Auto Detect Encoding can not work / Inaccurate results

[AtlantisDe]

Description

Auto Detect Encoding can not work
tp web Encoding is gb2312 / (936)
Inaccurate results

Test CODE Inaccurate results (AutoDetectCharsetEncoding )

var scrapingBrowser_demo001 = new ScrapySharp.Network.ScrapingBrowser()
{
 AutoDetectCharsetEncoding = true
};
ScrapySharp.Network.WebPage homePage_demo001 = 
scrapingBrowser_demo001.NavigateToPage(
new Uri("https://news.163.com/19/0717/11/EK9KFG4A0001885B.html"));

tks very much

[AtlantisDe]

Here is demo code

• You can refer to the following code. The running result is not very accurate.
• zzzprojects/html-agility-pack#320

public static System.Text.Encoding GetType(string FILE_NAME)
{
    FileStream fs = new FileStream(FILE_NAME, FileMode.Open, FileAccess.Read);
    Encoding r = GetType(fs);
    fs.Close();
    return r;
}

public static System.Text.Encoding GetType(FileStream fs)
{
    byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };
    byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
    byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //带BOM 
    Encoding reVal = Encoding.Default;

    BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
    int i;
    int.TryParse(fs.Length.ToString(), out i);
    byte[] ss = r.ReadBytes(i);
    if (IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
    {
        reVal = Encoding.UTF8;
    }
    else if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
    {
        reVal = Encoding.BigEndianUnicode;
    }
    else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41)
    {
        reVal = Encoding.Unicode;
    }
    r.Close();
    return reVal;

}

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;
}

public static System.Text.Encoding GetType(Stream fs)
{
    byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };
    byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
    byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //带BOM 
    Encoding reVal = Encoding.Default;

    BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
    int i;
    int.TryParse(fs.Length.ToString(), out i);
    byte[] ss = r.ReadBytes(i);
    if (IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF))
    {
        reVal = Encoding.UTF8;
    }
    else if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
    {
        reVal = Encoding.BigEndianUnicode;
    }
    else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41)
    {
        reVal = Encoding.Unicode;
    }
    r.Close();
    return reVal;

}