porterstemmer.java

dragontoolkit用于机器学习

                if (ends("enci")) {
                    r("ence");
                    break;
                }
                if (ends("anci")) {
                    r("ance");
                    break;
                }
                break;
            case 'e':
                if (ends("izer")) {
                    r("ize");
                    break;
                }
                break;
            case 'l':
                if (ends("bli")) {
                    r("ble");
                    break;
                }
                if (ends("alli")) {
                    r("al");
                    break;
                }
                if (ends("entli")) {
                    r("ent");
                    break;
                }
                if (ends("eli")) {
                    r("e");
                    break;
                }
                if (ends("ousli")) {
                    r("ous");
                    break;
                }
                break;
            case 'o':
                if (ends("ization")) {
                    r("ize");
                    break;
                }
                if (ends("ation")) {
                    r("ate");
                    break;
                }
                if (ends("ator")) {
                    r("ate");
                    break;
                }
                break;
            case 's':
                if (ends("alism")) {
                    r("al");
                    break;
                }
                if (ends("iveness")) {
                    r("ive");
                    break;
                }
                if (ends("fulness")) {
                    r("ful");
                    break;
                }
                if (ends("ousness")) {
                    r("ous");
                    break;
                }
                break;
            case 't':
                if (ends("aliti")) {
                    r("al");
                    break;
                }
                if (ends("iviti")) {
                    r("ive");
                    break;
                }
                if (ends("biliti")) {
                    r("ble");
                    break;
                }
                break;
            case 'g':
                if (ends("logi")) {
                    r("log");
                    break;
                }
        }
    }

    /* step4() deals with -ic-, -full, -ness etc. similar strategy to step3. */

    private final void step4() {
        switch (b[k]) {
            case 'e':
                if (ends("icate")) {
                    r("ic");
                    break;
                }
                if (ends("ative")) {
                    r("");
                    break;
                }
                if (ends("alize")) {
                    r("al");
                    break;
                }
                break;
            case 'i':
                if (ends("iciti")) {
                    r("ic");
                    break;
                }
                break;
            case 'l':
                if (ends("ical")) {
                    r("ic");
                    break;
                }
                if (ends("ful")) {
                    r("");
                    break;
                }
                break;
            case 's':
                if (ends("ness")) {
                    r("");
                    break;
                }
                break;
        }
    }

    /* step5() takes off -ant, -ence etc., in context <c>vcvc<v>. */

    private final void step5() {
        if (k == 0) {
            return; /* for Bug 1 */
        }
        switch (b[k - 1]) {
            case 'a':
                if (ends("al")) {
                    break;
                }
                return;
            case 'c':
                if (ends("ance")) {
                    break;
                }
                if (ends("ence")) {
                    break;
                }
                return;
            case 'e':
                if (ends("er")) {
                    break;
                }
                return;
            case 'i':
                if (ends("ic")) {
                    break;
                }
                return;
            case 'l':
                if (ends("able")) {
                    break;
                }
                if (ends("ible")) {
                    break;
                }
                return;
            case 'n':
                if (ends("ant")) {
                    break;
                }
                if (ends("ement")) {
                    break;
                }
                if (ends("ment")) {
                    break;
                }

                /* element etc. not stripped before the m */
                if (ends("ent")) {
                    break;
                }
                return;
            case 'o':
                if (ends("ion") && j >= 0 && (b[j] == 's' || b[j] == 't')) {
                    break;
                }

                /* j >= 0 fixes Bug 2 */
                if (ends("ou")) {
                    break;
                }
                return;
            /* takes care of -ous */
            case 's':
                if (ends("ism")) {
                    break;
                }
                return;
            case 't':
                if (ends("ate")) {
                    break;
                }
                if (ends("iti")) {
                    break;
                }
                return;
            case 'u':
                if (ends("ous")) {
                    break;
                }
                return;
            case 'v':
                if (ends("ive")) {
                    break;
                }
                return;
            case 'z':
                if (ends("ize")) {
                    break;
                }
                return;
            default:
                return;
        }
        if (m() > 1) {
            k = j;
        }
    }

    /* step6() removes a final -e if m() > 1. */

    private final void step6() {
        j = k;
        if (b[k] == 'e') {
            int a = m();
            if (a > 1 || a == 1 && !cvc(k - 1)) {
                k--;
            }
        }
        if (b[k] == 'l' && doublec(k) && m() > 1) {
            k--;
        }
    }

    /** Stem the word placed into the Lemmatiser buffer through calls to add().
     * Returns true if the stemming process resulted in a word different
     * from the input.  You can retrieve the result with
     * getResultLength()/getResultBuffer() or toString().
     */
    public void stem() {
        k = i - 1;
        if (k > 1) {
            step1();
            step2();
            step3();
            step4();
            step5();
            step6();
        }
        i_end = k + 1;
        i = 0;
    }

    /** Test program for demonstrating the Lemmatiser.  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 Lemmatiser class.
     * Usage: Lemmatiser file-name file-name ...
     */
    public static void main(String[] args) {
        char[] w = new char[501];
        PorterStemmer s = new PorterStemmer();
        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;
            }
        }
    }

}