从xhtml文档中删除未关闭的打开标签

这应该起作用:

public static class XHTMLCleanerUpperThingy
{
    private const string p = "<p>";
    private const string closingp = "</p>";

    public static string CleanUpXHTML(string xhtml)
    {
        StringBuilder builder = new StringBuilder(xhtml);
        for (int idx = 0; idx < xhtml.Length; idx++)
        {
            int current;
            if ((current = xhtml.IndexOf(p, idx)) != -1)
            {
                int idxofnext = xhtml.IndexOf(p, current + p.Length);
                int idxofclose = xhtml.IndexOf(closingp, current);

                // if there is a next <p> tag
                if (idxofnext > 0)
                {
                    // if the next closing tag is farther than the next <p> tag
                    if (idxofnext < idxofclose)
                    {
                        for (int j = 0; j < p.Length; j++)
                        {
                            builder[current + j] = ' ';
                        }
                    }
                }
                // if there is not a final closing tag
                else if (idxofclose < 0)
                {
                    for (int j = 0; j < p.Length; j++)
                    {
                        builder[current + j] = ' ';
                    }
                }
            }
        }

        return builder.ToString();
    }
}

你必须找出,什么样的DOM树被创建了。它可以解释为

<p><strong>Company Registration No.1</strong> </p>
<p><strong>Company Registration No.2</strong></p>

<p>      <!-- extra tag -->
  <p>      <!-- extra tag -->
    <hr/>     
    <p><strong> HALL WOOD (LEEDS) LIMITED</strong><br/></p>
    <p><strong>REPORT AND FINANCIAL STATEMENTS </strong></p>
  </p>
</p>

或

<p><strong>Company Registration No.1</strong> </p>
<p><strong>Company Registration No.2</strong></p>

<p></p>      <!-- extra tag -->
<p></p>      <!-- extra tag -->
<hr/>     
<p><strong> HALL WOOD (LEEDS) LIMITED</strong><br/></p>
<p><strong>REPORT AND FINANCIAL STATEMENTS </strong></p>