C# code:
IEnumerable<KeyValuePair<String, Int32>> ProcessText(String text, int X, int Y)
{
// common words, that will be ignored
var exclude = new string[] { "and", "is", "the", "as", "of", "to", "or", "in", "for", "by", "an", "be", "may", "has", "can", "its" }.ToDictionary(word => word);
// regular expression to find quoted text
var regex = new Regex("\"[^\"]\"", RegexOptions.Compiled);
return
// remove quoted text (it will be processed later)
regex.Replace(text, "")
// remove case dependency
.ToLower()
// split text by all these chars
.Split(".,'\\/[]{}()`~@#$%^&*-=+?!;:<>| \n\r".ToCharArray())
// add quoted text
.Concat(regex.Matches(text).Cast<Match>().Select(match => match.Value))
// group words by the word and count them
.GroupBy(word => word, (word, words) => new KeyValuePair<String, Int32>(word, words.Count()))
// apply filter(min word count and word length) and remove common words
.Where(pair => pair.Value >= X && pair.Key.Length >= Y && !exclude.ContainsKey(pair.Key));
}
Output for ProcessText(text, 3, 2) call:
3 x languages
3 x such
4 x code
4 x which
3 x based
3 x each
4 x declarations
5 x function
4 x statements
3 x new
3 x types
3 x keywords
3 x variables
7 x statement
4 x expression
3 x execution
3 x programming
3 x operators
