/* Run the lexicon over 5,954 rows of real Spanish output and inspect EVERY
   change. A lexicon that corrupts correct Spanish is worse than no lexicon. */
const fs=require('fs'), vm=require('vm');
const B=require('./bible-lexicon.js');
const src=fs.readFileSync('engine.js','utf8');
const sb={console};vm.createContext(sb);
vm.runInContext(src.slice(src.indexOf('const SCRIPT_NO_SPACES'), src.indexOf('function applyFixes')), sb);
const rows=require('/tmp/es-corpus.json');
const bl=B.forLanguage('spa_Latn');
const pairs=Object.keys(bl).map(from=>({from,to:bl[from]}));
let n=0; const seen={};
for (const r of rows){
  const es=String((r.tr&&r.tr.spa_Latn)||''); if(!es) continue;
  const out=sb.applyTable(es,pairs);
  if(out===es) continue; n++;
  const a=es.split(/\s+/),b=out.split(/\s+/),d=[];
  for(let i=0;i<Math.max(a.length,b.length);i++) if(a[i]!==b[i]) d.push((a[i]||'')+' -> '+(b[i]||''));
  const k=d.join('  |  '); seen[k]=(seen[k]||0)+1;
}
console.log('rows changed by the lexicon: '+n+'  ('+(n/rows.length*100).toFixed(2)+'%)\n');
console.log('EVERY change:');
Object.entries(seen).sort((a,b)=>b[1]-a[1]).forEach(([d,c])=>console.log('  '+String(c).padStart(3)+'x  '+d));