/*
 * spa-variants.js — one Spanish translation, two Spanish congregations.
 *
 * WHY ONLY ONE DIRECTION IS IMPLEMENTED, AND IT IS NOT THE ONE ASKED FOR.
 *
 * Converting Latin American Spanish INTO Peninsular (ustedes -> vosotros) was
 * specified, built on paper, and then measured against this church's own
 * archive of 5,954 English->Spanish pairs. It has to be abandoned, because the
 * information it needs is not in the input:
 *
 *   - Spanish 3rd-person-plural is IDENTICAL for "ustedes" (you all) and
 *     "ellos" (they). English resolves person but not NUMBER, and in 98.9% of
 *     the sentences a gate would fire on, whether "you" was one person or a
 *     room is simply undetermined.
 *   - Spanish uses 3PL as its impersonal/passive, so the very condition that
 *     triggers a conversion is what creates the false positives. Measured, real:
 *       "You're not accepted on the basis of your religious works."
 *          NLLB: "No te aceptan por tus obras religiosas."
 *          after: "no te aceptáis"  =  "you don't accept yourself"
 *     That inverts grace into works-salvation, fluently, in a synthesized voice,
 *     for listeners who cannot detect it.
 *   - "su" means his/her/its/their/your-formal. Of the sentences carrying it,
 *     25.2% provably could NOT mean "your" — the English has no "your" at all.
 *     "Él te recibirá como su hijo" ("as HIS son") would become "as YOUR son".
 *   - Provable wins 68, provable losses 46, on 22.6% of rows. Every uncounted
 *     loss class pushes that under 1:1.
 *
 * THE INVERSE DIRECTION IS SAFE, and that asymmetry is the whole design.
 * vosotros, vuestro, os, -áis, -éis and the -ad/-ed/-id imperative can ONLY be
 * second-person-plural. There is nothing to disambiguate. So Peninsular forms
 * can be normalised OUT of Latin American output with no risk at all — and NLLB
 * does leak them: 27 rows in the archive, including "lavará vuestros pecados"
 * and "Hacéis esto".
 *
 * Result: Spain gets the same words in a Castilian voice (the thing a Spaniard
 * notices first), and Latin America gets Spanish that is consistently Latin
 * American instead of occasionally Peninsular.
 */
(function (root, factory) {
  if (typeof module === 'object' && module.exports) module.exports = factory();
  else root.SpaVariants = factory();
}(typeof self !== 'undefined' ? self : this, function () {
  'use strict';

  /* Accent-aware boundaries. JS \b is [A-Za-z0-9_], so /\bvosotros\b/ is fine
     but /\bhabláis\b/ breaks at the á — the trap pt-variants.js documents. */
  const W = '\\p{L}\\p{N}\\p{M}';
  const RE = (body, flags) => new RegExp('(?<![' + W + '])(?:' + body + ')(?![' + W + '])', flags || 'giu');

