"""Parser for KMT Storage."""

from __future__ import annotations

import re

from bs4 import BeautifulSoup

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


class Facility041086Parser(BaseParser):
    """Extract storage units from KMT Storage."""

    platform = "custom_facility_041086"

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

        # Sizes are mentioned in a paragraph about storage options
        # Extract all unique dimension patterns from the page text
        text = soup.get_text()
        dims = re.findall(r"\b(\d+[xX]\d+)\b", text)
        # Filter to reasonable storage unit sizes
        seen = set()
        for dim in dims:
            # Skip duplicates
            if dim in seen:
                continue
            parts = re.split(r"[xX]", dim)
            if len(parts) != 2:
                continue
            try:
                w = float(parts[0])
                l = float(parts[1])
            except ValueError:
                continue
            # Filter to plausible storage unit sizes (5-50 ft per side)
            if 5 <= w <= 50 and 5 <= l <= 50:
                seen.add(dim)
                unit = UnitResult()
                unit.size = dim
                wn, ln, sq = self.normalize_size(dim)
                if wn is not None:
                    unit.metadata = {"width": wn, "length": ln, "sqft": sq}
                result.units.append(unit)

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

        return result