/
CharacterNGram.java
112 lines (96 loc) · 3.73 KB
/
CharacterNGram.java
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
105
106
107
108
109
110
111
112
/*******************************************************************************
* Copyright 2018
* Ubiquitous Knowledge Processing (UKP) Lab
* Technische Universität Darmstadt
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
******************************************************************************/
package org.dkpro.tc.features.ngram;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.Set;
import org.apache.uima.fit.descriptor.TypeCapability;
import org.apache.uima.jcas.JCas;
import org.apache.uima.resource.ResourceInitializationException;
import org.apache.uima.util.Level;
import org.dkpro.tc.api.exception.TextClassificationException;
import org.dkpro.tc.api.features.Feature;
import org.dkpro.tc.api.features.meta.MetaCollectorConfiguration;
import org.dkpro.tc.api.type.TextClassificationTarget;
import org.dkpro.tc.features.ngram.meta.CharacterNGramMC;
import de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution;
/**
* Extracts character n-grams.
*/
@TypeCapability(inputs = { "de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Token" })
public class CharacterNGram
extends AbstractNgram
{
private Set<Feature> prepFeatSet;
@Override
public Set<Feature> extract(JCas aJCas, TextClassificationTarget aTarget)
throws TextClassificationException
{
if (prepFeatSet == null) {
prepare();
}
FrequencyDistribution<String> documentCharNgrams = CharacterNGramMC
.getAnnotationCharacterNgrams(aTarget,
ngramLowerCase,
ngramMinN,
ngramMaxN,
CharacterNGramMC.CHAR_WORD_BEGIN,
CharacterNGramMC.CHAR_WORD_END);
return getFeatureSet(documentCharNgrams);
}
@Override
protected String getFieldName()
{
return CharacterNGramMC.LUCENE_CHAR_NGRAM_FIELD + featureExtractorName;
}
@Override
protected String getFeaturePrefix()
{
return getClass().getSimpleName();
}
@Override
protected int getTopN()
{
return ngramUseTopK;
}
@Override
public List<MetaCollectorConfiguration> getMetaCollectorClasses(
Map<String, Object> parameterSettings)
throws ResourceInitializationException
{
return Arrays
.asList(new MetaCollectorConfiguration(CharacterNGramMC.class, parameterSettings)
.addStorageMapping(CharacterNGramMC.PARAM_TARGET_LOCATION,
CharacterNGram.PARAM_SOURCE_LOCATION, CharacterNGramMC.LUCENE_DIR));
}
@Override
protected void logSelectionProcess(long N)
{
getLogger().log(Level.INFO, "+++ SELECTING THE " + N + " MOST FREQUENT CHARACTER ["
+ range() + "]-GRAMS (" + caseSensitivity() + ")");
}
private String range()
{
return ngramMinN == ngramMaxN ? ngramMinN + "" : ngramMinN + "-" + ngramMaxN;
}
private String caseSensitivity()
{
return ngramLowerCase ? "case-insensitive" : "case-sensitive";
}
}