blob: 6764c34b774a11791ca8d4816075039b8472127b (
plain)
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
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
/* 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 java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;
/**
* Tokenizes a sentence into words.
* Punctuation and whitespace gets its own token.
*
* @author Daniel Naber
*/
public class WordTokenizer implements Tokenizer {
public WordTokenizer() {
}
public List<String> tokenize(final String text) {
final List<String> l = new ArrayList<String>();
final StringTokenizer st = new StringTokenizer(text,
"\u0020\u00A0\u115f\u1160\u1680"
+ "\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007"
+ "\u2008\u2009\u200A\u200B\u200c\u200d\u200e\u200f"
+ "\u2028\u2029\u202a\u202b\u202c\u202d\u202e\u202f"
+ "\u205F\u2060\u2061\u2062\u2063\u206A\u206b\u206c\u206d"
+ "\u206E\u206F\u3000\u3164\ufeff\uffa0\ufff9\ufffa\ufffb"
+ ",.;()[]{}<>!?:/\\\"'«»„”“‘`’…¿¡\t\n\r", true);
while (st.hasMoreElements()) {
l.add(st.nextToken());
}
return l;
}
}
|
