/// <summary>
/// Gets a cleaned string with stop words removed, stemmed, and tokenized.
/// </summary>
/// <param name="sentence"></param>
/// <returns></returns>
public string[] Process(string sentence)
{
var tokens = sentence.Tokenize();
if (!RemoveStopWords && !StemWords)
{
return(tokens);
}
var result = new List <string>();
foreach (string token in tokens)
{
if (RemoveStopWords && StemWords)
{
if (StopWords.All(stopWord => !string.Equals(token, stopWord, StringComparison.InvariantCultureIgnoreCase)))
{
result.Add(_stemmer.Stem(token));
}
}
else if (!RemoveStopWords && StemWords)
{
result.Add(_stemmer.Stem(token));
}
else if (RemoveStopWords && !StemWords)
{
if (StopWords.All(stopWord => !string.Equals(token, stopWord, StringComparison.InvariantCultureIgnoreCase)))
{
result.Add(token);
}
}
}
return(result.ToArray());
}
