如何从纯文本中检索粗体，斜体和带下划线的单词，并用HTML标记将它们包围起来

Question

What I want to achieve:

Input: (Input text comes from a Excel cell)

This is a string includes bold , italic and underlined words.

Expected output:

This is a <b>string</b> includes <b>bold</b>, <i>italic</i> and <u>underlined</u> words.

What I tried: (This method iterates the plain text by characters not words.)

        StringBuilder html = new StringBuilder();
        StringBuilder fontText = new StringBuilder();
        string path = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "Test.xls");
        Application excel = new Application();
        Workbook wb = excel.Workbooks.Open(path);
        Worksheet excelSheet = wb.ActiveSheet;
        //Read the first cell
        Range cell = excelSheet.Cells[1, 1];
          for (int index = 1; index <= cell.Text.ToString().Length; index++)
            {
              //cell here is a Range object
              Characters ch = cell.get_Characters(index, 1);
              bool bold = (bool) ch.Font.Bold;
              if(bold){
                 if (html.Length == 0)
                      html.Append("<b>");
                 html.Append(ch.Text);
           }
      }
      if (html.Length !=0) html.Append("</b>")

But this method returns all bold texts surrounded by HTML tags like <b>stringbold</b>

Expected result is: <b>string</b> and <b>bold</b>

Any great thoughts on this?

Thanks in advance.

Answer 1

Here's what I would do:

1. Create a helper class that knows about Font styles, and their opening and closing tags, and which can keep track of the "current" font style

2. Start out the class with Regular style, and then in you loop, ask the helper class to insert opening and closing tags if the font style has changed before writing the current character

3. At the end of the loop, ask the helper to insert the proper closing tag

I don't have an Excel interop project to play with, so here's a sample, which you may have to adapt to the specific Excel font types.

First, the helper class:

static class TextHelper
{
    // You may have to use a different type than `FontStyle` 
    // Hopefully ch.Font has some type of `Style` property you can use
    public static FontStyle CurrentStyle { get; set; }
    public static string OpenTag { get { return GetOpenTag(); } }
    public static string CloseTag { get { return GetCloseTag(); } }

    // This will return the closing tag for the current font style, 
    // followed by the opening tag for the new font style
    public static string ChangeStyleIfNeeded(FontStyle newStyle)
    {
        if (newStyle == CurrentStyle) return string.Empty;

        var transitionStyleTags = GetCloseTag();
        CurrentStyle = newStyle;
        transitionStyleTags += GetOpenTag();

        return transitionStyleTags;
    }

    private static string GetOpenTag()
    {
        switch (CurrentStyle)
        {
            case FontStyle.Bold:
                return "<b>";
            case FontStyle.Italic:
                return "<i>";
            case FontStyle.Underline:
                return "<u>";
            default:
                return "";
        }
    }

    private static string GetCloseTag()
    {
        switch (CurrentStyle)
        {
            case FontStyle.Bold:
                return "</b>";
            case FontStyle.Italic:
                return "</i>";
            case FontStyle.Underline:
                return "</u>";
            default:
                return "";
        }
    }
}

Next, the implementation would look something like this:

// Start our helper class with 'Regular' font
TextHelper.CurrentStyle = FontStyle.Regular;
var html = new StringBuilder();

for (int index = 1; index <= cell.Text.ToString().Length; index++)
{
    char ch = cell.get_Characters(index, 1);

    // If the Font of this character is different than the current font, 
    // this will close the old style and open our new style.
    html.Append(TextHelper.ChangeStyleIfNeeded(ch.Font));

    // Append this character
    html.Append(ch.Text);
}

// Close the style at the very end
html.Append(TextHelper.CloseTag);

Answer 2

It took half of my day to figure out this solution.

1.The code works with Bold , Italic and underline characters.

2.The algorithm is little bit complicated. If any optimization available or anyone come up with better solution, please post new answer.

ExcelReader method:

public string ExcelReader(string excelFilePath)
    {
        StringBuilder resultText = new StringBuilder();
        //string excelFilePath = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "Test.xls");
        Application excel = new Application();
        Workbook wb = excel.Workbooks.Open(excelFilePath);
        Worksheet excelSheet = wb.ActiveSheet;
        //Read the first cell
        Range cell = excelSheet.Cells[1, 1];

        //Check if one bold or italic WORD.
        bool IfStop = false;
        //Check if character is the start of bold or italic character.
        bool ifFirstSpecialCharacter = true;
        //Initialize a empty tag
        string tag = "";
        //Check if it is the last index
        bool isLastIndex = false;
        for (int index = 1; index <= cell.Text.ToString().Length; index++)
        {
            //Check if the current character is bold or italic
            bool IfSpecialType = false;
            //cell here is a Range object
            Characters ch = cell.get_Characters(index, 1);
            XlUnderlineStyle temp = (XlUnderlineStyle)ch.Font.Underline;
            bool underline = false;

            if (temp == XlUnderlineStyle.xlUnderlineStyleSingle)
                underline = true;

            bool bold = (bool)ch.Font.Bold;
            bool italic = (bool)ch.Font.Italic;

            if (underline)
            {
                if (tag != "" && tag != "<u>")
                {
                    resultText.Append(tag.Insert(1, "/"));
                    ifFirstSpecialCharacter = true;
                    IfStop = true;
                }
                tag = "<u>";
                IfSpecialType = true;
            }
            if (bold)
            {
                if (tag != "" && tag != "<b>")
                {
                    resultText.Append(tag.Insert(1, "/"));
                    ifFirstSpecialCharacter = true;
                    IfStop = true;
                }
                tag = "<b>";
                IfSpecialType = true;
            }
            if (italic)
            {
                if (tag != "" && tag != "<i>")
                {
                    resultText.Append(tag.Insert(1, "/"));
                    ifFirstSpecialCharacter = true;
                    IfStop = true;
                }
                tag = "<i>";
                IfSpecialType = true;
            }
            if (index == cell.Text.ToString().Length)
                isLastIndex = true;
            DetectSpecialCharracterByType(isLastIndex, resultText, ref tag, IfSpecialType, ref IfStop, ref ifFirstSpecialCharacter, ch);
        }
        wb.Close();
        return resultText.ToString();
    }

DetectSpecialCharacterByType method:

private static void DetectSpecialCharacterByType(bool isLastIndex, StringBuilder fontText, ref string tag, bool ifSpecialType, ref bool IfStop, ref bool ifFirstSpecialCharacter, Characters ch)
    {
        if (ifSpecialType)
        {
            //If it is the first character of the word, put the <b> or <i> at the beginning.
            if (ifFirstSpecialCharacter)
            {
                fontText.Append(tag);
                ifFirstSpecialCharacter = false;
                IfStop = false;
            }
            //This is a edge case.If the last word of the text is bold or italic, put the </b> or </i>
            if (isLastIndex)
            {
                fontText.Append(ch.Text);
                fontText.Append(tag.Insert(1, "/"));
            }
            else
                fontText.Append(ch.Text);
        }
        else
        {
            //If it is the last character of one word, add </b> or </i> at the end.
            if (!IfStop && tag != "")
            {
                fontText.Append(tag.Insert(1, "/"));
                IfStop = true;
                ifFirstSpecialCharacter = true;
                tag = "";
            }
            fontText.Append(ch.Text);
        }
    }

Code perfectly works by simply copy pasting and adding new reference Microsoft.Office.Interop.Excel