import type { PatternDef } from './types.js';

/**
 * Swiss preset — the structured identifiers most relevant to the Swiss nLPD.
 * Order matters: specific patterns (AVS, IBAN) come before generic ones.
 */
const swiss: PatternDef[] = [
  { tag: 'AVS', re: /\b756\.\d{4}\.\d{4}\.\d{2}\b/g }, // Swiss social security (AVS/AHV)
  { tag: 'IBAN', re: /\bCH\d{2}[0-9A-Z]{17}\b/gi }, // Swiss IBAN
  { tag: 'EMAIL', re: /\b[\w.+-]+@[\w-]+\.[\w.-]+\b/g },
  { tag: 'TEL', re: /(?:\+41|0)(?:[\s.-]?\d){9}\b/g }, // Swiss phone number
  { tag: 'DATE', re: /\b\d{1,2}[./-]\d{1,2}[./-]\d{2,4}\b/g },
];

/** Luhn check on a credit-card candidate (ignores spaces/dashes); 13–19 digits. */
function luhnValid(value: string): boolean {
  const digits = value.replace(/\D/g, '');
  if (digits.length < 13 || digits.length > 19) return false;
  let sum = 0;
  let double = false;
  for (let i = digits.length - 1; i >= 0; i--) {
    let d = digits.charCodeAt(i) - 48; // '0' === 48
    if (double) {
      d *= 2;
      if (d > 9) d -= 9;
    }
    sum += d;
    double = !double;
  }
  return sum % 10 === 0;
}

/**
 * Generic preset — locale-agnostic identifiers useful as a starting point
 * anywhere. Best-effort: extend or compose with your own {@link PatternDef}s.
 *
 * Order matters (patterns run in sequence on the already-anonymized text):
 * specific identifiers claim their matches before broader ones, and dates are
 * claimed before phone numbers so they don't get mis-tagged as `TEL`.
 */
const generic: PatternDef[] = [
  { tag: 'EMAIL', re: /\b[\w.+-]+@[\w-]+\.[\w.-]+\b/g },
  { tag: 'IBAN', re: /\b[A-Z]{2}\d{2}[0-9A-Z]{11,30}\b/g },
  { tag: 'IPV4', re: /\b(?:\d{1,3}\.){3}\d{1,3}\b/g },
  // 13–19 digits in optional space/dash groups, gated by Luhn to avoid eating
  // arbitrary long digit runs (account numbers, ids).
  { tag: 'CREDIT_CARD', re: /\b\d(?:[ -]?\d){12,18}\b/g, validate: luhnValid },
  { tag: 'DATE', re: /\b\d{1,2}[./-]\d{1,2}[./-]\d{2,4}\b/g },
  // Requires grouped/separated digits (or a leading +country) so plain integers
  // aren't mistaken for phone numbers.
  { tag: 'TEL', re: /(?:\+\d{1,3}[\s.-]?)?(?:\(?\d{2,4}\)?[\s.-]){2,3}\d{2,4}/g },
];

/** Built-in pattern sets for the regex fallback. */
export const presets = { swiss, generic };