| 1 | /* |
|---|
| 2 | * This program is free software; you can redistribute it and/or modify |
|---|
| 3 | * it under the terms of the GNU General Public License as published by |
|---|
| 4 | * the Free Software Foundation; either version 2 of the License, or |
|---|
| 5 | * (at your option) any later version. |
|---|
| 6 | * |
|---|
| 7 | * This program is distributed in the hope that it will be useful, |
|---|
| 8 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
|---|
| 9 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|---|
| 10 | * GNU General Public License for more details. |
|---|
| 11 | * |
|---|
| 12 | * You should have received a copy of the GNU General Public License |
|---|
| 13 | * along with this program; if not, write to the Free Software |
|---|
| 14 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. |
|---|
| 15 | */ |
|---|
| 16 | |
|---|
| 17 | /* |
|---|
| 18 | * IteratedLovinsStemmer.java |
|---|
| 19 | * Copyright (C) 2001 University of Waikato, Hamilton, New Zealand |
|---|
| 20 | * |
|---|
| 21 | */ |
|---|
| 22 | |
|---|
| 23 | package weka.core.stemmers; |
|---|
| 24 | |
|---|
| 25 | import weka.core.RevisionUtils; |
|---|
| 26 | |
|---|
| 27 | /** |
|---|
| 28 | <!-- globalinfo-start --> |
|---|
| 29 | * An iterated version of the Lovins stemmer. It stems the word (in case it's longer than 2 characters) until it no further changes.<br/> |
|---|
| 30 | * <br/> |
|---|
| 31 | * For more information about the Lovins stemmer see:<br/> |
|---|
| 32 | * <br/> |
|---|
| 33 | * Julie Beth Lovins (1968). Development of a stemming algorithm. Mechanical Translation and Computational Linguistics. 11:22-31. |
|---|
| 34 | * <p/> |
|---|
| 35 | <!-- globalinfo-end --> |
|---|
| 36 | * |
|---|
| 37 | <!-- technical-bibtex-start --> |
|---|
| 38 | * BibTeX: |
|---|
| 39 | * <pre> |
|---|
| 40 | * @article{Lovins1968, |
|---|
| 41 | * author = {Julie Beth Lovins}, |
|---|
| 42 | * journal = {Mechanical Translation and Computational Linguistics}, |
|---|
| 43 | * pages = {22-31}, |
|---|
| 44 | * title = {Development of a stemming algorithm}, |
|---|
| 45 | * volume = {11}, |
|---|
| 46 | * year = {1968} |
|---|
| 47 | * } |
|---|
| 48 | * </pre> |
|---|
| 49 | * <p/> |
|---|
| 50 | <!-- technical-bibtex-end --> |
|---|
| 51 | * |
|---|
| 52 | * @author Eibe Frank (eibe at cs dot waikato dot ac dot nz) |
|---|
| 53 | * @version $Revision: 5953 $ |
|---|
| 54 | * @see LovinsStemmer |
|---|
| 55 | */ |
|---|
| 56 | public class IteratedLovinsStemmer |
|---|
| 57 | extends LovinsStemmer { |
|---|
| 58 | |
|---|
| 59 | /** for serialization */ |
|---|
| 60 | static final long serialVersionUID = 960689687163788264L; |
|---|
| 61 | |
|---|
| 62 | /** |
|---|
| 63 | * Returns a string describing the stemmer |
|---|
| 64 | * @return a description suitable for |
|---|
| 65 | * displaying in the explorer/experimenter gui |
|---|
| 66 | */ |
|---|
| 67 | public String globalInfo() { |
|---|
| 68 | return |
|---|
| 69 | "An iterated version of the Lovins stemmer. It stems the word (in " |
|---|
| 70 | + "case it's longer than 2 characters) until it no further changes.\n\n" |
|---|
| 71 | + "For more information about the Lovins stemmer see:\n\n" |
|---|
| 72 | + getTechnicalInformation().toString(); |
|---|
| 73 | } |
|---|
| 74 | |
|---|
| 75 | /** |
|---|
| 76 | * Iterated stemming of the given word. |
|---|
| 77 | * Word is converted to lower case. |
|---|
| 78 | * |
|---|
| 79 | * @param str the word to stem |
|---|
| 80 | * @return the stemmed word |
|---|
| 81 | */ |
|---|
| 82 | public String stem(String str) { |
|---|
| 83 | |
|---|
| 84 | if (str.length() <= 2) { |
|---|
| 85 | return str; |
|---|
| 86 | } |
|---|
| 87 | String stemmed = super.stem(str); |
|---|
| 88 | while (!stemmed.equals(str)) { |
|---|
| 89 | str = stemmed; |
|---|
| 90 | stemmed = super.stem(stemmed); |
|---|
| 91 | } |
|---|
| 92 | return stemmed; |
|---|
| 93 | } |
|---|
| 94 | |
|---|
| 95 | /** |
|---|
| 96 | * Returns the revision string. |
|---|
| 97 | * |
|---|
| 98 | * @return the revision |
|---|
| 99 | */ |
|---|
| 100 | public String getRevision() { |
|---|
| 101 | return RevisionUtils.extract("$Revision: 5953 $"); |
|---|
| 102 | } |
|---|
| 103 | |
|---|
| 104 | /** |
|---|
| 105 | * Runs the stemmer with the given options |
|---|
| 106 | * |
|---|
| 107 | * @param args the options |
|---|
| 108 | */ |
|---|
| 109 | public static void main(String[] args) { |
|---|
| 110 | try { |
|---|
| 111 | Stemming.useStemmer(new IteratedLovinsStemmer(), args); |
|---|
| 112 | } |
|---|
| 113 | catch (Exception e) { |
|---|
| 114 | e.printStackTrace(); |
|---|
| 115 | } |
|---|
| 116 | } |
|---|
| 117 | } |
|---|
| 118 | |
|---|