function utf8Slice()

in src/aws-client.js [15813:15884]


  function utf8Slice (buf, start, end) {
    end = Math.min(buf.length, end)
    var res = []
  
    var i = start
    while (i < end) {
      var firstByte = buf[i]
      var codePoint = null
      var bytesPerSequence = (firstByte > 0xEF) ? 4
        : (firstByte > 0xDF) ? 3
        : (firstByte > 0xBF) ? 2
        : 1
  
      if (i + bytesPerSequence <= end) {
        var secondByte, thirdByte, fourthByte, tempCodePoint
  
        switch (bytesPerSequence) {
          case 1:
            if (firstByte < 0x80) {
              codePoint = firstByte
            }
            break
          case 2:
            secondByte = buf[i + 1]
            if ((secondByte & 0xC0) === 0x80) {
              tempCodePoint = (firstByte & 0x1F) << 0x6 | (secondByte & 0x3F)
              if (tempCodePoint > 0x7F) {
                codePoint = tempCodePoint
              }
            }
            break
          case 3:
            secondByte = buf[i + 1]
            thirdByte = buf[i + 2]
            if ((secondByte & 0xC0) === 0x80 && (thirdByte & 0xC0) === 0x80) {
              tempCodePoint = (firstByte & 0xF) << 0xC | (secondByte & 0x3F) << 0x6 | (thirdByte & 0x3F)
              if (tempCodePoint > 0x7FF && (tempCodePoint < 0xD800 || tempCodePoint > 0xDFFF)) {
                codePoint = tempCodePoint
              }
            }
            break
          case 4:
            secondByte = buf[i + 1]
            thirdByte = buf[i + 2]
            fourthByte = buf[i + 3]
            if ((secondByte & 0xC0) === 0x80 && (thirdByte & 0xC0) === 0x80 && (fourthByte & 0xC0) === 0x80) {
              tempCodePoint = (firstByte & 0xF) << 0x12 | (secondByte & 0x3F) << 0xC | (thirdByte & 0x3F) << 0x6 | (fourthByte & 0x3F)
              if (tempCodePoint > 0xFFFF && tempCodePoint < 0x110000) {
                codePoint = tempCodePoint
              }
            }
        }
      }
  
      if (codePoint === null) {
        // we did not generate a valid codePoint so insert a
        // replacement char (U+FFFD) and advance only 1 byte
        codePoint = 0xFFFD
        bytesPerSequence = 1
      } else if (codePoint > 0xFFFF) {
        // encode to utf16 (surrogate pair dance)
        codePoint -= 0x10000
        res.push(codePoint >>> 10 & 0x3FF | 0xD800)
        codePoint = 0xDC00 | codePoint & 0x3FF
      }
  
      res.push(codePoint)
      i += bytesPerSequence
    }
  
    return decodeCodePointsArray(res)
  }