"""Parser for B&H Mini-Storage."""

from __future__ import annotations

import re

from bs4 import BeautifulSoup

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


class Facility094794Parser(BaseParser):
    """Extract storage units from B&H Mini-Storage."""

    platform = "custom_facility_094794"

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

        # Unit sizes are in an h4 element containing "UNIT SIZES:" followed by
        # concatenated size strings like "10' X 10'10' X 15'10' X 20'10' x 30'"
        # Use 1-2 digit constraint to split concatenated sizes.
        size_pattern = re.compile(r"(\d{1,2})['\u2019]?\s*[xX]\s*(\d{1,2})['\u2019]?(?=\d|$|\s|')")

        for h4 in soup.find_all("h4"):
            text = h4.get_text(strip=True)
            if "UNIT SIZES" in text.upper():
                # Extract all size pairs from the concatenated text
                seen_sizes = set()
                for match in size_pattern.finditer(text):
                    size_text = f"{match.group(1)}' x {match.group(2)}'"
                    if size_text not in seen_sizes:
                        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)
                break

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

        return result