Function utf8ToBytes

stackgl_modules/index.js:1419–1481

(string, units)

  return str;
}
function utf8ToBytes(string, units) {
  units = units || Infinity;
  var codePoint;
  var length = string.length;
  var leadSurrogate = null;
  var bytes = [];
  for (var i = 0; i < length; ++i) {
    codePoint = string.charCodeAt(i);

    // is surrogate component
    if (codePoint > 0xD7FF && codePoint < 0xE000) {
      // last char was a lead
      if (!leadSurrogate) {
        // no lead yet
        if (codePoint > 0xDBFF) {
          // unexpected trail
          if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD);
          continue;
        } else if (i + 1 === length) {
          // unpaired lead
          if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD);
          continue;
        }

        // valid lead
        leadSurrogate = codePoint;
        continue;
      }

      // 2 leads in a row
      if (codePoint < 0xDC00) {
        if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD);
        leadSurrogate = codePoint;
        continue;
      }

      // valid surrogate pair
      codePoint = (leadSurrogate - 0xD800 << 10 | codePoint - 0xDC00) + 0x10000;
    } else if (leadSurrogate) {
      // valid bmp char, but last char was a lead
      if ((units -= 3) > -1) bytes.push(0xEF, 0xBF, 0xBD);
    }
    leadSurrogate = null;

    // encode utf8
    if (codePoint < 0x80) {
      if ((units -= 1) < 0) break;
      bytes.push(codePoint);
    } else if (codePoint < 0x800) {
      if ((units -= 2) < 0) break;
      bytes.push(codePoint >> 0x6 | 0xC0, codePoint & 0x3F | 0x80);
    } else if (codePoint < 0x10000) {
      if ((units -= 3) < 0) break;
      bytes.push(codePoint >> 0xC | 0xE0, codePoint >> 0x6 & 0x3F | 0x80, codePoint & 0x3F | 0x80);
    } else if (codePoint < 0x110000) {
      if ((units -= 4) < 0) break;
      bytes.push(codePoint >> 0x12 | 0xF0, codePoint >> 0xC & 0x3F | 0x80, codePoint >> 0x6 & 0x3F | 0x80, codePoint & 0x3F | 0x80);
    } else {