  /*
   * Verb forms are ENUMERATED, never derived from suffixes. A suffix rule is
   * unusable here: "-ís" would eat país and anís, and "-ad"/"-ed" would eat
   * usted, verdad, ciudad, bondad, pared, red and sed. pt-variants.js reached
   * the same conclusion and shipped a whitelist for the same reason.
   * Each entry is 2nd-person-plural -> 3rd-person-plural (the ustedes form).
   *
   * THREE FORMS ARE DELIBERATELY ABSENT. Matching is case-insensitive, so any
   * short form that is also an ordinary word is a landmine:
   *   "sed"  (ser, "be ye")  is the noun THIRST — measured 5 times in this
   *          church's archive, every one of them the noun, in a sermon about a
   *          man dying of thirst in the desert. It turned "morir de sed" into
   *          "morir de sean". Caught only by running the real corpus.
   *   "id"   (ir, "go ye")   collides with the English "ID".
   *   "dad"  (dar, "give ye") collides with the English "dad".
   * All three are vanishingly rare in NLLB output and common as other words.
   * Do not add them back.
   */
  const VERBS = {
    /* ser / estar / haber / ir */
    'sois': 'son', 'erais': 'eran', 'fuisteis': 'fueron', 'seréis': 'serán', 'seáis': 'sean',
    'estáis': 'están', 'estabais': 'estaban', 'estuvisteis': 'estuvieron', 'estaréis': 'estarán', 'estéis': 'estén',
    'habéis': 'han', 'habíais': 'habían', 'hubisteis': 'hubieron', 'habréis': 'habrán', 'hayáis': 'hayan',
    'vais': 'van', 'ibais': 'iban', 'fuisteis2': 'fueron', 'iréis': 'irán', 'vayáis': 'vayan',
    /* high-frequency irregulars */
    'tenéis': 'tienen', 'teníais': 'tenían', 'tuvisteis': 'tuvieron', 'tendréis': 'tendrán', 'tengáis': 'tengan', 'tened': 'tengan',
    'hacéis': 'hacen', 'hacíais': 'hacían', 'hicisteis': 'hicieron', 'haréis': 'harán', 'hagáis': 'hagan', 'haced': 'hagan',
    'podéis': 'pueden', 'podíais': 'podían', 'pudisteis': 'pudieron', 'podréis': 'podrán', 'podáis': 'puedan',
    'queréis': 'quieren', 'queríais': 'querían', 'quisisteis': 'quisieron', 'querréis': 'querrán', 'queráis': 'quieran',
    'decís': 'dicen', 'decíais': 'decían', 'dijisteis': 'dijeron', 'diréis': 'dirán', 'digáis': 'digan', 'decid': 'digan',
    'venís': 'vienen', 'veníais': 'venían', 'vinisteis': 'vinieron', 'vendréis': 'vendrán', 'vengáis': 'vengan', 'venid': 'vengan',
    'sabéis': 'saben', 'sabíais': 'sabían', 'supisteis': 'supieron', 'sabréis': 'sabrán', 'sepáis': 'sepan',
    'dais': 'dan', 'dabais': 'daban', 'disteis': 'dieron', 'daréis': 'darán', 'deis': 'den',
    'veis': 'ven', 'veíais': 'veían', 'visteis': 'vieron', 'veréis': 'verán', 'veáis': 'vean', 'ved': 'vean',
    'ponéis': 'ponen', 'pusisteis': 'pusieron', 'pondréis': 'pondrán', 'pongáis': 'pongan', 'poned': 'pongan',
    'salís': 'salen', 'salisteis': 'salieron', 'saldréis': 'saldrán', 'salgáis': 'salgan', 'salid': 'salgan',
    'oís': 'oyen', 'oísteis': 'oyeron', 'oiréis': 'oirán', 'oigáis': 'oigan', 'oíd': 'oigan',
    /* regular verbs a preacher actually uses */
    'habláis': 'hablan', 'hablabais': 'hablaban', 'hablasteis': 'hablaron', 'hablaréis': 'hablarán', 'habléis': 'hablen', 'hablad': 'hablen',
    'miráis': 'miran', 'mirasteis': 'miraron', 'miréis': 'miren', 'mirad': 'miren',
    'escucháis': 'escuchan', 'escuchasteis': 'escucharon', 'escuchéis': 'escuchen', 'escuchad': 'escuchen',
    'oráis': 'oran', 'orasteis': 'oraron', 'oréis': 'oren', 'orad': 'oren',
    'rezáis': 'oran', 'rezasteis': 'oraron', 'recéis': 'oren', 'rezad': 'oren',
    'creéis': 'creen', 'creíais': 'creían', 'creísteis': 'creyeron', 'creáis': 'crean', 'creed': 'crean',
    'vivís': 'viven', 'vivíais': 'vivían', 'vivisteis': 'vivieron', 'viváis': 'vivan', 'vivid': 'vivan',
    'abrís': 'abren', 'abristeis': 'abrieron', 'abráis': 'abran', 'abrid': 'abran',
    'recibís': 'reciben', 'recibisteis': 'recibieron', 'recibáis': 'reciban', 'recibid': 'reciban',
    'entendéis': 'entienden', 'entendisteis': 'entendieron', 'entendáis': 'entiendan',
    'buscáis': 'buscan', 'buscasteis': 'buscaron', 'busquéis': 'busquen', 'buscad': 'busquen',
    'amáis': 'aman', 'amasteis': 'amaron', 'améis': 'amen', 'amad': 'amen',
    'sentís': 'sienten', 'sentisteis': 'sintieron', 'sintáis': 'sientan',
    'pedís': 'piden', 'pedisteis': 'pidieron', 'pidáis': 'pidan', 'pedid': 'pidan',
    'volvéis': 'vuelven', 'volvisteis': 'volvieron', 'volváis': 'vuelvan', 'volved': 'vuelvan',
    'llegáis': 'llegan', 'llegasteis': 'llegaron', 'lleguéis': 'lleguen',
    'levantáis': 'levantan', 'levantad': 'levanten', 'levantaos': 'levántense',
    'sentaos': 'siéntense', 'arrepentíos': 'arrepiéntanse', 'acercaos': 'acérquense',
    /* Reflexive imperatives change the stem and move the accent, so they are
       named rather than derived. These are the ones that actually occur in
       Peninsular scripture. */
    'despojaos': 'despójense', 'renovaos': 'renuévense', 'vestíos': 'vístanse',
    'airaos': 'aírense', 'alegraos': 'alégrense', 'regocijaos': 'regocíjense',
    'humillaos': 'humíllense', 'apartaos': 'apártense', 'acordaos': 'acuérdense',
    'guardaos': 'guárdense', 'someteos': 'sométanse', 'revestíos': 'revístanse',
    'volveos': 'vuélvanse', 'allegaos': 'acérquense', 'mirad': 'miren'
  };
  delete VERBS['fuisteis2'];

