public static List <News> ComputeWords(List <News> news)
{
foreach (News info in news)
{
var words = new List <string>();
Filter(info);
string[] wordstemp = info.rawData.Split(' ');
for (int i = 0; i < wordstemp.Length; i++)
{
// normalization
string word = wordstemp[i].ToLower().Trim();
if (WordQuilifier.WordIsOK(word))
{
// steaming
word = Stemmer.DoPorterStemming(word);
//if (word.Length > 2)
//{
words.Add(word);
//}
}
}
info.words = words;
}
return(news);
}
public List <string> getWordList(string pureText)
{
List <string> words = new List <string>();
string[] wordstemp = pureText.Split(' ');
for (int i = 0; i < wordstemp.Length; i++)
{
// normalization
string word = wordstemp[i].ToLower().Trim();
// steaming
word = Stemmer.DoPorterStemming(word);
if (WordQuilifier.WordIsOK(word))
{
words.Add(word);
}
}
return(words);
}