Pastable version of Balance HTML Tags

<pre class='prettyprint' language='cs'>private static Regex _namedtags = new Regex
    (@&quot;&lt;/?(?&lt;tagname&gt;\w+)[^&gt;]*(\s|$|&gt;)&quot;,
    RegexOptions.Singleline | RegexOptions.ExplicitCapture | RegexOptions.Compiled);

/// &lt;summary&gt;
/// attempt to balance HTML tags in the html string
/// by removing any unmatched opening or closing tags
/// IMPORTANT: we *assume* HTML has *already* been 
/// sanitized and is safe/sane before balancing!
/// 
/// CODESNIPPET: A8591DBA-D1D3-11DE-947C-BA5556D89593
/// &lt;/summary&gt;
public static string BalanceTags(string html)
{
    if (String.IsNullOrEmpty(html)) return html;

// convert everything to lower case; this makes
    // our case insensitive comparisons easier
    MatchCollection tags = _namedtags.Matches(html.ToLowerInvariant());

// no HTML tags present? nothing to do; exit now
    int tagcount = tags.Count;
    if (tagcount == 0) return html;

string tagname;
    string tag;
    const string ignoredtags = &quot;&lt;p&gt;&lt;img&gt;&lt;br&gt;&lt;li&gt;&lt;hr&gt;&quot;;
    int match;
    var tagpaired = new bool[tagcount];
    var tagremove = new bool[tagcount];

// loop through matched tags in forward order
    for (int ctag = 0; ctag &lt; tagcount; ctag++)
    {
        tagname = tags[ctag].Groups[&quot;tagname&quot;].Value;

// skip any already paired tags
        // and skip tags in our ignore list; assume they're self-closed
        if (tagpaired[ctag] || ignoredtags.Contains(&quot;&lt;&quot; + tagname + &quot;&gt;&quot;))
            continue;

tag = tags[ctag].Value;
        match = -1;

if (tag.StartsWith(&quot;&lt;/&quot;))
        {
            // this is a closing tag
            // search backwards (previous tags), look for opening tags
            for (int ptag = ctag - 1; ptag &gt;= 0; ptag--)
            {
                string prevtag = tags[ptag].Value;
                if (!tagpaired[ptag] &amp;&amp; prevtag.Equals(&quot;&lt;&quot; + tagname, StringComparison.InvariantCulture))
                {
                    // minor optimization; we do a simple possibly incorrect match above
                    // the start tag must be &lt;tag&gt; or &lt;tag{space} to match
                    if (prevtag.StartsWith(&quot;&lt;&quot; + tagname + &quot;&gt;&quot;) || prevtag.StartsWith(&quot;&lt;&quot; + tagname + &quot; &quot;))
                    {
                        match = ptag;
                        break;
                    }
                }
            }
        }
        else
        {
            // this is an opening tag
            // search forwards (next tags), look for closing tags
            for (int ntag = ctag + 1; ntag &lt; tagcount; ntag++)
            {
                if (!tagpaired[ntag] &amp;&amp; tags[ntag].Value.Equals(&quot;&lt;/&quot; + tagname + &quot;&gt;&quot;, StringComparison.InvariantCulture))
                {
                    match = ntag;
                    break;
                }
            }
        }

// we tried, regardless, if we got this far
        tagpaired[ctag] = true;
        if (match == -1)
            tagremove[ctag] = true; // mark for removal
        else
            tagpaired[match] = true; // mark paired
    }

// loop through tags again, this time in reverse order
    // so we can safely delete all orphaned tags from the string
    for (int ctag = tagcount - 1; ctag &gt;= 0; ctag--)
    {
        if (tagremove[ctag])
        {
            html = html.Remove(tags[ctag].Index, tags[ctag].Length);
            System.Diagnostics.Debug.WriteLine(&quot;unbalanced tag removed: &quot; + tags[ctag]);
        }
    }

return html;
}</pre>
<a href="http://www.refactormycode.com/codes/360-balance-html-tags" style="color:#fff" title="As seen on RefactorMyCode.com"><img alt="Small_logo" src="http://www.refactormycode.com/images/small_logo.gif" style="border:0" /></a>

Refactor :my => 'code'

Recent

Popular

Pastable version of Balance HTML Tags