"""Parser for LaramieStorage facility (Laramie, Wyoming).

This is a WordPress/MotoPress site that lists storage unit types as h1 headings
inside .motopress-text-obj divs. No prices are published on the website —
only unit dimensions and feature descriptions are available.

Unit types found:
  - 20x30: Garage door 9' wide x 9' high, Walk-in door, Overhead lights, 110 electric outlets
  - 10x20: Garage door 9' wide x 9' high, Overhead lights
  - 5x10:  Walk-in door, Overhead light
"""

from __future__ import annotations

import re

from bs4 import BeautifulSoup

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

# Match dimension headings like "20×30", "10×20", "5×10" (standard x or Unicode ×)
_SIZE_RE = re.compile(r"^(\d+)\s*[xX\u00d7\u2715]\s*(\d+)$")


class Facility016286Parser(BaseParser):
    """Extract storage units from LaramieStorage (laramiestorage.com).

    The storage-units page uses MotoPress rows where each unit type is
    represented by an h1 heading (the size) followed by a paragraph with
    feature descriptions inside a .motopress-text-obj div.  No pricing
    information is published on the site.
    """

    platform = "custom_facility_016286"

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

        # Each unit type lives inside a .motopress-text-obj div that has
        # an h1 whose text matches a WxL dimension pattern.
        for text_obj in soup.select(".motopress-text-obj"):
            heading = text_obj.find(re.compile(r"^h[1-6]$"))
            if not heading:
                continue

            heading_text = heading.get_text(strip=True)
            m = _SIZE_RE.match(heading_text)
            if not m:
                continue

            width = float(m.group(1))
            length = float(m.group(2))
            size_label = f"{int(width)}x{int(length)}"

            # Collect feature text from the paragraph(s) that follow the heading
            desc_parts: list[str] = []
            for sibling in heading.find_next_siblings():
                text = sibling.get_text(separator=", ", strip=True)
                if text:
                    desc_parts.append(text)

            description = "; ".join(desc_parts) if desc_parts else None

            unit = UnitResult(
                size=size_label,
                description=description,
                url=url or "https://www.laramiestorage.com/storage-units/",
                metadata={
                    "width": width,
                    "length": length,
                    "sqft": width * length,
                },
            )
            result.units.append(unit)

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

        return result