C# code to linkify urls in a string

Question

Does anyone have any good c# code (and regular expressions) that will parse a string and \"linkify\" any urls that may be in the string?

Answer 1

There is class:

public class TextLink
{
    #region Properties

    public const string BeginPattern = "((http|https)://)?(www.)?";

    public const string MiddlePattern = @"([a-z0-9\-]*\.)+[a-z]+(:[0-9]+)?";

    public const string EndPattern = @"(/\S*)?";

    public static string Pattern { get { return BeginPattern + MiddlePattern + EndPattern; } }

    public static string ExactPattern { get { return string.Format("^{0}$", Pattern); } }

    public string OriginalInput { get; private set; }

    public bool Valid { get; private set; }

    private bool _isHttps;

    private string _readyLink;

    #endregion

    #region Constructor

    public TextLink(string input)
    {
        this.OriginalInput = input;

        var text = Regex.Replace(input, @"(^\s)|(\s$)", "", RegexOptions.IgnoreCase);

        Valid = Regex.IsMatch(text, ExactPattern);

        if (Valid)
        {
            _isHttps = Regex.IsMatch(text, "^https:", RegexOptions.IgnoreCase);
            // clear begin:
            _readyLink = Regex.Replace(text, BeginPattern, "", RegexOptions.IgnoreCase);
            // HTTPS
            if (_isHttps)
            {
                _readyLink = "https://www." + _readyLink;
            }
            // Default
            else
            {
                _readyLink = "http://www." + _readyLink;
            }
        }
    }

    #endregion

    #region Methods

    public override string ToString()
    {
        return _readyLink;
    }

    #endregion
}

Use it in this method:

public static string ReplaceUrls(string input)
{
    var result = Regex.Replace(input.ToSafeString(), TextLink.Pattern, match =>
    {
        var textLink = new TextLink(match.Value);
        return textLink.Valid ?
            string.Format("{1}", textLink, textLink.OriginalInput) :
            textLink.OriginalInput;
    });
    return result;
}

Test cases:

[TestMethod]
public void RegexUtil_TextLink_Parsing()
{
    Assert.IsTrue(new TextLink("smthing.com").Valid);
    Assert.IsTrue(new TextLink("www.smthing.com/").Valid);
    Assert.IsTrue(new TextLink("http://smthing.com").Valid);
    Assert.IsTrue(new TextLink("http://www.smthing.com").Valid);
    Assert.IsTrue(new TextLink("http://www.smthing.com/").Valid);
    Assert.IsTrue(new TextLink("http://www.smthing.com/publisher").Valid);

    // port
    Assert.IsTrue(new TextLink("http://www.smthing.com:80").Valid);
    Assert.IsTrue(new TextLink("http://www.smthing.com:80/").Valid);
    // https
    Assert.IsTrue(new TextLink("https://smthing.com").Valid);

    Assert.IsFalse(new TextLink("").Valid);
    Assert.IsFalse(new TextLink("smthing.com.").Valid);
    Assert.IsFalse(new TextLink("smthing.com-").Valid);
}

[TestMethod]
public void RegexUtil_TextLink_ToString()
{
    // default
    Assert.AreEqual("http://www.smthing.com", new TextLink("smthing.com").ToString());
    Assert.AreEqual("http://www.smthing.com", new TextLink("http://www.smthing.com").ToString());
    Assert.AreEqual("http://www.smthing.com/", new TextLink("smthing.com/").ToString());

    Assert.AreEqual("https://www.smthing.com", new TextLink("https://www.smthing.com").ToString());
}