golang IsTextUTF8

IsTextUTF8.go

func IsTextUTF8(inputStream []byte) bool {
	encodingBytesCount := 0
    allTextsAreASCIIChars := true;
 
    for  i := 0; i < len(inputStream); i++ {
        current := inputStream[i]

        if (current & 0x80) == 0x80 {                    
            allTextsAreASCIIChars = false
        }
        // First byte
        if encodingBytesCount == 0 {
            if (current & 0x80) == 0 {
                // ASCII chars, from 0x00-0x7F
                continue
            }
 
            if (current & 0xC0) == 0xC0 {
                encodingBytesCount = 1
                current <<= 2
 
                // More than two bytes used to encoding a unicode char.
                // Calculate the real length.
                for (current & 0x80) == 0x80 {
                    current <<= 1;
                    encodingBytesCount++;
                }
            }  else  {
                // Invalid bits structure for UTF8 encoding rule.
                return false;
            }
        }  else {
            // Following bytes, must start with 10.
            if (current & 0xC0) == 0x80 {                        
                encodingBytesCount--
            }else{
                // Invalid bits structure for UTF8 encoding rule.
                return false
            }
        }
    }
 
    if encodingBytesCount != 0 {
        // Invalid bits structure for UTF8 encoding rule.
        // Wrong following bytes count.
        return false
    }
 
    // Although UTF8 supports encoding for ASCII chars, we regard as a input stream, whose contents are all ASCII as default encoding.
    return !allTextsAreASCIIChars
}