1 /*
2 * ====================================================================
3 *
4 * The Apache Software License, Version 1.1
5 *
6 * Copyright (c) 2003 Nick Lothian. All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 *
12 * 1. Redistributions of source code must retain the above copyright
13 * notice, this list of conditions and the following disclaimer.
14 *
15 * 2. Redistributions in binary form must reproduce the above copyright
16 * notice, this list of conditions and the following disclaimer in
17 * the documentation and/or other materials provided with the
18 * distribution.
19 *
20 * 3. The end-user documentation included with the redistribution, if
21 * any, must include the following acknowlegement:
22 * "This product includes software developed by the
23 * developers of Classifier4J (http://classifier4j.sf.net/)."
24 * Alternately, this acknowlegement may appear in the software itself,
25 * if and wherever such third-party acknowlegements normally appear.
26 *
27 * 4. The name "Classifier4J" must not be used to endorse or promote
28 * products derived from this software without prior written
29 * permission. For written permission, please contact
30 * http://sourceforge.net/users/nicklothian/.
31 *
32 * 5. Products derived from this software may not be called
33 * "Classifier4J", nor may "Classifier4J" appear in their names
34 * without prior written permission. For written permission, please
35 * contact http://sourceforge.net/users/nicklothian/.
36 *
37 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
38 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
39 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
40 * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
41 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
42 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
43 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
44 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
45 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
46 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
47 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
48 * SUCH DAMAGE.
49 * ====================================================================
50 */
51
52 package net.sf.classifier4J.bayesian;
53
54 import java.io.Serializable;
55 import java.util.Collection;
56 import java.util.HashMap;
57 import java.util.Map;
58
59 /***
60 *
61 * @author Nick Lothian
62 * @author Peter Leschev
63 *
64 */
65 public class SimpleWordsDataSource implements IWordsDataSource, Serializable {
66
67 private Map words = new HashMap();
68
69 public void setWordProbability(WordProbability wp) {
70 words.put(wp.getWord(), wp);
71 }
72
73 /***
74 * @see net.sf.classifier4J.bayesian.IWordsDataSource#getWordProbability(java.lang.String)
75 */
76 public WordProbability getWordProbability(String word) {
77 if (words.containsKey(word)) {
78 return (WordProbability) words.get(word);
79 } else {
80 return null;
81 }
82 }
83
84 public Collection getAll() {
85 return words.values();
86 }
87
88 /***
89 * @see net.sf.classifier4J.bayesian.IWordsDataSource#addMatch(java.lang.String)
90 */
91 public void addMatch(String word) {
92 WordProbability wp = (WordProbability) words.get(word);
93 if (wp == null) {
94 wp = new WordProbability(word, 1, 0);
95 } else {
96 wp.setMatchingCount(wp.getMatchingCount() + 1);
97 }
98 setWordProbability(wp);
99 }
100
101 /***
102 * @see net.sf.classifier4J.bayesian.IWordsDataSource#addNonMatch(java.lang.String)
103 */
104 public void addNonMatch(String word) {
105 WordProbability wp = (WordProbability) words.get(word);
106 if (wp == null) {
107 wp = new WordProbability(word, 0, 1);
108 } else {
109 wp.setNonMatchingCount(wp.getNonMatchingCount() + 1);
110 }
111 setWordProbability(wp);
112 }
113
114 }