public static void getNN_NNs(string input, string[][] pos, HashSet <string> result)
{
//HashSet<string> result = new HashSet<string>();
//List<int> npIndex = new List<int>();
//for (int i = 0; i < pos.Length; i++)
//{
// if (pos[i].Equals("NN") || pos[i].Equals("NNS"))
// npIndex.Add(i);
//}
//string[] words = input.Split((char[])null, StringSplitOptions.RemoveEmptyEntries);
// foreach (int indx in npIndex)
// result.Add(words[indx]);
//return result;
List <int> npIndex = new List <int>();
int indx = 0;
for (int i = 0; i < pos.GetLength(0); i++)
{
for (int j = 0; j < pos[0].Length; j++)
{
if (pos[i][j].Equals("NN") || pos[i][j].Equals("NNS"))
{
npIndex.Add(indx);
}
indx++;
}
}
//foreach (int ind in npIndex)
// Console.WriteLine(ind);
input = LanguageAnalyze.RemovePunctuation(input);
string[] words = input.Split((char[])null, StringSplitOptions.RemoveEmptyEntries);
//foreach (String s in words)
// Console.WriteLine(s);
foreach (int inin in npIndex)
{
if (inin < words.Length)
{
result.Add(words[inin]);
}
}
}
public static HashSet <string> getNP(string input)
{
HashSet <string> npAll = new HashSet <string>();
string[] syntaxt = LanguageAnalyze.analyzeDependancyTree(input);
foreach (string syn in syntaxt)
{
Extract(syn, npAll);
}
Tuple <string, string[][]> t = LanguageAnalyze.analyzePOSTag(input);
HashSet <string> nn = new HashSet <string>();
getNN_NNs(t.Item1, t.Item2, nn);
HashSet <string> result = new HashSet <string>();
foreach (string nnn in nn)
{
if (!containWord(npAll, nnn) && !isStop(nnn))
{
result.Add(nnn);
}
}
foreach (string nnp in npAll)
{
if (!isStop(nnp))
{
result.Add(nnp);
}
}
//if (result.Contains("data mining"))
// result.Remove("data mining");
if (result.Contains("database"))
{
result.Remove("database");
}
return(result);
}