"""Parser for Mosquito Creek Storage (Warren, OH)."""

from __future__ import annotations

import re

from bs4 import BeautifulSoup

from src.parsers.base import BaseParser, ParseResult, UnitResult


class Facility021630Parser(BaseParser):
    """Extract storage units from Mosquito Creek Storage (Duda CMS site)."""

    platform = "custom_facility_021630"

    def parse(self, html: str, url: str = "") -> ParseResult:
        soup = BeautifulSoup(html, "lxml")
        result = ParseResult(platform=self.platform, parser_name=self.__class__.__name__)

        # Sizes are embedded in strong elements describing unit categories,
        # e.g. "5x5 and 5x10 self storage units in Trumbull County, Ohio"
        size_pattern = re.compile(r"\b(\d+x\d+)\b", re.IGNORECASE)

        seen_sizes: set[str] = set()

        # Find strong elements that contain size references
        for strong in soup.find_all("strong"):
            text = strong.get_text(strip=True)
            if "storage" not in text.lower() and not size_pattern.search(text):
                continue

            matches = size_pattern.findall(text)
            for size_text in matches:
                if size_text in seen_sizes:
                    continue
                seen_sizes.add(size_text)

                unit = UnitResult()
                unit.size = size_text
                w, ln, sq = self.normalize_size(size_text)
                if w is not None:
                    unit.metadata = {"width": w, "length": ln, "sqft": sq}

                result.units.append(unit)

        if not result.units:
            result.warnings.append("No units found on page")

        return result