// Test filename sanitization for Unicode characters

function sanitizeFilename(filename) {
  // Remove path traversal attempts FIRST from entire filename
  let cleaned = filename.replace(/\.\./g, '').trim();

  // Split filename and extension
  const lastDotIndex = cleaned.lastIndexOf('.');
  let baseName = lastDotIndex > 0 ? cleaned.substring(0, lastDotIndex) : cleaned;
  const extension = lastDotIndex > 0 ? cleaned.substring(lastDotIndex) : '';

  // Remove dangerous characters from base name
  baseName = baseName
    .replace(/[<>:"/\\|?*\x00-\x1f]/g, '') // Remove dangerous chars
    .trim();

  // Replace non-ASCII characters with ASCII equivalents or remove them
  // This prevents S3 signature mismatches with MinIO
  baseName = baseName
    .normalize('NFD') // Decompose combined characters (é -> e + ´)
    .replace(/[\u0300-\u036f]/g, '') // Remove diacritical marks
    .replace(/[^\x20-\x7E]/g, '_') // Replace any remaining non-ASCII with underscore
    .replace(/[^\w\s\-_.]/g, '_') // Replace special chars (except word chars, space, dash, underscore, dot) with underscore
    .replace(/\s+/g, '_') // Replace spaces with underscores
    .replace(/_{2,}/g, '_') // Collapse multiple underscores
    .replace(/^_+|_+$/g, ''); // Remove leading/trailing underscores

  // Ensure we still have a valid base name
  if (baseName.length === 0) {
    baseName = 'file';
  }

  // Sanitize extension (remove only dangerous chars, keep the dot)
  let sanitizedExt = extension
    .replace(/[<>:"/\\|?*\x00-\x1f]/g, '')
    .replace(/[^\x20-\x7E]/g, '')
    .toLowerCase();

  // Ensure extension starts with a dot and is reasonable
  if (sanitizedExt && !sanitizedExt.startsWith('.')) {
    sanitizedExt = '.' + sanitizedExt;
  }
  if (sanitizedExt.length > 10) {
    sanitizedExt = sanitizedExt.substring(0, 10);
  }

  const result = baseName + sanitizedExt;
  return result.substring(0, 255); // Limit total length
}

// Test cases
const testCases = [
  'Ущелье.png', // Cyrillic (Russian)
  '测试文件.jpg', // Chinese
  'test-file.png', // ASCII
  'café-français.jpg', // French with accents
  '🎉party🎊.gif', // Emoji
  'test_مرحبا.webp', // Arabic
  'file@#$%.png', // Special chars
  '../../../etc/passwd', // Path traversal
  '...hidden.txt', // Leading dots
];

console.log('Filename Sanitization Test Results:\n');
console.log('=' .repeat(80));

testCases.forEach(filename => {
  const sanitized = sanitizeFilename(filename);
  console.log(`Original:  ${filename}`);
  console.log(`Sanitized: ${sanitized}`);
  console.log('-'.repeat(80));
});