2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 package jalview.analysis;
23 import static org.testng.AssertJUnit.assertEquals;
24 import static org.testng.AssertJUnit.assertNull;
26 import jalview.datamodel.Alignment;
27 import jalview.datamodel.AlignmentAnnotation;
28 import jalview.datamodel.Sequence;
29 import jalview.datamodel.SequenceI;
30 import jalview.gui.AlignFrame;
32 import java.util.List;
34 import org.testng.annotations.BeforeMethod;
35 import org.testng.annotations.Test;
37 public class ParsePropertiesTest
42 private ParseProperties pp;
45 * Construct an alignment with 4 sequences with varying description format
47 @BeforeMethod(alwaysRun = true)
50 SequenceI[] seqs = new SequenceI[] {
51 new Sequence("sq1", "THISISAPLACEHOLDER"),
52 new Sequence("sq2", "THISISAPLACEHOLDER"),
53 new Sequence("sq3", "THISISAPLACEHOLDER"),
54 new Sequence("sq4", "THISISAPLACEHOLDER") };
55 seqs[0].setDescription("1 mydescription1");
56 seqs[1].setDescription("mydescription2");
57 seqs[2].setDescription("2. 0.1 mydescription+3");
58 seqs[3].setDescription("3 0.01 mydescription4");
59 al = new Alignment(seqs);
61 pp = new ParseProperties(al);
66 * Test with a description pattern that matches any string ending in one or
67 * more 'number characters' (0-9+.), i.e. greedily matches any trailing
68 * numeric part of the string
70 @Test(groups = { "Functional" })
71 public void testGetScoresFromDescription()
73 String regex = ".*([-0-9.+]+)";
74 final int count = pp.getScoresFromDescription("my Score",
75 "my Score Description", regex, true);
76 System.out.println("Matched " + count + " for " + regex);
77 assertEquals(4, count);
80 * Verify values 1/2/3/4 have been parsed from sequence descriptions
82 AlignmentAnnotation[] anns = al.getSequenceAt(0).getAnnotation();
83 assertEquals(1, anns.length);
84 assertEquals(1d, anns[0].getScore(), 0.001d);
85 assertEquals("my Score Description", anns[0].description);
86 assertEquals("my Score", anns[0].label);
87 anns = al.getSequenceAt(1).getAnnotation();
88 assertEquals(1, anns.length);
89 assertEquals(2d, anns[0].getScore(), 0.001d);
90 assertEquals("my Score Description", anns[0].description);
91 assertEquals("my Score", anns[0].label);
92 anns = al.getSequenceAt(2).getAnnotation();
93 assertEquals(1, anns.length);
94 assertEquals(3d, anns[0].getScore(), 0.001d);
95 anns = al.getSequenceAt(3).getAnnotation();
96 assertEquals(1, anns.length);
97 assertEquals(4d, anns[0].getScore(), 0.001d);
101 * Test with a description pattern that matches any string (or none), followed
102 * by a 'number character' (0-9+.), followed by at least one separator
103 * character, followed by at least one 'number character', then any trailing
106 @Test(groups = { "Functional" })
107 public void testGetScoresFromDescription_twoScores()
109 String regex = ".*([-0-9.+]+).+([-0-9.+]+).*";
110 final int count = pp.getScoresFromDescription("my Score",
111 "my Score Description", regex, true);
112 System.out.println("Matched " + count + " for " + regex);
113 assertEquals(3, count);
116 * Seq1 has two score values parsed out
118 AlignmentAnnotation[] anns = al.getSequenceAt(0).getAnnotation();
119 assertEquals(2, anns.length);
120 assertEquals(1d, anns[0].getScore(), 0.001d);
121 assertEquals("my Score Description", anns[0].description);
122 assertEquals("my Score", anns[0].label);
123 assertEquals(1d, anns[1].getScore(), 0.001d);
124 assertEquals("my Score Description (column 1)", anns[1].description);
125 assertEquals("my Score_1", anns[1].label);
128 * Seq2 has no score parsed out (is this right?)
130 assertNull(al.getSequenceAt(1).getAnnotation());
133 * Seq3 has two score values parsed out
135 // TODO parsed values (1.0 and 3.0) look wrong v description
136 // would expect 2.0 and 0.1
137 // undesired 'greedy' behaviour of regex?
138 anns = al.getSequenceAt(2).getAnnotation();
139 assertEquals(2, anns.length);
140 assertEquals(1d, anns[0].getScore(), 0.001d);
141 assertEquals("my Score Description", anns[0].description);
142 assertEquals("my Score", anns[0].label);
143 assertEquals(3d, anns[1].getScore(), 0.001d);
144 assertEquals("my Score Description (column 1)", anns[1].description);
145 assertEquals("my Score_1", anns[1].label);
148 * Seq3 has two score values parsed out
150 // TODO parsed values (1.0 and 4.0) look wrong v description
151 // would expect 3 and 0.01
152 anns = al.getSequenceAt(3).getAnnotation();
153 assertEquals(2, anns.length);
154 assertEquals(1d, anns[0].getScore(), 0.001d);
155 assertEquals("my Score Description", anns[0].description);
156 assertEquals("my Score", anns[0].label);
157 assertEquals(4d, anns[1].getScore(), 0.001d);
158 assertEquals("my Score Description (column 1)", anns[1].description);
159 assertEquals("my Score_1", anns[1].label);
163 * Test with a regex that looks for numbers separated by words - as currently
164 * used in Jalview (May 2015)
166 * @see AlignFrame.extractScores_actionPerformed
168 @Test(groups = { "Functional" })
169 public void testGetScoresFromDescription_wordBoundaries()
171 String regex = "\\W*([-+eE0-9.]+)";
172 List<SequenceI> seqs = al.getSequences();
173 seqs.get(0).setDescription("Ferredoxin");
174 seqs.get(1).setDescription(" Ferredoxin-1, chloroplast precursor");
175 seqs.get(2).setDescription("GH28E30p");
176 seqs.get(3).setDescription("At1g10960/T19D16_12");
177 final int count = pp.getScoresFromDescription("description column",
178 "score in description column ", regex, true);
179 assertEquals(3, count);
182 * No score parsable from seq1 description
184 AlignmentAnnotation[] anns = al.getSequenceAt(0).getAnnotation();
188 * Seq2 description has a '1' in it
190 anns = al.getSequenceAt(1).getAnnotation();
191 assertEquals(1, anns.length);
192 assertEquals(1d, anns[0].getScore(), 0.001d);
195 * Seq3 description has '28E30' in it
197 * Note: 1.8E308 or larger would result in 'Infinity'
199 anns = al.getSequenceAt(2).getAnnotation();
200 assertEquals(1, anns.length);
201 assertEquals(2.8E31d, anns[0].getScore(), 0.001d);
204 * Seq4 description has several numbers in it
206 anns = al.getSequenceAt(3).getAnnotation();
207 assertEquals(5, anns.length);
208 assertEquals(1d, anns[0].getScore(), 0.001d);
209 assertEquals(10960d, anns[1].getScore(), 0.001d);
210 assertEquals(19d, anns[2].getScore(), 0.001d);
211 assertEquals(16d, anns[3].getScore(), 0.001d);
212 assertEquals(12d, anns[4].getScore(), 0.001d);