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;
53
54 import java.util.Arrays;
55
56 import net.sf.classifier4J.util.ToStringBuilder;
57
58
59 /***
60 * @author Nick Lothian
61 * @author Peter Leschev
62 */
63 public class DefaultStopWordsProvider implements IStopWordProvider {
64 // This array is sorted in the constructor
65 private String[] stopWords = { "a", "and", "the", "me", "i", "of", "if", "it", "is", "they", "there", "but", "or", "to", "this", "you", "in", "your", "on", "for", "as", "are", "that", "with", "have", "be", "at", "or", "was", "so", "out", "not", "an" };
66 private String[] sortedStopWords = null;
67
68 public DefaultStopWordsProvider() {
69 sortedStopWords = getStopWords();
70 Arrays.sort(sortedStopWords);
71 }
72
73 /***
74 * getter method which can be overridden to
75 * supply the stop words. The array returned by this
76 * method is sorted and then used internally
77 *
78 * @return the array of stop words
79 */
80 public String[] getStopWords() {
81 return stopWords;
82 }
83
84 /***
85 * @see net.sf.classifier4J.IStopWordProvider#isStopWord(java.lang.String)
86 */
87 public boolean isStopWord(String word) {
88 if (word == null || "".equals(word)) {
89 return false;
90 } else {
91 // search the sorted array for the word, converted to lowercase
92 // if it is found, the index will be >= 0
93 return (Arrays.binarySearch(sortedStopWords, word.toLowerCase()) >= 0);
94 }
95 }
96
97 public String toString() {
98 return new ToStringBuilder(this).append("stopWords.size()", sortedStopWords.length).toString();
99 }
100 }