clean_stopword_cs

clean_stopword_cs.cs

List<string> stopword = new List<string>();

foreach (var line in File.ReadLines("stopword.txt"))
{
    stopword.Add(line);
}

var stopword_set = new HashSet<string>(stopword);  //Hashset of Stopwords

// Let t_tokens_str be the tokenized version of the string

List<string> stop_tokens_str = new List<string>();

foreach (string word in tokens_str)
{
    if (stopword_set.Contains(word))
        continue;
    else
        stop_tokens_str.Add(word);

}