tractatus/scripts/translate-gdpr-deepl.js

#!/usr/bin/env node

/**
 * Translate gdpr.json from EN to DE and FR using DeepL API
 *
 * Usage: node scripts/translate-gdpr-deepl.js [--force]
 *
 * Options:
 *   --force    Overwrite existing translations
 *
 * Requires: DEEPL_API_KEY environment variable
 */

require('dotenv').config();
const fs = require('fs');
const path = require('path');
const https = require('https');

const DEEPL_API_KEY = process.env.DEEPL_API_KEY;
const API_URL = 'api.deepl.com'; // Pro API endpoint

const FORCE = process.argv.includes('--force');

if (!DEEPL_API_KEY) {
  console.error('❌ ERROR: DEEPL_API_KEY environment variable not set');
  console.error('   Set it with: export DEEPL_API_KEY="your-key-here"');
  process.exit(1);
}

const EN_FILE = path.join(__dirname, '../public/locales/en/gdpr.json');
const DE_FILE = path.join(__dirname, '../public/locales/de/gdpr.json');
const FR_FILE = path.join(__dirname, '../public/locales/fr/gdpr.json');

// Load JSON files
const enData = JSON.parse(fs.readFileSync(EN_FILE, 'utf8'));
const deData = JSON.parse(fs.readFileSync(DE_FILE, 'utf8'));
const frData = JSON.parse(fs.readFileSync(FR_FILE, 'utf8'));

// DeepL API request function
function translateText(text, targetLang) {
  return new Promise((resolve, reject) => {
    const postData = new URLSearchParams({
      auth_key: DEEPL_API_KEY,
      text: text,
      target_lang: targetLang,
      source_lang: 'EN',
      formality: 'default',
      preserve_formatting: '1',
      tag_handling: 'html'  // Preserve HTML tags
    }).toString();

    const options = {
      hostname: API_URL,
      port: 443,
      path: '/v2/translate',
      method: 'POST',
      headers: {
        'Content-Type': 'application/x-www-form-urlencoded',
        'Content-Length': Buffer.byteLength(postData)
      }
    };

    const req = https.request(options, (res) => {
      let data = '';
      res.on('data', (chunk) => { data += chunk; });
      res.on('end', () => {
        if (res.statusCode === 200) {
          try {
            const response = JSON.parse(data);
            resolve(response.translations[0].text);
          } catch (err) {
            reject(new Error(`Failed to parse response: ${err.message}`));
          }
        } else {
          reject(new Error(`DeepL API error: ${res.statusCode} - ${data}`));
        }
      });
    });

    req.on('error', reject);
    req.write(postData);
    req.end();
  });
}

// Helper to get nested value
function getNestedValue(obj, path) {
  return path.split('.').reduce((current, key) => current?.[key], obj);
}

// Helper to set nested value
function setNestedValue(obj, path, value) {
  const keys = path.split('.');
  const lastKey = keys.pop();
  const target = keys.reduce((current, key) => {
    if (!current[key]) current[key] = {};
    return current[key];
  }, obj);
  target[lastKey] = value;
}

// Recursively find all string values and their paths
function findAllStrings(obj, prefix = '') {
  const strings = [];

  for (const [key, value] of Object.entries(obj)) {
    const currentPath = prefix ? `${prefix}.${key}` : key;

    if (typeof value === 'string') {
      strings.push(currentPath);
    } else if (typeof value === 'object' && value !== null && !Array.isArray(value)) {
      strings.push(...findAllStrings(value, currentPath));
    } else if (Array.isArray(value)) {
      // Handle arrays of strings
      value.forEach((item, index) => {
        if (typeof item === 'string') {
          strings.push(`${currentPath}.${index}`);
        }
      });
    }
  }

  return strings;
}

// Main translation function
async function translateFile(targetLang, targetData, targetFile) {
  console.log(`\n🌐 Translating to ${targetLang}...`);

  const allPaths = findAllStrings(enData);
  let translatedCount = 0;
  let skippedCount = 0;
  let errorCount = 0;

  for (const keyPath of allPaths) {
    const enValue = getNestedValue(enData, keyPath);
    const existingValue = getNestedValue(targetData, keyPath);

    // Skip if already translated (not empty) unless --force flag
    if (!FORCE && existingValue && existingValue.trim().length > 0 && existingValue !== enValue) {
      skippedCount++;
      process.stdout.write('.');
      continue;
    }

    try {
      // Translate
      const translated = await translateText(enValue, targetLang);
      setNestedValue(targetData, keyPath, translated);
      translatedCount++;
      process.stdout.write('✓');

      // Rate limiting: wait 500ms between requests to avoid 429 errors
      await new Promise(resolve => setTimeout(resolve, 500));

    } catch (error) {
      console.error(`\n❌ Error translating ${keyPath}:`, error.message);
      errorCount++;
      process.stdout.write('✗');
    }
  }

  console.log(`\n\n📊 Translation Summary for ${targetLang}:`);
  console.log(`   ✓ Translated: ${translatedCount}`);
  console.log(`   . Skipped (already exists): ${skippedCount}`);
  console.log(`   ✗ Errors: ${errorCount}`);

  // Save updated file
  fs.writeFileSync(targetFile, JSON.stringify(targetData, null, 2) + '\n', 'utf8');
  console.log(`   💾 Saved: ${targetFile}`);
}

// Run translations
async function main() {
  console.log('═══════════════════════════════════════════════════════════');
  console.log('  DeepL Translation: gdpr.json (EN → DE, FR)');
  console.log('═══════════════════════════════════════════════════════════\n');

  if (FORCE) {
    console.log('⚠️  --force flag enabled: Will overwrite existing translations\n');
  }

  const totalStrings = findAllStrings(enData).length;
  console.log(`📝 Total translation keys in EN file: ${totalStrings}`);

  try {
    // Translate to German
    await translateFile('DE', deData, DE_FILE);

    // Translate to French
    await translateFile('FR', frData, FR_FILE);

    console.log('\n✅ Translation complete!');
    console.log('\n💡 Next steps:');
    console.log('   1. Review translations in de/gdpr.json and fr/gdpr.json');
    console.log('   2. Test on local server: npm start');
    console.log('   3. Visit http://localhost:9000/gdpr.html and switch languages');

  } catch (error) {
    console.error('\n❌ Fatal error:', error);
    process.exit(1);
  }
}

main();