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
113
114
115
116
117
118
|
package de.lmu.ifi.dbs.elki.datasource.parser;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2015
Ludwig-Maximilians-Universität München
Lehr- und Forschungseinheit für Datenbanksysteme
ELKI Development Team
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program 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 Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
import gnu.trove.list.array.TLongArrayList;
import de.lmu.ifi.dbs.elki.data.BitVector;
import de.lmu.ifi.dbs.elki.data.LabelList;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
/**
* Parser for parsing one BitVector per line, bits separated by whitespace.
* <p/>
* Several labels may be given per BitVector. A label must not be parseable as
* Bit. Lines starting with "#" will be ignored.
*
* @author Arthur Zimek
*
* @apiviz.has BitVector
*/
@Title("Bit Vector Label Parser")
@Description("Parses the following format of lines:\n" + //
"A single line provides a single BitVector. Bits are separated by whitespace. " + //
"Any substring not containing whitespace is tried to be read as Bit. " + //
"If this fails, it will be appended to a label. " + //
"(Thus, any label must not be parseable as Bit.) " + //
"Empty lines and lines beginning with \"#\" will be ignored.")
public class BitVectorLabelParser extends NumberVectorLabelParser<BitVector> implements Parser {
/**
* Class logger
*/
private static final Logging LOG = Logging.getLogger(BitVectorLabelParser.class);
/**
* Buffer, will be reused.
*/
TLongArrayList buf = new TLongArrayList();
/**
* Constructor.
*
* @param format Input format
*/
public BitVectorLabelParser(CSVReaderFormat format) {
super(format, null, BitVector.FACTORY);
}
@Override
protected boolean parseLineInternal() {
int curdim = 0;
for(; tokenizer.valid(); tokenizer.advance()) {
try {
final int word = curdim >>> 6;
final int off = curdim & 0x3F;
if(word >= buf.size()) { // Ensure size.
buf.add(0L);
}
if(tokenizer.getLongBase10() > 0) {
buf.set(word, buf.get(word) | (1L << off));
}
++curdim;
}
catch(NumberFormatException e) {
labels.add(tokenizer.getSubstring());
}
}
if(curdim == 0) { // Maybe a label row
return false;
}
curvec = new BitVector(buf.toArray(), curdim);
curlbl = LabelList.make(labels);
buf.clear();
labels.clear();
return true;
}
@Override
protected Logging getLogger() {
return LOG;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractStreamingParser.Parameterizer {
@Override
protected BitVectorLabelParser makeInstance() {
return new BitVectorLabelParser(format);
}
}
}
|