/** Text normalisation helpers shared by entity resolution, search and connectors. */

export function slugify(input: string, maxLength = 96): string {
  const s = input
    .normalize('NFKD')
    .replace(/[̀-ͯ]/g, '')
    .toLowerCase()
    .replace(/&/g, ' and ')
    .replace(/[^a-z0-9]+/g, '-')
    .replace(/^-+|-+$/g, '');
  return s.length > maxLength ? s.slice(0, maxLength).replace(/-+$/g, '') : s;
}

/** Aggressive normalisation for matching: lowercase, ASCII, punctuation removed, common noise words dropped. */
const NOISE = new Set(['the', 'a', 'an', 'of', 'and', '&', 'card', 'cards', 'lot', 'rare', 'mint', 'nm', 'lp', 'mp', 'hp', 'wow', 'look', 'nice', 'beautiful', 'gorgeous', 'pop', 'gem', 'mt', 'l@@k']);
export function normalizeForMatch(input: string): string {
  return input
    .normalize('NFKD')
    .replace(/[̀-ͯ]/g, '')
    .toLowerCase()
    .replace(/[#№]/g, ' ')
    .replace(/[^a-z0-9./\- ]+/g, ' ')
    .split(/\s+/)
    .filter((t) => t && !NOISE.has(t))
    .join(' ')
    .trim();
}

export function tokens(input: string): string[] {
  return normalizeForMatch(input).split(' ').filter(Boolean);
}

/** Jaccard similarity of token sets (0–1). */
export function jaccard(a: string, b: string): number {
  const A = new Set(tokens(a));
  const B = new Set(tokens(b));
  if (A.size === 0 && B.size === 0) return 1;
  let inter = 0;
  for (const t of A) if (B.has(t)) inter++;
  return inter / (A.size + B.size - inter);
}

export function truncate(s: string, n: number): string {
  return s.length <= n ? s : `${s.slice(0, n - 1)}…`;
}

export function compactWhitespace(s: string): string {
  return s.replace(/\s+/g, ' ').trim();
}

/** Extract a 4-digit year plausible for collectibles (1800–current+1). */
export function extractYear(s: string): number | null {
  const now = new Date().getUTCFullYear() + 1;
  const m = s.match(/\b(1[89]\d{2}|20\d{2})\b/g);
  if (!m) return null;
  for (const y of m) {
    const n = Number(y);
    if (n >= 1800 && n <= now) return n;
  }
  return null;
}