import * as cheerio from 'cheerio';

/** Thin HTML helpers shared by connectors (cheerio). */
export function load(html: string) {
  return cheerio.load(html);
}

export type CheerioRoot = ReturnType<typeof cheerio.load>;

export function text($el: { text(): string } | null | undefined): string | null {
  const t = $el?.text()?.replace(/\s+/g, ' ').trim();
  return t ? t : null;
}

export function absUrl(base: string, href: string | null | undefined): string | null {
  if (!href) return null;
  try {
    return new URL(href, base).toString();
  } catch {
    return null;
  }
}

/** Extract JSON-LD blocks of a given @type (e.g. Product, Offer) from HTML. */
export function jsonLd(html: string, type?: string): Record<string, unknown>[] {
  const $ = cheerio.load(html);
  const out: Record<string, unknown>[] = [];
  $('script[type="application/ld+json"]').each((_, el) => {
    const raw = $(el).contents().text();
    try {
      const parsed = JSON.parse(raw) as unknown;
      const items = Array.isArray(parsed) ? parsed : (parsed && typeof parsed === 'object' && '@graph' in (parsed as object) ? ((parsed as { '@graph': unknown[] })['@graph'] ?? []) : [parsed]);
      for (const it of items) {
        if (it && typeof it === 'object') {
          const t = (it as { '@type'?: string | string[] })['@type'];
          const types = Array.isArray(t) ? t : t ? [t] : [];
          if (!type || types.includes(type)) out.push(it as Record<string, unknown>);
        }
      }
    } catch {
      /* ignore malformed JSON-LD */
    }
  });
  return out;
}

/** Extract Next.js __NEXT_DATA__ payload when present. */
export function nextData(html: string): unknown | null {
  const m = html.match(/<script id="__NEXT_DATA__"[^>]*>([\s\S]*?)<\/script>/);
  if (!m) return null;
  try {
    return JSON.parse(m[1]!);
  } catch {
    return null;
  }
}

/** Extract a JS object literal assigned to a global, e.g. window.__INITIAL_STATE__ = {...}; */
export function inlineJson(html: string, marker: string): unknown | null {
  const idx = html.indexOf(marker);
  if (idx < 0) return null;
  const start = html.indexOf('{', idx);
  if (start < 0) return null;
  let depth = 0;
  let inStr: string | null = null;
  for (let i = start; i < html.length; i++) {
    const ch = html[i]!;
    if (inStr) {
      if (ch === '\\') i++;
      else if (ch === inStr) inStr = null;
      continue;
    }
    if (ch === '"' || ch === "'") inStr = ch;
    else if (ch === '{') depth++;
    else if (ch === '}') {
      depth--;
      if (depth === 0) {
        try {
          return JSON.parse(html.slice(start, i + 1));
        } catch {
          return null;
        }
      }
    }
  }
  return null;
}