import { createHash } from "node:crypto";

export function sha256(input: string | Uint8Array): string {
  return createHash("sha256").update(input).digest("hex");
}

/** Canonical URL for fingerprinting: lowercase host, no fragment, sorted query, trailing slash trimmed, tracking params dropped. */
export function canonicalUrl(raw: string): string {
  const u = new URL(raw);
  u.hash = "";
  u.hostname = u.hostname.toLowerCase();
  if ((u.protocol === "https:" && u.port === "443") || (u.protocol === "http:" && u.port === "80")) u.port = "";
  const drop = /^(utm_|fbclid|gclid|mc_cid|mc_eid|ref$|source$|_ga$|_gl$)/i;
  const params = [...u.searchParams.entries()].filter(([k]) => !drop.test(k)).sort(([a], [b]) => a.localeCompare(b));
  u.search = "";
  for (const [k, v] of params) u.searchParams.append(k, v);
  let s = u.toString();
  if (u.pathname !== "/" && s.endsWith("/") && !u.search) s = s.slice(0, -1);
  return s;
}

export function urlFingerprint(raw: string): string {
  return sha256(canonicalUrl(raw)).slice(0, 32);
}

/**
 * Content fingerprint that ignores volatile noise: whitespace runs, HTML comments, script/style bodies,
 * nonces, CSRF tokens, timestamps in attributes. Two fetches of an unchanged page should hash identically.
 */
export function contentFingerprint(body: string, contentType: string | null | undefined): string {
  let s = body;
  if (!contentType || /html/i.test(contentType)) {
    s = s
      .replace(/<!--[\s\S]*?-->/g, "")
      .replace(/<script\b[^>]*>[\s\S]*?<\/script>/gi, "")
      .replace(/<style\b[^>]*>[\s\S]*?<\/style>/gi, "")
      .replace(/<noscript\b[^>]*>[\s\S]*?<\/noscript>/gi, "")
      .replace(/\s(nonce|data-nonce|csrf-token|data-csrf|data-timestamp|data-build|data-reactroot)="[^"]*"/gi, "")
      .replace(/<meta[^>]+(csrf|nonce|build|generated)[^>]*>/gi, "")
      .replace(/<input[^>]+type="hidden"[^>]*>/gi, "");
  }
  s = s.replace(/\s+/g, " ").trim();
  return sha256(s);
}

/** Plain-text projection of HTML for diffing and regex extraction. */
export function htmlToText(html: string): string {
  return html
    .replace(/<script\b[^>]*>[\s\S]*?<\/script>/gi, " ")
    .replace(/<style\b[^>]*>[\s\S]*?<\/style>/gi, " ")
    .replace(/<!--[\s\S]*?-->/g, " ")
    .replace(/<\/(p|div|li|tr|h[1-6]|section|article|br|table|ul|ol|dd|dt)>/gi, "\n")
    .replace(/<br\s*\/?>/gi, "\n")
    .replace(/<[^>]+>/g, " ")
    .replace(/&nbsp;/g, " ")
    .replace(/&amp;/g, "&")
    .replace(/&lt;/g, "<")
    .replace(/&gt;/g, ">")
    .replace(/&quot;/g, '"')
    .replace(/&#39;|&apos;/g, "'")
    .replace(/&#(\d+);/g, (_, d) => String.fromCodePoint(Number(d)))
    .replace(/[ \t]+/g, " ")
    .replace(/\n\s*\n+/g, "\n")
    .trim();
}