Question

I have read a html file as string builder.Now I want to put anchor tag between h1,h2,and h3 and to give different id and href link. So how can I achive this.I want following thing to do.
I have tried Sb.Replace("<h1>", "<h1> <a id=1>"); but I can not give uniqe Id to anchor tag.So how can I read all h1,h2 and h3 and put anchor tag and give unique id to anchor tag.

Answer 1

You can call Regex.Replace in the System.Text.RegularExpressions namespace and define a custom MatchEvaluator callback where you assign the new ids.

Something like the following:

var regHeaders = new Regex(@"<(?<close>/)?h(?<header>\d)\s*>", RegexOptions.Compiled | RegexOptions.IgnoreCase);
var replaced = regHeaders.Replace(sb.ToString(), new MatchEvaluator(EvaluateHeaders));

And define the EvaluateHeaders callback something like this:

private static string EvaluateHeaders(Match m)
{
    bool closeTag = m.Groups["close"].Success;
    switch (int.Parse(m.Groups["header"].Value))
    {
        case 1: // h1
            return closeTag ? "</a></h1>" : "<h1><a href=\"header1\">Header1";
        // todo: your own implementation of the various other headers.
        default:
            return m.Value;
    }
}

EDIT
In light of your latest comment, I’ve changed the code to the following:

var regHeaders = new Regex(@"<h(?<header>\d)\s*>(?<content>.+?)</h\1>", RegexOptions.Compiled | RegexOptions.IgnoreCase | RegexOptions.Singleline);
var replaced = regHeaders.Replace(sb.ToString(), EvaluateHeaders);

private static string EvaluateHeaders(Match m)
{
    switch(int.Parse(m.Groups["header"].Value))
    {
        case 1: // <h1>content</h1>
            return string.Format("<h1><a href=\"#\" id=\"{0}\">{0}</a><h1>", m.Groups["content"].Value);
        default:
            return m.Value;
    }
}