1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
|
/* LanguageTool, a natural language style checker
* Copyright (C) 2005 Daniel Naber (http://www.danielnaber.de)
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301
* USA
*/
package de.danielnaber.languagetool.tokenizers;
import junit.framework.TestCase;
import java.util.List;
public class WordTokenizerTest extends TestCase {
public void testTokenize() {
WordTokenizer w = new WordTokenizer();
List <String> testList = w.tokenize("This is\u00A0a test");
assertEquals(testList.size(), 7);
assertEquals("[This, , is, \u00A0, a, , test]", testList.toString());
testList = w.tokenize("This\rbreaks");
assertEquals(3, testList.size());
assertEquals("[This, \r, breaks]", testList.toString());
}
}
|
