Parse a non-ascii (unicode) number-string as integer in .NET

Question

I have a string containing a number in a non-ascii format e.g. unicode BENGALI DIGIT ONE (U+09E7) : \"১\"

How do I parse this as an integer in .NET?

Answer 1

Having found this question while looking for a similar answer, but not finding any of the answers quite matched what I needed, I wrote the following as it treats signs okay, and is faster to fail if given a very long string. It does not though, ignore any grouping characters like ,, ', ’, though that could be easily added if someone wanted (I didn't):

public static int ParseIntInternational(this string str)
{
  int result = 0;
  bool neg = false;
  bool seekingSign = true; // Accept sign at beginning only.
  bool done = false; // Accept whitespace at beginning end or between sign and number.
                     // If we see whitespace once we've seen a number, we're "done" and
                     // further digits should fail.
  for(int i = 0; i != str.Length; ++i)
  {
    if(char.IsWhiteSpace(str, i))
    {
      if(!seekingSign)
        done = true;
    }
    else if(char.IsDigit(str, i))
    {
      if(done)
        throw new FormatException();
      seekingSign = false;
      result = checked(result * 10 + (int)char.GetNumericValue(str, i));
    }
    else if(seekingSign)
      switch(str[i])
      {
        case '﬩': case '+':
          //do nothing: Sign unchanged.
          break;
        case '-': case '−':
          neg = !neg;
          break;
        default:
          throw new FormatException();
      }
    else throw new FormatException();
  }
  if(seekingSign)
    throw new FormatException();
  return neg ? -result : result;
}