【代码片段】判断UTF8格式文件内容是否带BOM的

        /// <summary>
        /// 判断是否是不带 BOM 的 UTF8 格式
        /// </summary>
        /// <param name="data"></param>
        /// <returns></returns>
        public static bool IsUTF8Bytes(byte[] data)
        {
            int charByteCounter = 1;  //计算当前正分析的字符应还有的字节数
            byte curByte; //当前分析的字节.
            for (int i = 0; i < data.Length; i++)
            {
                curByte = data[i];
                if (charByteCounter == 1)
                {
                    if (curByte >= 0x80)
                    {
                        //判断当前
                        while (((curByte <<= 1) & 0x80) != 0)
                        {
                            charByteCounter++;
                        }
                        //标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X 
                        if (charByteCounter == 1 || charByteCounter > 6)
                        {
                            return false;
                        }
                    }
                }
                else
                {
                    //若是UTF-8 此时第一位必须为1
                    if ((curByte & 0xC0) != 0x80)
                    {
                        return false;
                    }
                    charByteCounter--;
                }
            }
            return true;
        }

猜你喜欢

转载自blog.csdn.net/michelsn/article/details/80287191