public void run() {
int articleID = IDManager.getNextStemArticleID();
char[] w = new char[501];
Stemmer s = new Stemmer();
// NewsTextRetriever nt = new NewsTextRetriever();
while (articleID != 0) {
String document = DBConnection.getInstance().getNewsText(articleID);
if (document == null) {
articleID = IDManager.getNextStemArticleID();
continue;
}
// replace useless stuff
document = document.replace(";", "");
document = document.replace("!", "");
document = document.replace("?", "");
document = document.replace(",", "");
document = document.replace("'", "");
document = document.replace("´", "");
document = document.replace("`", "");
document = document.replace(".", "");
document = document.replace(":", "");
char[] text = document.toCharArray();
Article article = new Article(articleID);
// Iterate over all words and stem them. Original algorithm
int i = 0;
while (i < text.length) {
char ch = text[i];
i++;
if (Character.isLetter((char) ch)) {
int j = 0;
while (i < text.length) {
{
ch = Character.toLowerCase((char) ch);
w[j] = (char) ch;
if (j < 500) j++;
ch = text[i];
i++;
if (!Character.isLetter((char) ch) || i == text.length) {
if (i == text.length) {
w[j] = (char) ch;
if (j < 500) j++;
}
/* 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 stem = s.toString();
if (stem.length() < 255) {
article.addArticleFeatureInstance(stem);
break;
}
}
}
}
if (ch < 0) break;
}
}
DBConnection.getInstance().storeNewsStems(article);
articleID = IDManager.getNextStemArticleID();
}
}
public PhySimObj() {
this(IDManager.getNextID());
}
