public static void Main()
{
// TryMatch() can get a single match
if (IsoDate.TryMatch("2021-02-03T01:23:45.678Z", out var isoDate))
{
Console.WriteLine($"IsoDate: year={isoDate.Year} month={isoDate.Month} day={isoDate.Day}");
}
// IsMatch() allows simple validity checks
var testUsernames = new[] { "foo-bar", "foobar", "3foobar", "foo-bar-", "-foo-bar", "foo--bar" };
foreach (var username in testUsernames)
{
Console.WriteLine($"GithubUsername: {username}: {GithubUsername.IsMatch(username)}");
}
// Matches() allows iterating through several matches
var sourceText =
"This is some example text showing URL matching, for https://example.org. " +
"It will match with IPs http://192.0.2.1 or ftp://some.site.example.org and" +
"also long ones https://user:[email protected]:4433/some/path?query=abc¶m=234.";
foreach (var url in UrlRegex.Matches(sourceText))
{
Console.WriteLine($"Found URL, scheme = {url.Scheme}, fullhost = {url.Fullhost}");
foreach (var path in url.Path)
{
Console.WriteLine(" " + path);
}
}
}
public override List <ExtractResult> Extract(string text)
{
var ret = base.Extract(text);
var urlMatches = UrlRegex.Matches(text);
foreach (Match urlMatch in urlMatches)
{
var tldString = urlMatch.Groups["Tld"].Value;
var tldMatches = TldMatcher.Find(tldString);
if (tldMatches.Any(o => o.Start == 0 && o.End == tldString.Length))
{
ret.Add(new ExtractResult
{
Start = urlMatch.Index,
Length = urlMatch.Length,
Text = urlMatch.Value,
Type = ExtractType,
Data = Constants.URL_REGEX
});
}
}
return(ret);
}
public override IEnumerable <UTCourse> FetchItems()
{
List <UTCourse> results = new List <UTCourse>();
if (this.Content == null)
{
return(results);
}
this.Content = this.Content.Replace("\n", String.Empty).Replace("\r", String.Empty);
MatchCollection matches = CourseRegex.Matches(this.Content);
foreach (Match match in matches)
{
UTCourse course = new UTCourse()
{
Code = match.Groups["code"].Value,
SemesterPrefix = match.Groups["prefix"].Value,
Name = SpaceRegex.Replace(HttpUtility.HtmlDecode(match.Groups["name"].Value).Trim(' ').Trim(' '), " ")
};
string[] properties = AngleRegex.Replace(match.Groups["content"].Value.Replace("<br>", "|"), String.Empty).Split('|');
string description = String.Empty;
bool afterDescription = false;
foreach (string property in properties)
{
if (property.Trim(' ').StartsWith("Prerequisite: "))
{
course.Prerequisites = SpaceRegex.Replace(HttpUtility.HtmlDecode(property.Trim(' ').Substring("Prerequisite: ".Length)), " ");
afterDescription = true;
}
else if (property.Trim(' ').StartsWith("Exclusion: "))
{
course.Exclusions = SpaceRegex.Replace(HttpUtility.HtmlDecode(property.Trim(' ').Substring("Exclusion: ".Length)), " ");
afterDescription = true;
}
else if (property.Trim(' ').StartsWith("Breadth Requirement: "))
{
course.Exclusions = SpaceRegex.Replace(HttpUtility.HtmlDecode(property.Trim(' ').Substring("Breadth Requirement: ".Length)), " ");
afterDescription = true;
}
else if (property.Trim(' ').StartsWith("Corequisite: "))
{
course.Corequisites = SpaceRegex.Replace(HttpUtility.HtmlDecode(property.Trim(' ').Substring("Corequisite: ".Length)), " ");
afterDescription = true;
}
else if (!afterDescription)
{
description += property;
}
}
course.Description = description;
course.Department = SpaceRegex.Replace(HttpUtility.HtmlDecode(description), " ").Trim(' ');
course.Department = UrlRegex.Match(this.Url).Groups["name"].Value.Replace("_", " ");
results.Add(course);
//Console.WriteLine("UTSC Course: " + course.Abbr);
}
return(results);
}
public static void ParseUrls(MessageModel msg)
{
// clone MessageParts
IList <MessagePartModel> parts = new List <MessagePartModel>(msg.MessageParts);
foreach (MessagePartModel part in parts)
{
if (part is UrlMessagePartModel)
{
// no need to reparse URL parts
continue;
}
if (!(part is TextMessagePartModel))
{
continue;
}
TextMessagePartModel textPart = (TextMessagePartModel)part;
Match urlMatch = UrlRegex.Match(textPart.Text);
// OPT: fast regex scan
if (!urlMatch.Success)
{
// no URLs in this MessagePart, nothing to do
continue;
}
// found URL(s)
// remove current MessagePartModel as we need to split it
int idx = msg.MessageParts.IndexOf(part);
msg.MessageParts.RemoveAt(idx);
string[] textPartParts = textPart.Text.Split(new char[] { ' ' });
for (int i = 0; i < textPartParts.Length; i++)
{
string textPartPart = textPartParts[i];
urlMatch = UrlRegex.Match(textPartPart);
if (urlMatch.Success)
{
UrlMessagePartModel urlPart = new UrlMessagePartModel(textPartPart);
//urlPart.ForegroundColor = new TextColor();
msg.MessageParts.Insert(idx++, urlPart);
msg.MessageParts.Insert(idx++, new TextMessagePartModel(" "));
}
else
{
