Question

Why isn’t it possible to use fluent language on string?

For example:

var x = "asdf1234";
var y = new string(x.TakeWhile(char.IsLetter).ToArray());

Isn’t there a better way to convert IEnumerable<char> to string?

Here is a test I’ve made:

class Program
{
  static string input = "asdf1234";
  static void Main()
  {
    Console.WriteLine("1000 times:");
    RunTest(1000, input);
    Console.WriteLine("10000 times:");
    RunTest(10000,input);
    Console.WriteLine("100000 times:");
    RunTest(100000, input);
    Console.WriteLine("100000 times:");
    RunTest(100000, "ffff57467");


    Console.ReadKey();

  }

  static void RunTest( int times, string input)
  {

    Stopwatch sw = new Stopwatch();

    sw.Start();
    for (int i = 0; i < times; i++)
    {
      string output = new string(input.TakeWhile(char.IsLetter).ToArray());
    }
    sw.Stop();
    var first = sw.ElapsedTicks;

    sw.Restart();
    for (int i = 0; i < times; i++)
    {
      string output = Regex.Match(input, @"^[A-Z]+", 
        RegexOptions.IgnoreCase).Value;
    }
    sw.Stop();
    var second = sw.ElapsedTicks;

    var regex = new Regex(@"^[A-Z]+", 
      RegexOptions.IgnoreCase);
    sw.Restart();
    for (int i = 0; i < times; i++)
    {
      var output = regex.Match(input).Value;
    }
    sw.Stop();
    var third = sw.ElapsedTicks;

    double percent = (first + second + third) / 100;
    double p1 = ( first / percent)/  100;
    double p2 = (second / percent )/100;
    double p3 = (third / percent  )/100;


    Console.WriteLine("TakeWhile took {0} ({1:P2}).,", first, p1);
    Console.WriteLine("Regex took {0}, ({1:P2})." , second,p2);
    Console.WriteLine("Preinstantiated Regex took {0}, ({1:P2}).", third,p3);
    Console.WriteLine();
  }
}

Result:

1000 times:
TakeWhile took 11217 (62.32%).,
Regex took 5044, (28.02%).
Preinstantiated Regex took 1741, (9.67%).

10000 times:
TakeWhile took 9210 (14.78%).,
Regex took 32461, (52.10%).
Preinstantiated Regex took 20669, (33.18%).

100000 times:
TakeWhile took 74945 (13.10%).,
Regex took 324520, (56.70%).
Preinstantiated Regex took 172913, (30.21%).

100000 times:
TakeWhile took 74511 (13.77%).,
Regex took 297760, (55.03%).
Preinstantiated Regex took 168911, (31.22%).

Conclusion: I’m doubting what’s better to prefer, I think I’m gonna go on the TakeWhile which is the slowest only on first run.

Anyway, my question is if there is any way to optimize the performance by restringing the result of the TakeWhile function.

Answer 1

Assuming that you’re looking predominantly for performance, then something like this should be substantially faster than any of your examples:

string x = "asdf1234";
string y = x.LeadingLettersOnly();

// ...

public static class StringExtensions
{
    public static string LeadingLettersOnly(this string source)
    {
        if (source == null)
            throw new ArgumentNullException("source");

        if (source.Length == 0)
            return source;

        char[] buffer = new char[source.Length];
        int bufferIndex = 0;

        for (int sourceIndex = 0; sourceIndex < source.Length; sourceIndex++)
        {
            char c = source[sourceIndex];

            if (!char.IsLetter(c))
                break;

            buffer[bufferIndex++] = c;
        }
        return new string(buffer, 0, bufferIndex);
    }
}