Question

Is there any .Net library to remove all problematic characters of a string and only leave alphanumeric, hyphen and underscore (or similar subset) in an intelligent way? This is for using in URLs, file names, etc.

I’m looking for something similar to stringex which can do the following:

A simple prelude

“simple English”.to_url =>
“simple-english”

“it’s nothing at all”.to_url =>
“its-nothing-at-all”

“rock & roll”.to_url =>
“rock-and-roll”

Let’s show off

“$12 worth of Ruby power”.to_url =>
“12-dollars-worth-of-ruby-power”

“10% off if you act now”.to_url =>
“10-percent-off-if-you-act-now”

You don’t even wanna trust Iconv for this next part

“kick it en Français”.to_url =>
“kick-it-en-francais”

“rock it Español style”.to_url =>
“rock-it-espanol-style”

“tell your readers 你好”.to_url =>
“tell-your-readers-ni-hao”

Answer 1

I couldn’t find any library that does it, like in Ruby, so I ended writing my own method. This is it in case anyone cares:

/// <summary>
/// Turn a string into something that's URL and Google friendly.
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static string ForUrl(this string str) {
  return str.ForUrl(true);
}
public static string ForUrl(this string str, bool MakeLowerCase) {
  // Go to lowercase.
  if (MakeLowerCase) {
    str = str.ToLower();
  }

  // Replace accented characters for the closest ones:
  char[] from = "ÂÃÄÀÁÅÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝàáâãäåçèéêëìíîïðñòóôõöøùúûüýÿ".ToCharArray();
  char[] to = "AAAAAACEEEEIIIIDNOOOOOOUUUUYaaaaaaceeeeiiiidnoooooouuuuyy".ToCharArray();
  for (int i = 0; i < from.Length; i++) {
    str = str.Replace(from[i], to[i]);
  }

  // Thorn http://en.wikipedia.org/wiki/%C3%9E
  str = str.Replace("Þ", "TH");
  str = str.Replace("þ", "th");

  // Eszett http://en.wikipedia.org/wiki/%C3%9F
  str = str.Replace("ß", "ss");

  // AE http://en.wikipedia.org/wiki/%C3%86
  str = str.Replace("Æ", "AE");
  str = str.Replace("æ", "ae");

  // Esperanto http://en.wikipedia.org/wiki/Esperanto_orthography
  from = "ĈĜĤĴŜŬĉĝĥĵŝŭ".ToCharArray();
  to = "CXGXHXJXSXUXcxgxhxjxsxux".ToCharArray();
  for (int i = 0; i < from.Length; i++) {
    str = str.Replace(from[i].ToString(), "{0}{1}".Args(to[i*2], to[i*2+1]));
  }

  // Currencies.
  str = new Regex(@"([¢€£\$])([0-9\.,]+)").Replace(str, @"$2 $1");
  str = str.Replace("¢", "cents");
  str = str.Replace("€", "euros");
  str = str.Replace("£", "pounds");
  str = str.Replace("$", "dollars");

  // Ands
  str = str.Replace("&", " and ");

  // More aesthetically pleasing contractions
  str = str.Replace("'", "");
  str = str.Replace("’", "");

  // Except alphanumeric, everything else is a dash.
  str = new Regex(@"[^A-Za-z0-9-]").Replace(str, "-");

  // Remove dashes at the begining or end.
  str = str.Trim("-".ToCharArray());

  // Compact duplicated dashes.
  str = new Regex("-+").Replace(str, "-");

  // Let's url-encode just in case.
  return str.UrlEncode();
}