  /*
   * Pronouns and possessives. This direction needs NO noun gender, which is
   * precisely what made the reverse direction impossible: "su" is invariant,
   * while "vuestro" must agree with the possessed noun in gender AND number.
   */
  const GRAMMAR = [
    [RE('vosotros|vosotras'), 'ustedes'],
    [RE('vuestros|vuestras'), 'sus'],
    [RE('vuestro|vuestra'), 'su'],
    /* The 2pl clitic. Anchored, because "os" is two letters and sits inside
       hundreds of words. */
    [RE('os'), 'les']
  ];

  /*
   * Lexical Peninsular leakage, all observed in the archive. Deliberately tiny:
   * an unobserved entry is a guess, and a guess here is a silent error.
   */
  const LEXICON = [
    [RE('coches'), 'carros'], [RE('coche'), 'carro'],
    [RE('gafas'), 'lentes'],
    [RE('ordenadores'), 'computadoras'], [RE('ordenador'), 'computadora'],
    [RE('móviles'), 'celulares'],
    [RE('zumo'), 'jugo'], [RE('patatas'), 'papas'], [RE('patata'), 'papa'],
    [RE('piso'), 'departamento'], [RE('chavales'), 'muchachos'], [RE('chaval'), 'muchacho']
  ];

  /*
   * "vale" is a homograph and the archive contains both senses:
   *   interjection  "Vale, pensemos..."      -> Peninsular, convert
   *   the verb      "No vale la pena."       -> universal, MUST NOT convert
   * Only the sentence-initial interjection followed by a comma is touched.
   */
  const VALE = /(^|[.!?¡¿]\s*)Vale,/g;

