church-translate/app/liturgy.js

/*
 * liturgy.js — the handful of words that must never be guessed at.
 *
 * Measured against the shipped NLLB, the single most frequent word in a service
 * translates as follows:
 *
 *   "Amen."  →  spa  "- Sí, estoy bien."     ("yes, I'm fine")
 *               fra  "Je vous en prie."      ("you're welcome")
 *               deu  "- Das ist doch gut."   ("well, that's good")
 *               zho  "现在,我们要去."          ("now, we're going to go")
 *               rus  "- Да, да."             ("yes, yes")
 *
 * Of ten languages tested, four were right. This is not a translation problem
 * that better decoding fixes — one word carries no context for a context model
 * to work from. So these bypass the model completely.
 *
 * SCOPE IS DELIBERATELY TINY. Only Hebrew LOANWORDS are here — amen, hallelujah,
 * hosanna — words every tradition transliterated rather than translated, so
 * there is one right answer and no denominational choice hiding in it.
 * "Praise the Lord" and "Glory to God" are NOT here: they are translated
 * phrases, and their wording differs between Protestant and Catholic editions
 * of the same language. Guessing those would be the exact silent, confident
 * error this file exists to prevent.
 *
 * Matching is WHOLE-UTTERANCE ONLY. "Amen" is a title of Christ in Revelation
 * 3:14 and a deity in an Exodus sermon; "can I get an amen?" is a sentence.
 * None of those may be touched, and equality matching means none of them are.
 */
(function (root, factory) {
  if (typeof module === 'object' && module.exports) module.exports = factory();
  else root.Liturgy = factory();
}(typeof self !== 'undefined' ? self : this, function () {
  'use strict';

  /*
   * Whisper writes these many ways: "Amen", "amen!", "A-men.", "Amen...".
   *
   * Hyphens are removed (A-men -> amen) but whitespace is COLLAPSED, not
   * deleted. Deleting it turned "praise god" into "praisegod", which could
   * never match a table key — so every multi-word entry would have been a
   * silent no-op. Only single words are in the table today, so this was latent;
   * fixing it now means a multi-word entry added later actually works.
   */
  function key(text) {
    return String(text || '')
      .toLowerCase()
      .replace(/[‘’']/g, '')
      .replace(/[-‐-―]+/g, '')        // A-men -> amen
      .replace(/\s+/g, ' ')           // collapse, do NOT delete
      .replace(/[.!?,;:…。！？]+$/g, '')
      .trim();
  }

  /*
   * Confidence is recorded per language, not assumed. HIGH = a form I can state
   * without hedging. REVIEW = believed correct and worth a native speaker's
   * glance before a service. A language absent from a table falls through to
   * NLLB — no entry is better than a confident wrong one.
   */
  const REVIEW = { vie_Latn: 1, hin_Deva: 1, hat_Latn: 1, arb_Arab: 1, kor_Hang: 1, npi_Deva: 1 };

  const AMEN = {
    spa_Latn: 'Amén.',      por_Latn: 'Amém.',      por_PT: 'Amém.',
    fra_Latn: 'Amen.',      deu_Latn: 'Amen.',      ita_Latn: 'Amen.',
    nld_Latn: 'Amen.',      pol_Latn: 'Amen.',      ces_Latn: 'Amen.',
    swe_Latn: 'Amen.',      dan_Latn: 'Amen.',      fin_Latn: 'Aamen.',
    hun_Latn: 'Ámen.',      cat_Latn: 'Amén.',      ron_Latn: 'Amin.',
    tur_Latn: 'Âmin.',      ell_Grek: 'Αμήν.',      rus_Cyrl: 'Аминь.',
    ukr_Cyrl: 'Амінь.',     srp_Cyrl: 'Амин.',      swh_Latn: 'Amina.',
    zho_Hans: '阿们。',      zho_Hant: '阿們。',      kor_Hang: '아멘.',
    vie_Latn: 'A-men.',     hat_Latn: 'Amèn.',      arb_Arab: 'آمين.',
    hin_Deva: 'आमीन।',      urd_Arab: 'آمین۔',      pes_Arab: 'آمین.'
  };

  const HALLELUJAH = {
    spa_Latn: '¡Aleluya!',  por_Latn: 'Aleluia!',   por_PT: 'Aleluia!',
    fra_Latn: 'Alléluia !', deu_Latn: 'Halleluja!', ita_Latn: 'Alleluia!',
    nld_Latn: 'Halleluja!', pol_Latn: 'Alleluja!',  ces_Latn: 'Aleluja!',
    swe_Latn: 'Halleluja!', dan_Latn: 'Halleluja!', fin_Latn: 'Halleluja!',
    hun_Latn: 'Halleluja!', cat_Latn: 'Al·leluia!', ron_Latn: 'Aleluia!',
    ell_Grek: 'Αλληλούια!', rus_Cyrl: 'Аллилуйя!',  ukr_Cyrl: 'Алілуя!',
    srp_Cyrl: 'Алилуја!',   zho_Hans: '哈利路亚！',   zho_Hant: '哈利路亞！',
    kor_Hang: '할렐루야!',   vie_Latn: 'Ha-lê-lu-gia!', hat_Latn: 'Alelouya!',
    arb_Arab: 'هللويا!'
  };

  const HOSANNA = {
    spa_Latn: '¡Hosanna!',  por_Latn: 'Hosana!',    por_PT: 'Hosana!',
    fra_Latn: 'Hosanna !',  deu_Latn: 'Hosianna!',  ita_Latn: 'Osanna!',
    nld_Latn: 'Hosanna!',   pol_Latn: 'Hosanna!',   rus_Cyrl: 'Осанна!',
    ell_Grek: 'Ωσαννά!',    zho_Hans: '和散那！',    zho_Hant: '和散那！',
    kor_Hang: '호산나!',     hat_Latn: 'Ozana!'
  };

  const PHRASES = {
    amen: AMEN,
    hallelujah: HALLELUJAH, halleluyah: HALLELUJAH, alleluia: HALLELUJAH,
    hosanna: HOSANNA, hosana: HOSANNA
  };

  /* The whole utterance, or nothing. Returns null so callers fall through to
     normal translation, which must stay the default path. */
  /* A regional variant inherits its base language's forms. Without this a
     Spain or Portugal listener falls through to NLLB for the single most
     frequent utterance in the service. Canonical list: NLLB_ALIAS. */
  const VARIANT_OF = { por_PT: 'por_Latn', spa_ES: 'spa_Latn', spa_MX: 'spa_Latn' };

  function lookup(text, lang) {
    const table = PHRASES[key(text)];
    if (!table) return null;
    return table[lang] || table[VARIANT_OF[lang]] || null;
  }

  function needsReview(lang) { return !!REVIEW[lang]; }
  function phrases() { return Object.keys(PHRASES); }

  return { lookup, key, needsReview, phrases, PHRASES };
}));