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.io.BufferedReader;
55 import java.io.IOException;
56 import java.io.InputStreamReader;
57 import java.util.ArrayList;
58 import java.util.Arrays;
59
60 import net.sf.classifier4J.util.*;
61
62 public class CustomizableStopWordProvider implements IStopWordProvider {
63
64 private Resource resource;
65 private String[] words;
66
67 public static final String DEFAULT_STOPWORD_PROVIDER_RESOURCENAME = "defaultStopWords.txt";
68
69 /***
70 *
71 * @param filename Identifies the name of a textfile on the classpath that contains
72 * a list of stop words, one on each line
73 */
74 public CustomizableStopWordProvider(String resourcename) throws IOException {
75 resource = new Resource(resourcename);
76
77 init();
78 }
79
80 public CustomizableStopWordProvider() throws IOException {
81 this(DEFAULT_STOPWORD_PROVIDER_RESOURCENAME);
82 }
83
84 protected void init() throws IOException {
85 ArrayList wordsLst = new ArrayList();
86 BufferedReader reader = new BufferedReader(new InputStreamReader(resource.getInputStream()));
87
88 String word;
89 while ((word = reader.readLine()) != null) {
90 wordsLst.add(word.trim());
91 }
92
93 words = (String[]) wordsLst.toArray(new String[wordsLst.size()]);
94
95 Arrays.sort(words);
96 }
97
98 /***
99 * @see net.sf.classifier4J.IStopWordProvider#isStopWord(java.lang.String)
100 */
101 public boolean isStopWord(String word) {
102 return (Arrays.binarySearch(words, word) >= 0);
103 }
104
105 }