What code would I use to convert a SQL like expression to a regex on the fly?

Question

I'm looking to convert a SQL like statement on the fly to the equivalent regex i.e.

LIKE '%this%'
LIKE 'Sm_th'
LIKE '[C-P]arsen'

What's the best approach to doing this?

P.S. I'm looking to do this on the .Net Framework (C#).

Answer 1

The following Regex converts an SQL like pattern into a Regex pattern with the help of a MatchEvaluator delegate. It correctly handles square bracket blocks and escapes special Regex characters.

string regexPattern = "^" + Regex.Replace(
    likePattern,
    @"[%_]|\[[^]]*\]|[^%_[]+",
    match =>
    {
        if (match.Value == "%")
        {
            return ".*";
        }
        if (match.Value == "_")
        {
            return ".";
        }
        if (match.Value.StartsWith("[") && match.Value.EndsWith("]"))
        {
            return match.Value;
        }
        return Regex.Escape(match.Value);
    }) + "$";

Answer 2

In addition to @Nathan-Baulch's solution you can use the code below to also handle the case where a custom escape character has been defined using the LIKE '!%' ESCAPE '!' syntax.

   public Regex ConvertSqlLikeToDotNetRegex(string regex, char? likeEscape = null)
   {
        var pattern = string.Format(@"
            {0}[%_]|
            [%_]|
            \[[^]]*\]|
            [^%_[{0}]+
            ", likeEscape);

        var regexPattern = Regex.Replace(
            regex,
            pattern,
            ConvertWildcardsAndEscapedCharacters,
            RegexOptions.IgnorePatternWhitespace);

        regexPattern = "^" + regexPattern + "$";

        return new Regex(regexPattern,
            !m_CaseSensitive ? RegexOptions.IgnoreCase : RegexOptions.None);
    }

    private string ConvertWildcardsAndEscapedCharacters(Match match)
    {
        // Wildcards
        switch (match.Value)
        {
            case "%":
                return ".*";
            case "_":
                return ".";
        }

        // Remove SQL defined escape characters from C# regex
        if (StartsWithEscapeCharacter(match.Value, likeEscape))
        {
            return match.Value.Remove(0, 1);
        }

        // Pass anything contained in []s straight through 
        // (These have the same behaviour in SQL LIKE Regex and C# Regex)
        if (StartsAndEndsWithSquareBrackets(match.Value))
        {
            return match.Value;
        }

        return Regex.Escape(match.Value);
    }

    private static bool StartsAndEndsWithSquareBrackets(string text)
    {
        return text.StartsWith("[", StringComparison.Ordinal) &&
               text.EndsWith("]", StringComparison.Ordinal);
    }

    private bool StartsWithEscapeCharacter(string text, char? likeEscape)
    {
        return (likeEscape != null) &&
               text.StartsWith(likeEscape.ToString(), StringComparison.Ordinal);
    }