Encoding Utilities

// String to hex
function textToHex(text) {
  return Array.from(new TextEncoder().encode(text))
    .map(b => b.toString(16).padStart(2, '0'))
    .join(' ');
}

// Hex to string
function hexToText(hex) {
  const bytes = hex.replace(/\s/g, '').match(/.{2}/g)
    .map(b => parseInt(b, 16));
  return new TextDecoder().decode(new Uint8Array(bytes));
}

// String to binary (8-bit per char)
function textToBinary(text) {
  return Array.from(new TextEncoder().encode(text))
    .map(b => b.toString(2).padStart(8, '0'))
    .join(' ');
}

// Binary to string
function binaryToText(binary) {
  const bytes = binary.split(' ')
    .map(b => parseInt(b, 2));
  return new TextDecoder().decode(new Uint8Array(bytes));
}

// String to decimal (Unicode code points)
function textToDecimal(text) {
  return Array.from(text)
    .map(c => c.codePointAt(0).toString())
    .join(' ');
}

// Usage
const text = 'Hello';
console.log(textToHex(text));       // 48 65 6c 6c 6f
console.log(textToBinary(text));    // 01001000 01100101 01101100 01101100 01101111
console.log(textToDecimal(text));   // 72 101 108 108 111
console.log(hexToText('48 65 6c 6c 6f')); // Hello

function detectEncoding(bytes) {
  // Check for BOM (Byte Order Mark)
  if (bytes[0] === 0xEF && bytes[1] === 0xBB && bytes[2] === 0xBF) {
    return { encoding: 'UTF-8', bom: true, confidence: 'high' };
  }
  if (bytes[0] === 0xFF && bytes[1] === 0xFE) {
    return { encoding: 'UTF-16 LE', bom: true, confidence: 'high' };
  }
  if (bytes[0] === 0xFE && bytes[1] === 0xFF) {
    return { encoding: 'UTF-16 BE', bom: true, confidence: 'high' };
  }

  // Check for valid UTF-8 sequences
  let isValidUTF8 = true;
  let i = 0;
  while (i < bytes.length) {
    if (bytes[i] <= 0x7F) { i++; continue; }
    if ((bytes[i] & 0xE0) === 0xC0) { i += 2; continue; }
    if ((bytes[i] & 0xF0) === 0xE0) { i += 3; continue; }
    if ((bytes[i] & 0xF8) === 0xF0) { i += 4; continue; }
    isValidUTF8 = false;
    break;
  }

  if (isValidUTF8) {
    return { encoding: 'UTF-8', bom: false, confidence: 'medium' };
  }

  // Check for high bytes in Latin-1 range
  const hasHighBytes = bytes.some(b => b > 127);
  if (hasHighBytes) {
    return { encoding: 'Latin-1 (ISO-8859-1)', bom: false, confidence: 'low' };
  }

  return { encoding: 'ASCII', bom: false, confidence: 'high' };
}

// Usage
const sample = new TextEncoder().encode('Hello, 世界');
console.log(detectEncoding(sample));
// { encoding: 'UTF-8', bom: false, confidence: 'medium' }