/
FakeWordsEncoderAnalyzer.java
56 lines (46 loc) · 1.78 KB
/
FakeWordsEncoderAnalyzer.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
/*
* Anserini: A Lucene toolkit for replicable information retrieval research
*
* 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 io.anserini.ann.fw;
import io.anserini.ann.FeatureVectorsTokenizer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.Tokenizer;
/**
* {@link Analyzer} that encodes input vectors as "fake words", see paper "Large scale indexing
* and searching deep convolutional neural network features" from Amato et al. (DaWaK 2016).
*/
public class FakeWordsEncoderAnalyzer extends Analyzer {
static final String REMOVE_IT = "_";
public static final int DEFAULT_Q = 80;
private final int q;
private final CharArraySet set = new CharArraySet(1, false);
public FakeWordsEncoderAnalyzer() {
this(DEFAULT_Q);
}
public FakeWordsEncoderAnalyzer(int q) {
this.q = q;
this.set.add(REMOVE_IT);
}
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer t = new FeatureVectorsTokenizer();
TokenFilter filter = new FakeWordsEncodeAndQuantizeFilter(t, q);
filter = new StopFilter(filter, set);
return new TokenStreamComponents(t, filter);
}
}