export function extractTitleFromHtml(html: string): string {
  const match = html.match(/<title[^>]*>([^<]+)<\/title>/i);
  return match?.[1]?.trim() ?? "";
}

export function isLikelyJSRendered(html: string): boolean {
  const bodyMatch = html.match(/<body[^>]*>([\s\S]*?)<\/body>/i);
  if (!bodyMatch) return false;
  const textContent = bodyMatch[1]
    .replace(/<script[\s\S]*?<\/script>/gi, "")
    .replace(/<style[\s\S]*?<\/style>/gi, "")
    .replace(/<[^>]+>/g, "")
    .replace(/\s+/g, " ")
    .trim();
  const scriptCount = (html.match(/<script/gi) || []).length;
  return textContent.length < 300 && scriptCount >= 2;
}

export function htmlToMarkdown(html: string): string {
  let s = html.replace(/<(script|style|noscript|svg|canvas|form|nav|footer|header|aside)[\s\S]*?<\/\1>/gi, " ");
  s = s.replace(/<!--[\s\S]*?-->/g, " ");

  // Headings
  s = s.replace(/<h1[^>]*>([\s\S]*?)<\/h1>/gi, "\n\n# $1\n\n");
  s = s.replace(/<h2[^>]*>([\s\S]*?)<\/h2>/gi, "\n\n## $1\n\n");
  s = s.replace(/<h3[^>]*>([\s\S]*?)<\/h3>/gi, "\n\n### $1\n\n");
  s = s.replace(/<h4[^>]*>([\s\S]*?)<\/h4>/gi, "\n\n#### $1\n\n");
  s = s.replace(/<h5[^>]*>([\s\S]*?)<\/h5>/gi, "\n\n##### $1\n\n");
  s = s.replace(/<h6[^>]*>([\s\S]*?)<\/h6>/gi, "\n\n###### $1\n\n");

  // Code blocks and inline code
  s = s.replace(/<pre[^>]*><code[^>]*>([\s\S]*?)<\/code><\/pre>/gi, "\n```\n$1\n```\n");
  s = s.replace(/<pre[^>]*>([\s\S]*?)<\/pre>/gi, "\n```\n$1\n```\n");
  s = s.replace(/<code[^>]*>([\s\S]*?)<\/code>/gi, " `$1` ");

  // Blockquotes and emphasis
  s = s.replace(/<blockquote[^>]*>([\s\S]*?)<\/blockquote>/gi, "\n> $1\n");
  s = s.replace(/<(strong|b)[^>]*>([\s\S]*?)<\/\1>/gi, "**$2**");
  s = s.replace(/<(em|i)[^>]*>([\s\S]*?)<\/\1>/gi, "*$2*");

  // Links
  s = s.replace(/<a\s+[^>]*href=["']([^"']+)["'][^>]*>([\s\S]*?)<\/a>/gi, (_, href, text) => {
    const t = text.replace(/<[^>]*>/g, "").trim();
    if (!t) return "";
    if (href.startsWith("#") || href.startsWith("javascript:")) return t;
    return `[${t}](${href})`;
  });

  // Lists
  s = s.replace(/<li[^>]*>([\s\S]*?)<\/li>/gi, "\n- $1");
  s = s.replace(/<\/(ul|ol)>/gi, "\n\n");

  // Tables
  s = s.replace(/<tr[^>]*>([\s\S]*?)<\/tr>/gi, "\n$1 |");
  s = s.replace(/<t[dh][^>]*>([\s\S]*?)<\/t[dh]>/gi, " | $1");
  s = s.replace(/<\/(table|thead|tbody)>/gi, "\n\n");

  // Paragraphs and line breaks
  s = s.replace(/<\/(p|div|section|article)>/gi, "\n\n");
  s = s.replace(/<br\s*\/?>/gi, "\n");

  // Strip remaining tags
  s = s.replace(/<[^>]*>/g, " ");

  // HTML entity decoding
  s = s
    .replace(/&nbsp;/g, " ")
    .replace(/&amp;/g, "&")
    .replace(/&lt;/g, "<")
    .replace(/&gt;/g, ">")
    .replace(/&quot;/g, '"')
    .replace(/&#39;/g, "'")
    .replace(/&hellip;/g, "…")
    .replace(/&mdash;/g, "—")
    .replace(/&ndash;/g, "–");

  return s
    .split("\n")
    .map((line) => line.trimEnd())
    .filter((line, i, arr) => !(line === "" && arr[i - 1] === ""))
    .join("\n")
    .trim();
}