Question

I’m searching for strings inside a word document using the Open XML Office SDK 2.0 and list those.

    MatchCollection Matches;
    using (WordprocessingDocument wordDoc = WordprocessingDocument.Open(txtLocation.Text, true))
    {
        string docText = null;
        using (StreamReader sr = new StreamReader(wordDoc.MainDocumentPart.GetStream()))
        {
            docText = sr.ReadToEnd();
        }
        Regex regex = new   Regex(@"\(.*?\)");
        Matches = regex.Matches(docText);
    }
    int i = 0;
    while (i < Matches.Count)
    {    Label lb = new Label();
         lb.Text = Matches[i].ToString();
         lb.Location = new System.Drawing.Point(24, (28 + i * 24));
         this.panel1.Controls.Add(lb);
         i++;
     }

The problem is that sometimes it returnes the right string, eg: (HelloWorld) but sometimes its something totally different with tags like: < w:rFonts w:ascii=”Arial” w:hAnsi=”Arial” w:cs=”Arial”/ >

How do I get rid of those?

Answer 1

Found out what I had to do, run the string to another Regex.Replace.
This one replaces all <> tags (so XML/HTML)

String str = Matches[i].ToString();
str = Regex.Replace(str, @"<(.|\n)*?>", "");
lb.Text  = str;