Question

我使用RichTextBox将RTF中的字符串转换为纯文本，使用以下代码：

private string ConvertToText(string rtf)
{
    if (string.IsNullOrWhiteSpace(rtf)) return string.Empty;

    if (!rtf.Contains("{\\rtf")) return rtf.Trim();  

    using (var helper = new System.Windows.Forms.RichTextBox())
    {
        helper.Rtf = rtf;
        var plainText = helper.Text;

        if (string.IsNullOrWhiteSpace(plainText)) return string.Empty;

        return "<< Rule in Rich Text Format converted to Plain Text >>\n\n" 
            + plainText 
            + "\n\n<< Rule in Rich Text Format converted to Plain Text >>";
    }
}

它适用于所有开发人员计算机，但在部署到Azure网站时不起作用：

{
"$id"             :"1",
"Message"         :"An error has occurred.",
"ExceptionMessage":"Out of memory.",
"ExceptionType"   :"System.OutOfMemoryException",
"StackTrace"      :"   
    at System.Drawing.Graphics.FromHdcInternal(IntPtr hdc)\r\n   
    at System.Drawing.Font.GetHeight()\r\n   
    at System.Drawing.Font.get_Height()\r\n   
    at System.Windows.Forms.Control.get_FontHeight()\r\n   
    at System.Windows.Forms.TextBoxBase.get_PreferredHeight()\r\n   
    at System.Windows.Forms.TextBoxBase.AdjustHeight(Boolean returnIfAnchored)\r\n   
    at System.Windows.Forms.TextBoxBase.set_Multiline(Boolean value)\r\n   
    at System.Windows.Forms.RichTextBox.set_Multiline(Boolean value)\r\n   
    at System.Windows.Forms.RichTextBox..ctor()\r\n   
    at ... "
}

无论RTF字符串的大小，都会发生。我已经在使用＆＃34;复制到本地＆＃34; System.Windows.Forms引用的属性。有没有人有处理RTF和Azure的经验？有没有其他方法可以将RTF转换为纯文本？

Answer 1

这是@Gusman在评论中提出的C++ forum link的改编C＃版本：

public static string ConvertToText(string rtf)
{
    bool slash = false; //indicates if backslash followed by the space
    bool figure_opened = false; //indicates if opening figure brace followed by the space
    bool figure_closed = false; //indicates if closing brace followed by the space
    bool first_space = false; //the else spaces are in plain text and must be included to the result

    if (rtf.Length < 4) return string.Empty;

    int i = 0;
    i = rtf.IndexOf("\\pard");
    if (i < 1) return "";

    var builder = new StringBuilder();
    for (int j = i; j < rtf.Length - 1; j++)
    {
        char ch = rtf[j];
        char nextCh = rtf[j + 1];

        if (ch == '\\' && nextCh == 'p') // appends \n if \pard, except for first
        {
            if (j > i && j < rtf.Length - 4)
            {
                string fiveChars = rtf.Substring(j, 5);
                if (fiveChars.Equals("\\pard"))
                {
                    builder.Append("\n");
                }
            }
        }

        if (ch == '\\' && nextCh == 'u') // to deal correctly with special characters
        {
            string fourChars = rtf.Substring(j + 2, 4);
            string digits = new string(fourChars.TakeWhile(char.IsDigit).ToArray());
            char specialChar = (char)int.Parse(digits);
            builder.Append(specialChar);
            j += digits.Length + 5;
            continue;
        }

        if (ch == '\\' && nextCh == '{') // if the text contains symbol '{'
        {
            slash = false;
            figure_opened = false;
            figure_closed = false;
            first_space = false;
            builder.Append('{');
            j++;
            continue;
        }
        else if (ch == '\\' && nextCh == '}') // if the text contains symbol '}'
        {
            slash = false;
            figure_opened = false;
            figure_closed = false;
            first_space = false;
            builder.Append('}');
            j++;
            continue;
        }
        else if (ch == '\\' && nextCh == '\\') // if the text contains symbol '\'
        {
            slash = false;
            figure_opened = false;
            figure_closed = false;
            first_space = false;
            builder.Append('\\');
            j++;
            continue;
        }
        else if (ch == '\\') // we are looking at the backslash
        {
            first_space = true;
            slash = true;
        }
        else if (ch == '{')
        {
            first_space = true;
            figure_opened = true;
        }
        else if (ch == '}')
        {
            first_space = true;
            figure_closed = true;
        }
        else if (ch == ' ')
        {
            slash = false;
            figure_opened = false;
            figure_closed = false;
        }

        if (!slash && !figure_opened && !figure_closed)
        {
            if (!first_space)
            {
                builder.Append(ch);
            }
            else
            {
                first_space = false;
            }
        }
    }
    return builder.ToString();
}

有效！ = d

RichTextBox在Azure上抛出OutOfMemory

1 个答案: