using System;
using System.Text.RegularExpressions;
public class Example
{
public static void Main()
{
string pattern = @"(?:([-‐‑‒–—―−⁃﹘﹣－])|(?:&(?:(?:#x(2d|201[0-5]|2212|2043|fe58|fe63|ff0d))|(?:#(45|820[89]|821[0123]|8722|8259|65112|65123|65293))|(hyphen|[nm]?dash|hybull|horbar|minus));?))";
string input = @"This captures an entity even if it lacks the ';', which is commonly encountered in the wild.
kbdash - - - - -; -
dash ‐ ‐ ‐ ‐ ‐ ‐; ‐
hyphen ‑ ‐ ‑ ‑ ‑ ‑; ‑
figure ‒ ‒ ‒ ‒ ‒; ‒
em – – – – – –; –
en — — — — — —; —
horbar ― ― ― ― ― ―; ―
minus − − − − − −; −
hybull ⁃ ⁃ ⁃ ⁃ ⁃ ⁃; ⁃
fe58 ﹘ ﹘ ﹘ ﹘ ﹘; ﹘
fe63 ﹣ ﹣ ﹣ ﹣ ﹣; ﹣
ff0d － － － － －; －
(?:([-‐‑‒–—―−⁃﹘﹣－])|(?:&(?:(?:#x(2d|201[0-5]|2212|2043|fe58|fe63|ff0d))|(?:#(45|820[89]|821[0123]|8722|8259|65112|65123|65293))|(hyphen|[nm]?dash|hybull|horbar|minus));?))";
RegexOptions options = RegexOptions.Multiline | RegexOptions.CultureInvariant;
foreach (Match m in Regex.Matches(input, pattern, options))
{
Console.WriteLine("'{0}' found at index {1}.", m.Value, m.Index);
}
}
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for C#, please visit: https://msdn.microsoft.com/en-us/library/system.text.regularexpressions.regex(v=vs.110).aspx