"""Parser for Cherokee Storage / K&L Storage."""

from __future__ import annotations

import re

from bs4 import BeautifulSoup

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


class Facility046851Parser(BaseParser):
    """Extract storage units from Cherokee Storage / K&L Storage."""

    platform = "custom_facility_046851"

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

        # Units are in a tablesaw table with Type and Size columns
        # Find table by ID prefix or class
        table = soup.find("table", id=re.compile(r"^table-"))
        if not table:
            table = soup.find("table", class_=re.compile(r"pp-table-content"))

        if table:
            rows = table.find_all("tr")
            for row in rows:
                cells = row.find_all(["td", "th"])
                if len(cells) < 2:
                    continue
                # Skip header rows
                if cells[0].name == "th":
                    continue

                # In tablesaw-stack mode, data is in .tablesaw-cell-content spans
                type_el = cells[0].find("span", class_="tablesaw-cell-content")
                size_el = cells[1].find("span", class_="tablesaw-cell-content")

                type_text = type_el.get_text(strip=True) if type_el else cells[0].get_text(strip=True)
                size_text = size_el.get_text(strip=True) if size_el else cells[1].get_text(strip=True)

                # Filter out header repeats
                if not size_text or size_text.lower() == "size":
                    continue

                if re.search(r"\d", size_text):
                    unit = UnitResult()
                    unit.size = size_text
                    unit.description = type_text if type_text else None
                    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