search(
        r"\b([A-Z]{1,2}\d[A-Z\d]?\s*\d[A-Z]{2})\b",
        left_part,
        re.IGNORECASE,
    )

    postcode = postcode_match.group(1).upper() if postcode_match else None
    first_part = left_part.split(",")[0].strip()

    return f"{first_part} {postcode}" if postcode else first_part