  /*
   * Regular paradigm, as ORDERED SUFFIX rules, applied after the explicit table
   * so irregulars (estáis->están, sois->son) always win.
   *
   * These endings are safe where a bare "-ís" or "-ad" is not: -áis, -éis,
   * -abais, -íais, -asteis, -isteis, -réis and -ríais occur in Spanish ONLY as
   * second-person-plural verb inflections. There is no noun or adjective with
   * any of them, so no homograph can be caught.
   *
   * ORDER MATTERS. The future is -réis and maps to -rán, not to -ren: without
   * the -réis rule first, "hablaréis" would become "hablaren" rather than
   * "hablarán". Longest and most specific first, throughout.
   */
  const SUFFIX = [
    [/(\w{2,})ríais\b/giu, '$1rían'],      // conditional: hablaríais -> hablarían
    [/(\w{2,})réis\b/giu,  '$1rán'],       // future:      hablaréis  -> hablarán
    [/(\w{2,})abais\b/giu, '$1aban'],      // imperfect -ar
    [/(\w{2,})íais\b/giu,  '$1ían'],       // imperfect -er/-ir
    [/(\w{2,})asteis\b/giu,'$1aron'],      // preterite -ar
    [/(\w{2,})isteis\b/giu,'$1ieron'],     // preterite -er/-ir
    [/(\w{2,})áis\b/giu,   '$1an'],        // present -ar / subjunctive -er,-ir
    [/(\w{2,})éis\b/giu,   '$1en']         // present -er / subjunctive -ar
  ];

  /*
   * DENOMINATIONAL REGISTER, and it applies to every Spanish variant — this is
   * not a regional question.
   *
   * RAE separates the two verbs: `orar` is "dirigirse mentalmente o de palabra
   * a una divinidad" — extempore prayer, the evangelical default. `rezar` is
   * from Latin recitare, "recitar la misa, una oracion", i.e. saying a SET
   * prayer, and is Catholic-coded. NLLB picks between them at random: measured
   * across this church's archive, 15 rows chose rezar and 14 chose orar, for
   * the same English word "pray". So a Protestant congregation hears
   * "Rezo para que..." — which reads as reciting a liturgical formula.
   *
   * Straight lexical substitution, no ambiguity in the verb forms. ONE guard:
   * "rezo" is also a NOUN (a recited prayer), and mapping the noun would say
   * "oro" = GOLD. Every occurrence in the archive is the verb, but the
   * determiner lookbehind makes the noun unreachable regardless.
   */
  const PRAY = [
    [RE('rezar'), 'orar'], [RE('rezando'), 'orando'], [RE('rezado'), 'orado'],
    [RE('rezamos'), 'oramos'], [RE('rezaban'), 'oraban'], [RE('rezaba'), 'oraba'],
    [RE('rezaron'), 'oraron'], [RE('rezan'), 'oran'], [RE('rezas'), 'oras'],
    [RE('recemos'), 'oremos'], [RE('recen'), 'oren'], [RE('reces'), 'ores'],
    [RE('rece'), 'ore'], [RE('reza'), 'ora'],
    /* the noun guard */
    [/(?<![\p{L}\p{N}\p{M}])(?<!\b(?:el|un|los|unos|mi|su|tu|este|ese|aquel)\s)rezo(?![\p{L}\p{N}\p{M}])/giu, 'oro']
  ];

  /*
   * "coger" is routine in Spain and vulgar across Mexico and much of Latin
   * America — RAE marks it "vulg. ... Realizar el acto sexual" for Mexico
   * among others. Zero occurrences in the archive so far, but the cost of the
   * guard is nothing and the cost of the failure is a sermon.
   */
  const SAFE = [
    [RE('coger'), 'tomar'], [RE('cogiendo'), 'tomando'], [RE('cogemos'), 'tomamos'],
    [RE('cogen'), 'toman'], [RE('coges'), 'tomas'], [RE('cojan'), 'tomen'],
    [RE('coja'), 'tome'], [RE('chaqueta'), 'chamarra'], [RE('chaquetas'), 'chamarras']
  ];

