asp.net 判断字符串编码格式并转换为GB2312

Question

如何判断用户输入内容是否为GB2312编码格式？
如果不是，怎样强制转换为GB2312格式再保存到数据库？
js和asp.net的解决方法都行，求方法

Answer 1

如果是页面，页面本身有一个编码，你获取到的数据的编码应该和页面编码一致，或者你的Web服务器或应用程序模块进行了编码自动转换，获取到数据的编码就是经过转换的。这个编码应该是已知的。给你一个判断文件编码的做参考，不过意义不大。
/// <summary>
        /// 取得一个文本文件流的编码方式。
        /// </summary>
        /// <param name="stream">文本文件流。</param>
        /// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时，将返回该编码方式。</param>
        /// <returns></returns>
        public static Encoding GetEncoding(FileStream stream, Encoding defaultEncoding)
        {
            Encoding targetEncoding = defaultEncoding;            if (stream != null && stream.Length >= 2)
            {
                // 保存文件流的前4个字节
                byte byte1 = 0;
                byte byte2 = 0;
                byte byte3 = 0;
                byte byte4 = 0;
                // 保存当前Seek位置
                long origPos = stream.Seek(0, SeekOrigin.Begin);
                stream.Seek(0, SeekOrigin.Begin);                int nByte = stream.ReadByte();
                byte1 = Convert.ToByte(nByte);
                byte2 = Convert.ToByte(stream.ReadByte());
                if (stream.Length >= 3)
                {
                    byte3 = Convert.ToByte(stream.ReadByte());
                }
                if (stream.Length >= 4)
                {
                    byte4 = Convert.ToByte(stream.ReadByte());
                }
                // 根据文件流的前4个字节判断Encoding
                // Unicode {0xFF, 0xFE};
                // BE-Unicode {0xFE, 0xFF};
                // UTF8 = {0xEF, 0xBB, 0xBF};                if (byte1 == 0xFE && byte2 == 0xFF)//UnicodeBe
                {
                    targetEncoding = Encoding.BigEndianUnicode;
                }
                else if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode
                {
                    targetEncoding = Encoding.Unicode;
                }
                else
                {
                    if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)
                    {
                        targetEncoding = Encoding.UTF8;
                    }
                    else
                    {
                        int i;
                        if (int.TryParse(stream.Length.ToString(), out i))
                        {
                            BinaryReader r = new BinaryReader(stream, System.Text.Encoding.Default);
                            byte[] ss = r.ReadBytes(i);                            if (IsUTF8Bytes(ss))
                            {
                                targetEncoding = Encoding.UTF8;
                            }
                        }
                    }
                }
                // 恢复Seek位置       
                stream.Seek(origPos, SeekOrigin.Begin);
            }
            return targetEncoding;
        }        /// <summary>
        /// 判断是否是不带 BOM 的 UTF8 格式
        /// </summary>
        /// <param name="data"></param>
        /// <returns></returns>
        private 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--;
                }
            }
            if (charByteCounter > 1)
            {
                throw new Exception("非预期的byte格式!");
            }
            return true;
        }