public static void main(String[] args) {
Stemmer s = new Stemmer();
List l =
s.stemString(
"the a not they an one two three four five six seven eight nine on off no yes Mr "
+ "can be am it all run running runs ");
System.out.println(l);
System.out.println("Stem runs: " + s.stemOneWord("runs"));
}
/**
* 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 String stemFile(FileInputStream in) {
char[] w = new char[501];
String stemmed = new String();
stemmed = "";
Stemmer s = new Stemmer();
// try
// {
// FileInputStream in = new FileInputStream(filename);
try {
while (true) {
int ch = in.read();
if (Character.isLetter((char) ch)) {
int j = 0;
while (true) {
ch = Character.toLowerCase((char) ch);
w[j] = (char) ch;
if (j < 500) j++;
ch = in.read();
// System.out.println(ch);
if (!Character.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();
stemmed = stemmed + " " + u;
/* to test getResultBuffer(), getResultLength() : */
/* u = new String(s.getResultBuffer(), 0, s.getResultLength()); */
// System.out.print(u);
}
break;
}
}
}
if (ch < 0) break;
// System.out.print((char)ch);
}
} catch (IOException e) {
System.out.println("error reading ");
}
// }
// catch (FileNotFoundException e) { System.out.println("file not found"); }
// catch (Exception e) { System.out.println("file not found"); }
return stemmed;
}
/**
* 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 void main(String[] args) {
char[] w = new char[501];
Stemmer s = new Stemmer();
for (int i = 0; i < args.length; i++)
try {
FileInputStream in = new FileInputStream(args[i]);
try {
while (true) {
int ch = in.read();
if (Character.isLetter((char) ch)) {
int j = 0;
while (true) {
ch = Character.toLowerCase((char) ch);
w[j] = (char) ch;
if (j < 500) j++;
ch = in.read();
if (!Character.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()); */
System.out.print(u);
}
break;
}
}
}
if (ch < 0) break;
System.out.print((char) ch);
}
} catch (IOException e) {
System.out.println("error reading " + args[i]);
break;
}
} catch (FileNotFoundException e) {
System.out.println("file " + args[i] + " not found");
break;
}
}
// 輸入文章的ID回傳一個tokenize過的ArrayList
public static ArrayList<String> tokenize(int file) {
Scanner fileIn = null;
ArrayList<String> words = new ArrayList<String>();
try {
fileIn = new Scanner(new FileInputStream("IRTM/" + file + ".txt"));
} catch (FileNotFoundException e) {
System.out.println("File not found.");
System.exit(0);
}
while (fileIn.hasNext()) {
Stemmer s = new Stemmer();
String token = fileIn.next().toLowerCase().replaceAll("[^a-zA-Z0-9]", ""); // 將非字母與數字的char清除
// 濾掉stop word
boolean isStop = false;
for (int i = 0; i < stopList.size(); i++) {
if (token.equals(stopList.get(i)) || token.equals("")) {
isStop = true;
break;
}
}
if (!isStop) {
// 用stemmer將字stem
for (int k = 0; k < token.length(); k++) {
s.add(token.charAt(k));
}
s.stem();
// 在濾一次stop word
isStop = false;
for (int i = 0; i < stopList.size(); i++) {
if (s.toString().equals(stopList.get(i)) || s.toString().equals("")) {
isStop = true;
break;
}
}
if (!isStop) {
words.add(s.toString());
}
}
}
fileIn.close();
// readStop.close();
return words;
}
