blob: 77d79aeec61c9e280f9fec6636ca4d9b5353c7da (
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
|
/* LanguageTool, a natural language style checker
* Copyright (C) 2007 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.language;
import java.util.HashSet;
import java.util.Locale;
import java.util.Set;
import de.danielnaber.languagetool.Language;
import de.danielnaber.languagetool.synthesis.Synthesizer;
/*import de.danielnaber.languagetool.synthesis.en.EnglishSynthesizer; */
import de.danielnaber.languagetool.tagging.Tagger;
import de.danielnaber.languagetool.tagging.disambiguation.Disambiguator;
/*import de.danielnaber.languagetool.tagging.disambiguation.rules.en.EnglishRuleDisambiguator;*/
/*import de.danielnaber.languagetool.tagging.en.EnglishTagger;*/
import de.danielnaber.languagetool.tagging.nb.BokmalTagger;
import de.danielnaber.languagetool.tokenizers.SRXSentenceTokenizer;
import de.danielnaber.languagetool.tokenizers.SentenceTokenizer;
import de.danielnaber.languagetool.tokenizers.Tokenizer;
/*import de.danielnaber.languagetool.tokenizers.en.EnglishWordTokenizer;*/
public class Bokmal extends Language {
private final Tagger tagger = new BokmalTagger();
// private final Tokenizer wordTokenizer = new BokmalWordTokenizer();
private final SentenceTokenizer sentenceTokenizer = new SRXSentenceTokenizer("nb");
// private final Synthesizer synthesizer = new BokmalSynthesizer();
// private final Disambiguator disambiguator = new BokmalRuleDisambiguator();
private static final String[] COUNTRIES = {"NO"};
public final Locale getLocale() {
return new Locale(getShortName());
}
public final SentenceTokenizer getSentenceTokenizer() {
return sentenceTokenizer;
}
public final String getName() {
return "Bokmal";
}
public final String getShortName() {
return "nb";
}
public final String[] getCountryVariants() {
return COUNTRIES;
}
public final Tagger getTagger() {
return tagger;
}
/* public final Tokenizer getWordTokenizer() {
return wordTokenizer;
}
public final Synthesizer getSynthesizer() {
return synthesizer;
}
public final Disambiguator getDisambiguator() {
return disambiguator;
}*/
public final Contributor[] getMaintainers() {
return new Contributor[] {new Contributor("Arno Teigseth")/*,
new Contributor("Arno Teigseth")*/};
}
public final Set<String> getRelevantRuleIDs() {
final Set<String> ids = new HashSet<String>();
ids.add("COMMA_PARENTHESIS_WHITESPACE");
ids.add("DOUBLE_PUNCTUATION");
ids.add("EN_UNPAIRED_BRACKETS");
ids.add("UPPERCASE_SENTENCE_START");
ids.add("WORD_REPEAT_RULE");
ids.add("WHITESPACE_RULE");
// specific to English:
// ids.add("EN_A_VS_AN");
// ids.add("EN_COMPOUNDS");
return ids;
}
}
|
