#!/usr/bin/env node
// Mechanically extract every { en, pt } string pair from a file or directory,
// sorted and normalised, so a content migration can be proven lossless:
//
//   node .agents/scripts/extract-strings.mjs app.js       > /tmp/before.json
//   node .agents/scripts/extract-strings.mjs src/content/ > /tmp/after.json
//   diff /tmp/before.json /tmp/after.json
//
// A non-empty diff means you altered content. These are hand-written
// translations with deliberate tone — copy them, never retype them.

import { readdirSync, readFileSync, statSync } from 'node:fs';
import { join } from 'node:path';

const target = process.argv[2];
if (!target) {
  console.error('usage: extract-strings.mjs <file|dir>');
  process.exit(2);
}

const walk = (dir) =>
  readdirSync(dir).flatMap((name) => {
    const path = join(dir, name);
    return statSync(path).isDirectory() ? walk(path) : [path];
  });

const files = statSync(target).isDirectory() ? walk(target) : [target];

// Matches `en: '…'` / "en": "…" and the pt counterpart, single or double quoted,
// tolerating escaped quotes inside.
const PAIR = /["']?\b(en|pt)\b["']?\s*:\s*(['"])((?:\\.|(?!\2)[\s\S])*)\2/g;

const strings = [];
for (const file of files) {
  const source = readFileSync(file, 'utf8');
  for (const match of source.matchAll(PAIR)) {
    strings.push({ lang: match[1], value: match[3] });
  }
}

// Sort so file ordering and structure changes do not show up as content changes.
strings.sort((a, b) => (a.lang + a.value).localeCompare(b.lang + b.value));

console.log(JSON.stringify(strings, null, 2));
console.error(`extracted ${strings.length} strings from ${files.length} file(s)`);