"""Parser for Premier Self Storage-Sauk Rapids, MN."""

from __future__ import annotations

import re

from bs4 import BeautifulSoup

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


class Facility109021Parser(BaseParser):
    """Extract storage units from Premier Self Storage-Sauk Rapids, MN using table layout."""

    platform = "custom_facility_109021"

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

        table = soup.select_one("table._2QREMkZenGaFOjxHn8CDhU.table")
        if not table:
            # Fallback: find table with most price-containing rows
            tables = soup.find_all("table")
            best, best_count = None, 0
            for t in tables:
                c = sum(1 for r in t.find_all("tr") if "$" in r.get_text())
                if c > best_count:
                    best_count = c
                    best = t
            table = best

        if not table:
            result.warnings.append("No pricing table found")
            return result

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

            row_text = row.get_text()
            # Skip header rows
            if not re.search(r"\$\d+", row_text) and not re.search(r"\d+\s*[\'\'xX]\s*\d+", row_text):
                continue

            unit = UnitResult()

            # Extract size
            size_text = cells[1].get_text(strip=True)
            if size_text:
                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}

            # Extract price
            price_text = cells[2].get_text(strip=True)
            if price_text:
                # Try to find the price in this cell
                price_match = re.search(r"\$(\d[\d,.]*)", price_text)
                if price_match:
                    unit.price = self.normalize_price(price_match.group(1))

            unit.description = row.get_text(separator=" ", strip=True)

            if unit.size or unit.price:
                result.units.append(unit)

        if not result.units:
            result.warnings.append("No units found in table")

        return result