C# 根据传入(字节流)BYTE[]判断编码格式是否UTF8 网上转的,地址忘了

public static bool IsTextUTF8(byte[] inputStream)
        {
            int encodingBytesCount = 0;
            bool allTextsAreASCIIChars = true;

            for (int i = 0; i < inputStream.Length; i++)
            {
                byte 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.
                        while ((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;
        }

 

posted @ 2013-05-22 09:52  Everglow  阅读(1889)  评论(0编辑  收藏  举报