/// <summary>
/// 使用Porter stemmer做stemming。
/// </summary>
/// <param name="token">需要做stemming的字。</param>
/// <returns>stemming後的結果。</returns>
public string Stem(string token)
{
return(Stemmer.go(token));
}
/** Test program for demonstrating the Stemmer. It reads text from a
* a list of files, stems each word, and writes the result to standard
* output. Note that the word stemmed is expected to be in lower case:
* forcing lower case must be done outside the Stemmer class.
* Usage: Stemmer file-name file-name ...
*/
public static string go(String str)
{
string result = "";
char[] w = new char[501];
Stemmer s = new Stemmer();
for (int i = 0; i < 1; i++)
{
try
{
//FileStream _in = new FileStream(args[i], FileMode.Open, FileAccess.Read);
StringReader _in = new StringReader(str);
try
{
while (true)
{
int ch = _in.Read();
if (Char.IsLetter((char)ch))
{
int j = 0;
while (true)
{
ch = Char.ToLower((char)ch);
w[j] = (char)ch;
if (j < 500)
{
j++;
}
ch = _in.Read();
if (!Char.IsLetter((char)ch))
{
/* to test add(char ch) */
for (int c = 0; c < j; c++)
{
s.add(w[c]);
}
/* or, to test add(char[] w, int j) */
/* s.add(w, j); */
s.stem();
String u;
/* and now, to test toString() : */
u = s.ToString();
/* to test getResultBuffer(), getResultLength() : */
/* u = new String(s.getResultBuffer(), 0, s.getResultLength()); */
//Console.Write(u);
result += u;
break;
}
}
}
if (ch < 0)
{
break;
}
result += (char)ch;
//Console.Write((char)ch);
}
}
catch (IOException)
{
//Console.WriteLine("error reading " + args[i]);
break;
}
}
catch (FileNotFoundException)
{
//Console.WriteLine("file " + args[i] + " not found");
break;
}
}
return(result);
}