Nuget install Knuppe.SharpNL
public static string TokenizerAndStemmingInput(this string oData)
{
//return oData.ToLower();
//var tokenizerWordArray = SimpleTokenizer.Instance.Tokenize(oData.CleanSpecialSymbol());
var tokenizerWordArray = SimpleTokenizer.Instance.Tokenize(oData);
var output = new List<string>();
foreach (var word in tokenizerWordArray)
{
if (word.Trim() != "")
{
var stemWord = EnglishStemmer.Instance.Stem(word);
output.Add(stemWord);
}
}
if (output.Any())
{
return output.Aggregate((m1, m2) => m1 + " " + m2);
}
else
{
return "";
}
}