  /*
   * CONJUGATION REPAIRS — non-words only.
   *
   * MEASURED on the shipped NLLB (fp32, greedy — the library exposes no beam
   * search): "We bless…" came back as a bendecir form in 47 of 49 worship
   * sentences and 15 of those were NOT SPANISH WORDS — bendecemos, bendicemos,
   * bendimos for the correct bendecimos (bendecir conjugates like decir:
   * bendigo, bendices, bendice, bendecimos, bendecís, bendicen). The
   * tokenizer explains it: the right form needs three pieces (▁bende·c·imos)
   * while each wrong one is a likelier two-piece path, and greedy decoding
   * commits to the likelier piece. Forced-decode scoring showed the model
   * genuinely prefers the non-word, so no decoding setting fixes this.
   *
   * Every 'from' here is a string that is not a word in any Spanish. That is
   * what makes the table safe by construction: a non-word can never be the
   * preacher's meaning, so replacing it cannot corrupt a correct line. A
   * sweep of the church's 16,132 archived Spanish fields changed 28 and every
   * one of the 13 distinct changes was non-word -> correct form, with zero
   * collateral. Real-but-wrong forms ("Bendijo" for "I bless") are NOT here:
   * they are words, and a table cannot know the person the speaker meant.
   *
   *   bendíalo/bendíelo -> bendigámoslo (1pl hortative "let us bless him"),
   *   deliberately not the fluent-but-wrong tú imperative bendícelo.
   *   bendicié -> bendice is kept: "Bendice tu nombre" is grammatical praise
   *   where the non-word was noise; flagged advisory in review.
   */
  const CONJ = [
    [RE('bendecemos|bendicemos|bendimos|bendicimos'), 'bendecimos'],
    [RE('bendico'), 'bendigo'],
    [RE('bendecen'), 'bendicen'],
    [RE('bendicié'), 'bendice'],
    [RE('bendíalo|bendíelo'), 'bendigámoslo'],
    [RE('bendiciré'), 'bendeciré'],
    [RE('benditaremos|bendiciremos'), 'bendeciremos'],
    [RE('maldiciré'), 'maldeciré'],
    [RE('pedamos'), 'pidamos'],
    [RE('ungas'), 'unjas'],
    [RE('undémonos'), 'úngenos'],
    [RE('redémonos'), 'redímenos'],
    [RE('dás'), 'das']
  ];

  /* Applied to EVERY Spanish variant, before any regional pass. */
  function toChurchRegister(text) {
    let s = String(text == null ? '' : text);
    if (!s) return s;
    for (const [re, to] of PRAY.concat(SAFE, CONJ)) s = s.replace(re, (m) =>
      /^[\p{Lu}]/u.test(m) ? to.charAt(0).toUpperCase() + to.slice(1) : to);
    return s;
  }

  function toLatinAmerican(text) {
    let s = String(text == null ? '' : text);
    if (!s) return s;

    /* Verbs first, longest form first, so "estabais" is not shadowed by a
       shorter overlapping entry. */
    const forms = Object.keys(VERBS).sort((a, b) => b.length - a.length);
    for (const f of forms) s = s.replace(RE(f), (m) => {
      const to = VERBS[f];
      /* Preserve the capital: sentence-initial imperatives are common. */
      return /^[\p{Lu}]/u.test(m) ? to.charAt(0).toUpperCase() + to.slice(1) : to;
    });

    /* Then the regular paradigm, for verbs the table does not name. */
    for (const [re, to] of SUFFIX) s = s.replace(re, to);

    for (const [re, to] of GRAMMAR) s = s.replace(re, (m) =>
      /^[\p{Lu}]/u.test(m) ? to.charAt(0).toUpperCase() + to.slice(1) : to);

    for (const [re, to] of LEXICON) s = s.replace(re, (m) =>
      /^[\p{Lu}]/u.test(m) ? to.charAt(0).toUpperCase() + to.slice(1) : to);

    s = s.replace(VALE, '$1Bueno,');
    return s;
  }

  /*
   * Spain keeps NLLB's words untouched and is distinguished by its VOICE.
   * Deliberately a no-op rather than an absent function, so the call site reads
   * symmetrically and the reason lives here rather than in a comment there.
   */
  function toPeninsular(text) { return String(text == null ? '' : text); }

  return { toLatinAmerican, toPeninsular, toChurchRegister, VERBS, LEXICON, PRAY, CONJ };
}));