// FIXME: we put each text part into it's own object, instead of combining them (the smart way)
TextMessagePartModel notUrlPart = new TextMessagePartModel(textPartPart + " ");
// restore formatting / colors from the original text part
notUrlPart.IsHighlight = textPart.IsHighlight;
notUrlPart.ForegroundColor = textPart.ForegroundColor;
notUrlPart.BackgroundColor = textPart.BackgroundColor;
notUrlPart.Bold = textPart.Bold;
notUrlPart.Italic = textPart.Italic;
notUrlPart.Underline = textPart.Underline;
msg.MessageParts.Insert(idx++, notUrlPart);
}
}
}
}
private bool IsURLValid()
{
Match match = UrlRegex.Match(_url.Text);
if (!match.Success)
{
return(false);
}
return(true);
}
public void UrlRegex_DoNotMatchUrls([Values(
"http://",
"http://.",
"http://..",
"http://../",
"http://?",
"http://??",
"http://??/",
"http://#",
"http://##",
"http://##/",
"http://foo.bar?q=Spaces should be encoded",
"//",
"//a",
"///a",
"///",
"http:///a",
"foo.com",
"rdar://1234",
"h://test",
"http:// shouldfail.com",
":// should fail",
"http://foo.bar/foo(bar)baz quux",
"http://-error-.invalid/",
"http://-a.b.co",
"http://a.b-.co",
"http://123.123.123",
"http://3628126748",
"http://.www.foo.bar/",
"http://.www.foo.bar./",
"http://go/ogle.com",
"http://foo.bar/ /",
"http://a.b_z.com",
"http://ab_.z.com",
"http://google\\.com",
"http://www(google.com",
"http://www.example.xn--overly-long-punycode-test-string-test-tests-123-test-test123/",
"http://www=google.com",
"https://www.g.com/error\n/bleh/bleh",
"rdar://1234",
"/foo.bar/",
"///www.foo.bar./"
)]
[NotNull]
string argument)
{
var regex = UrlRegex.Create(true);
Assert.IsFalse(regex.IsMatch(argument));
}
public Task CheckAsync(DiscordMessage message)
{
//Set some obvious
MessageId = message.Id;
//Detect URL
var matches = UrlRegex.Match(message.Content);
if (matches.Success)
{
URL = matches.Value;
}
return(Task.CompletedTask);
}
public override RouteData GetRouteData(HttpContextBase httpContext)
{
var route = base.GetRouteData(httpContext);
if (route != null)
{
httpContext.Response.Clear();
httpContext.Response.StatusCode = _responseCode;
var url = GetRequestUrl(httpContext);
var replace = UrlRegex.Replace(url, ReplacePattern);
httpContext.Response.AppendHeader("Location", replace);
httpContext.Response.End();
}
return(null);
}
public void UrlRegex_MatchUrlsInText([Values(
@"Lorem ipsum //dolor.sit
<a href=""http://example.com"">example.com</a>
<a href=""http://example.com/with-path"">with path</a>
[and another](https://another.example.com) and
Foo //bar.net/?q=Query with spaces"
)]
[NotNull]
string argument)
{
var regex = UrlRegex.Create(tlds: false, compiled: true);
Assert.AreEqual(new[]
{
"//dolor.sit",
"http://example.com",
"http://example.com/with-path",
"https://another.example.com",
"//bar.net/?q=Query"
}, argument.Matches(regex).Select(x => x.Value).ToArray());
Assert.IsTrue(regex.IsMatch(argument));
}
private static IEnumerable <string> GetUrlsInMessage(string messages)
{
var matches = UrlRegex.Matches(messages);
return(from object match in matches select match.ToString());
}
public void UrlRegex_MatchUsingListOfTlds([Values(
"foo.com/blah_blah",
"foo.com/blah_blah/",
"foo.com/blah_blah_(wikipedia)",
"foo.com/blah_blah_(wikipedia)_(again)",
"www.example.com/wpstyle/?p=364",
"www.example.com/foo/?bar=baz&inga=42&quux",
"a.b.c.d.e.f.g.h.i.j.k.l.m.n.o.p.q.r.s.t.u.v.w.x.y.z.com",
"mw1.google.com/mw-earth-vectordb/kml-samples/gp/seattle/gigapxl/$[level]/r$[y]_c$[x].jpg",
"user:[email protected]:123/one/two.three?q1=a1&q2=a2#body",
"www.microsoft.xn--comindex-g03d.html.irongeek.com",
"✪df.ws/123",
"localhost/",
"userid:[email protected]:8080",
"userid:[email protected]:8080/",
"*****@*****.**",
"[email protected]/",
"[email protected]:8080",
"[email protected]:8080/",
"userid:[email protected]",
"userid:[email protected]/",
"142.42.1.1/",
"142.42.1.1:8080/",
"➡.ws/䨹",
"⌘.ws",
"⌘.ws/",
"foo.com/blah_(wikipedia)#cite-1",
"foo.com/blah_(wikipedia)_blah#cite-1",
"foo.com/unicode_(✪)_in_parens",
"foo.com/(something)?after=parens",
"☺.damowmow.com/",
"code.google.com/events/#&product=browser",
"j.mp",
"foo.bar/baz",
"foo.bar/?q=Test%20URL-encoded%20stuff",
"-.~_!$&\"()*+\";=:%40:80%2f::::::@example.com",
"1337.net",
"a.b-c.de",
"223.255.255.254",
"example.com?foo=bar",
"example.com#foo",
"localhost:8080",
"foo.ws",
"a.b-c.de",
"223.255.255.254",
"userid:[email protected]",
"➡.ws/䨹",
"//localhost:8080",
"//foo.ws",
"//a.b-c.de",
"//223.255.255.254",
"//userid:[email protected]",
"//➡.ws/䨹",
"www.google.com/unicorn",
"example.com."
)]
[NotNull]
string argument)
{
var regex = UrlRegex.Create(true, false, false);
Assert.IsTrue(regex.IsMatch(argument));
}
