church-translate/app/preach.js

/*
 * preach.js — plain English for the model, the preacher's words for the room.
 *
 * NLLB was trained on documents, not sermons. Handed a preaching idiom it
 * translates the words and loses the instruction, and it does it fluently, so
 * nobody watching a caption in a language they cannot read has any way to know.
 * Measured against the shipped model, into Spanish, Portuguese and French:
 *
 *   "Circle that in your Bible."  ->  spa "En su Biblia."        VERB GONE
 *                                     fra "Envoyez-le dans..."   (send it)
 *                                     por "Envolva isso..."      (wrap it)
 *   "Walk it out."                ->  fra "Je vais sortir."      (I'm leaving)
 *   "Let that sink in."           ->  spa "Deja que se hunde."   (drowns)
 *   "Open up to the book of John."->  spa "...la obra de Juan."   (the WORKS of John)
 *
 * Every entry below was measured before and after in at least three languages
 * and kept only where the rewrite was better in more than one. "God showed up."
 * was tested and REMOVED: "Dios apareció" was already right, so the rewrite was
 * just a different guess. Do not add entries by intuition — measure them.
 *
 * CRITICAL: this rewrites ONLY what is sent to the translator. The English
 * caption, the transcript archive and the operator's monitor all keep what was
 * actually said. Normalising the source itself would put words in the
 * preacher's mouth, and one source-side edit propagates to every language and
 * the permanent record at once.
 */
(function (root, factory) {
  if (typeof module === 'object' && module.exports) module.exports = factory();
  else root.Preach = factory();
}(typeof self !== 'undefined' ? self : this, function () {
  'use strict';

  /* Longest and most specific first — "open up to the book of" has to win over
     the general "open up to". Applied in order, each at most once per sentence. */
  const RULES = [
    /* Scripture navigation. "open up to" is the one that produced "obra". */
    [/\bopen up to the book of\b/gi, 'turn to the book of'],
    [/\bopen up to\b/gi,            'turn to'],
    [/\bdrop down to\b/gi,          'go to'],
    [/\bback up to\b/gi,            'go back to'],
    [/\bcircle (that|this|it)\b/gi, 'mark $1'],

    /* Instructions that became statements, or vanished. */
    [/\blet (that|this|it) sink in\b/gi,        'think carefully about $1'],
    [/\bwalk (it|that) out\b/gi,                'put $1 into practice'],
    [/\bunpack (that|this|it)\b/gi,             'explain $1'],
    [/\bcamp out here\b/gi,                     'stay here'],
    [/\bgive God a hand of praise\b/gi,         'applaud to praise God'],
    [/\bput a hand on your neighbou?r\b/gi,     'put a hand on the person next to you'],
    [/\bturn to your neighbou?r\b/gi,           'turn to the person next to you'],

    /* Rhetorical checks. Wrong sense, not wrong words. */
    [/\bare you tracking with me\b/gi,          'are you following me'],
    [/\b(catch|get) (this|that)\b/gi,           'understand $2'],
    [/\bthat will preach\b/gi,                  'that is worth preaching']
  ];

  /*
   * A rewrite must not change how the sentence is capitalised — the target
   * inherits sentence case from the source, and lowercasing the first word
   * produced mid-sentence-looking captions.
   */
  function forTranslation(text) {
    let out = String(text == null ? '' : text);
    if (!out) return out;
    const had = out;
    for (const [re, to] of RULES) out = out.replace(re, to);
    if (out === had) return had;
    /* Restore the opening capital if a rule replaced the first word. */
    if (/^[a-z]/.test(out) && /^[A-Z]/.test(had)) out = out.charAt(0).toUpperCase() + out.slice(1);
    return out;
  }

  /*
   * THE TERMINAL PERIOD ON A SHORT UTTERANCE. One character, and it is the
   * difference between a name and invented dialogue.
   *
   * Measured against the shipped model:
   *   "Peter."     -> spa "¿Qué es eso?"      | "Peter"     -> "Pedro"
   *   "Jesus."     -> spa "¿Qué quieres?"     | "Jesus"     -> "Jesús"
   *   "Matthew."   -> spa "¿Qué es eso?"      | "Matthew"   -> "Mateo"
   *   "Habakkuk."  -> fra "Habakuk est mort"  | "Habakkuk"  -> "Habakuk"
   *   "Simon Peter." -> spa "Sí, es el Simon Peter." | -> "Simón Pedro"
   *
   * With the period the model reads a complete conversational turn and answers
   * it; without, it translates the term. A preacher naming people one at a time
   * — "Peter. James. John." — got back a run of questions containing no names.
   *
   * Only the PERIOD is removed, and only from utterances of three words or
   * fewer. "?" and "!" carry real meaning and are left alone, and a full
   * sentence needs its punctuation for the model to parse it at all.
   */
  const SHORT_WORDS_FOR_DOT = 3;

  function stripShortPeriod(text) {
    const s = String(text == null ? '' : text);
    const t = s.trim();
    if (!/[^.!?]\.$/.test(t)) return { text: s, hadPeriod: false };
    if (t.split(/\s+/).filter(Boolean).length > SHORT_WORDS_FOR_DOT) return { text: s, hadPeriod: false };
    return { text: t.slice(0, -1), hadPeriod: true };
  }

  /* Put the period back, so the caption and the voice both get a finished line
     (espeak takes its final intonation from terminal punctuation). */
  function restorePeriod(out, hadPeriod) {
    const s = String(out == null ? '' : out).trim();
    if (!hadPeriod || !s) return s;
    return /[.!?\u3002\uff01\uff1f\u061f]$/.test(s) ? s : s + '.';
  }

  function rules() { return RULES.length; }

  return { forTranslation, stripShortPeriod, restorePeriod, rules, RULES };
}));