/* The whole chain as engine.js runs it: split -> liturgy-or-NLLB -> guard. */
import { pipeline, env } from '@huggingface/transformers';
import { createRequire } from 'module';
import os from 'os'; import path from 'path'; import fs from 'fs'; import vm from 'vm';
const require = createRequire(import.meta.url);
const Liturgy = require('./liturgy.js');
const Guard = require('./mt-guard.js');

const src = fs.readFileSync('engine.js','utf8');
const sb={console}; vm.createContext(sb);
vm.runInContext(src.match(/^const ABBREV_TAIL = .*$/m)[0], sb);
const grab=(n)=>{const i=src.indexOf('function '+n+'(');let d=0;for(let k=src.indexOf('{',i);k<src.length;k++){if(src[k]==='{')d++;else if(src[k]==='}'&&--d===0)return src.slice(i,k+1);}};
vm.runInContext(grab('splitSentences'), sb);

env.allowLocalModels=false;
env.cacheDir=path.join(os.homedir(),'Library/Application Support/Church Translate Models');
const pipe=await pipeline('translation','Xenova/nllb-200-distilled-600M',{dtype:'fp32'});

const CASES=['God is good. Amen.','Amen.','Hallelujah.','Donald Trump.',
             'Can I get an amen?','Jesus wept. Amen.','Dr. Luke wrote this. Amen.'];
const LANGS=['spa_Latn','fra_Latn','deu_Latn','zho_Hans'];

for (const text of CASES) {
  console.log('\n"'+text+'"   -> '+JSON.stringify(sb.splitSentences(text)));
  for (const lang of LANGS) {
    const parts=[];
    for (const s of sb.splitSentences(text)) {
      const set=Liturgy.lookup(s,lang);
      if (set) { parts.push(set+'  [liturgy]'); continue; }
      const o=await pipe(s,{src_lang:'eng_Latn',tgt_lang:lang});
      const raw=(Array.isArray(o)?o[0]:o).translation_text.trim();
      const g=Guard.clean(s,raw);
      parts.push(g.text + (g.trimmed?'  [guard: '+g.reason.slice(0,40)+']':''));
    }
    console.log('   '+lang+'  '+parts.join('  |  '));
  }
}