private NGramItem GetNGrams(string line) { var segments = TextCleaner.CleanSplit(" ", line); var frequency = long.Parse(segments[0]); if (English.IllegalTokens.Any(line.Contains)) { return(null); } if (frequency < MinimumFrequency) { return(null); } var words = segments.Skip(1).ToArray(); return(new NGramItem { Text = string.Join(" ", words), Frequency = frequency, Words = words }); }