[8815] | 1 | /*
|
---|
| 2 | * Stemmer.java
|
---|
| 3 | * Copyright (C) 2001 Eibe Frank
|
---|
| 4 | *
|
---|
| 5 | * This program is free software; you can redistribute it and/or modify
|
---|
| 6 | * it under the terms of the GNU General Public License as published by
|
---|
| 7 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 8 | * (at your option) any later version.
|
---|
| 9 | *
|
---|
| 10 | * This program is distributed in the hope that it will be useful,
|
---|
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 13 | * GNU General Public License for more details.
|
---|
| 14 | *
|
---|
| 15 | * You should have received a copy of the GNU General Public License
|
---|
| 16 | * along with this program; if not, write to the Free Software
|
---|
| 17 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 18 | */
|
---|
| 19 |
|
---|
| 20 | import java.util.*;
|
---|
| 21 | import java.io.*;
|
---|
| 22 |
|
---|
| 23 | /**
|
---|
| 24 | * Abstract class for stemmers.
|
---|
| 25 | *
|
---|
| 26 | * @author Eibe Frank ([email protected])
|
---|
| 27 | * @version 1.0
|
---|
| 28 | */
|
---|
| 29 | public abstract class Stemmer implements Serializable {
|
---|
| 30 |
|
---|
| 31 | /**
|
---|
| 32 | * Iterated stemming of the given word.
|
---|
| 33 | */
|
---|
| 34 | public abstract String stem(String str);
|
---|
| 35 |
|
---|
| 36 | /**
|
---|
| 37 | * Stems everything in the given string.
|
---|
| 38 | */
|
---|
| 39 | public String stemString(String str) {
|
---|
| 40 |
|
---|
| 41 | StringBuffer result = new StringBuffer();
|
---|
| 42 | int start = -1;
|
---|
| 43 | for (int j = 0; j < str.length(); j++) {
|
---|
| 44 | char c = str.charAt(j);
|
---|
| 45 | if (Character.isLetterOrDigit(c)) {
|
---|
| 46 | if (start == -1) {
|
---|
| 47 | start = j;
|
---|
| 48 | }
|
---|
| 49 | } else if (c == '\'') {
|
---|
| 50 | if (start == -1) {
|
---|
| 51 | result.append(c);
|
---|
| 52 | }
|
---|
| 53 | } else {
|
---|
| 54 | if (start != -1) {
|
---|
| 55 | result.append(stem(str.substring(start, j)));
|
---|
| 56 | start = -1;
|
---|
| 57 | }
|
---|
| 58 | result.append(c);
|
---|
| 59 | }
|
---|
| 60 | }
|
---|
| 61 | if (start != -1) {
|
---|
| 62 | result.append(stem(str.substring(start, str.length())));
|
---|
| 63 | }
|
---|
| 64 | return result.toString();
|
---|
| 65 | }
|
---|
| 66 | }
|
---|
| 67 |
|
---|
| 68 |
|
---|