WellKnownRegularExpressions.cs

using System;
using System.Text.RegularExpressions;

namespace GitHub.DistributedTask.Pipelines.Expressions
{
    public static class WellKnownRegularExpressions
    {
        public const String Email = nameof(Email);
        public const String IPv4Address = nameof(IPv4Address);
        public const String SHA1 = nameof(SHA1);
        public const String CommitHash = nameof(CommitHash);
        public const String Url = nameof(Url);

        /// <summary>
        /// Returns null if it's not a well-known type
        /// </summary>
        /// <param name="regexType"></param>
        /// <returns></returns>
        public static Lazy<Regex> GetRegex(String regexType)
        {
            switch (regexType)
            {
                case Email:
                    return s_validEmail;
                case IPv4Address:
                    return s_validIPv4Address;
                case SHA1:
                case CommitHash:
                    return s_validCommitHash;
                case Url:
                    return s_validUrl;
                default:
                    return null;
            }
        }

        // regex from http://index/?leftProject=System.ComponentModel.DataAnnotations&leftSymbol=cmnlm5e7vdio&file=DataAnnotations%5CEmailAddressAttribute.cs&rightSymbol=jfeiathypuap
        private static readonly Lazy<Regex> s_validEmail = new Lazy<Regex>(() => new Regex(
            @"^((([a-z]|\d|[!#\$%&'\*\+\-\/=\?\^_`{\|}~]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])+(\.([a-z]|\d|[!#\$%&'\*\+\-\/=\?\^_`{\|}~]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])+)*)|((\x22)((((\x20|\x09)*(\x0d\x0a))?(\x20|\x09)+)?(([\x01-\x08\x0b\x0c\x0e-\x1f\x7f]|\x21|[\x23-\x5b]|[\x5d-\x7e]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(\\([\x01-\x09\x0b\x0c\x0d-\x7f]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]))))*(((\x20|\x09)*(\x0d\x0a))?(\x20|\x09)+)?(\x22)))@((([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.)+(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.?$",
            RegexOptions.IgnoreCase | RegexOptions.CultureInvariant | RegexOptions.Compiled, RegexUtility.GetRegexTimeOut()
            )
        );

        // simple check - {1 to 3 digits}.{1 to 3 digits}.{1 to 3 digits}.{1 to 3 digits}
        private static readonly Lazy<Regex> s_validIPv4Address = new Lazy<Regex>(() => new Regex(
            @"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}",
            RegexOptions.IgnoreCase | RegexOptions.CultureInvariant | RegexOptions.Compiled, RegexUtility.GetRegexTimeOut()
            )
        );

        // 40 or 64 hex characters (SHA-1 or SHA-256 commit hash)
        private static readonly Lazy<Regex> s_validCommitHash = new Lazy<Regex>(() => new Regex(
            @"\b(?:[0-9a-f]{40}|[0-9a-f]{64})\b",
            RegexOptions.IgnoreCase | RegexOptions.CultureInvariant | RegexOptions.Compiled, RegexUtility.GetRegexTimeOut()
            )
        );

        // regex from http://index/?leftProject=System.ComponentModel.DataAnnotations&leftSymbol=gk29yrysvq6y&file=DataAnnotations%5CUrlAttribute.cs&line=11
        private static readonly Lazy<Regex> s_validUrl = new Lazy<Regex>(() => new Regex(
            @"^(https?|ftp):\/\/(((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:)*@)?(((\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5]))|((([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.)+(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.?)(:\d*)?)(\/((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|@)+(\/(([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|@)*)*)?)?(\?((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|@)|[\uE000-\uF8FF]|\/|\?)*)?(\#((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|@)|\/|\?)*)?$",
            RegexOptions.IgnoreCase | RegexOptions.CultureInvariant | RegexOptions.Compiled, RegexUtility.GetRegexTimeOut()
            )
        );
    }
}