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
53
54 package net.sf.classifier4J;
55
56 import junit.framework.TestCase;
57
58
59 public class SimpleHTMLTokenizerTest extends TestCase {
60 SimpleHTMLTokenizer tokenizer = null;
61
62 /***
63 * Constructor for SimpleHTMLTokenizerTest.
64 * @param arg0
65 */
66 public SimpleHTMLTokenizerTest(String arg0) {
67 super(arg0);
68 }
69
70 /*
71 * @see TestCase#setUp()
72 */
73 protected void setUp() throws Exception {
74 tokenizer = new SimpleHTMLTokenizer();
75 }
76
77 /*
78 * @see TestCase#tearDown()
79 */
80 protected void tearDown() throws Exception {
81 tokenizer = null;
82 }
83
84 public void testTokenize() {
85 String input = "<h1>This is in an html tag ></h1>";
86 String[] expected = { "This", "is", "in", "an", "html", "tag"};
87
88 String[] output = tokenizer.tokenize(input);
89 assertNotNull(output);
90 assertEquals(expected.length, output.length);
91
92 for (int i = 0; i < output.length; i++) {
93 assertEquals(expected[i], output[i]);
94 }
95
96 }
97
98 public void testResolveEntities() {
99 String normalString = "this is a normal string";
100 assertEquals(normalString, tokenizer.resolveEntities(normalString));
101
102 String withEnt = "this includes a non-breaking space ";
103 assertEquals(withEnt + " ", tokenizer.resolveEntities(withEnt + " "));
104 }
105
106 }