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;
31 import java.util.List;
33 import org.testng.annotations.BeforeMethod;
34 import org.testng.annotations.Test;
36 public class ParsePropertiesTest
41 private ParseProperties pp;
44 * Construct an alignment with 4 sequences with varying description format
46 @BeforeMethod(alwaysRun = true)
49 SequenceI[] seqs = new SequenceI[] {
50 new Sequence("sq1", "THISISAPLACEHOLDER"),
51 new Sequence("sq2", "THISISAPLACEHOLDER"),
52 new Sequence("sq3", "THISISAPLACEHOLDER"),
53 new Sequence("sq4", "THISISAPLACEHOLDER") };
54 seqs[0].setDescription("1 mydescription1");
55 seqs[1].setDescription("mydescription2");
56 seqs[2].setDescription("2. 0.1 mydescription+3");
57 seqs[3].setDescription("3 0.01 mydescription4");
58 al = new Alignment(seqs);
60 pp = new ParseProperties(al);
65 * Test with a description pattern that matches any string ending in one or
66 * more 'number characters' (0-9+.), i.e. greedily matches any trailing
67 * numeric part of the string
69 @Test(groups = { "Functional" })
70 public void testGetScoresFromDescription()
72 String regex = ".*([-0-9.+]+)";
73 final int count = pp.getScoresFromDescription("my Score",
74 "my Score Description", regex, true);
75 System.out.println("Matched " + count + " for " + regex);
76 assertEquals(4, count);
79 * Verify values 1/2/3/4 have been parsed from sequence descriptions
81 AlignmentAnnotation[] anns = al.getSequenceAt(0).getAnnotation();
82 assertEquals(1, anns.length);
83 assertEquals(1d, anns[0].getScore(), 0.001d);
84 assertEquals("my Score Description", anns[0].description);
85 assertEquals("my Score", anns[0].label);
86 anns = al.getSequenceAt(1).getAnnotation();
87 assertEquals(1, anns.length);
88 assertEquals(2d, anns[0].getScore(), 0.001d);
89 assertEquals("my Score Description", anns[0].description);
90 assertEquals("my Score", anns[0].label);
91 anns = al.getSequenceAt(2).getAnnotation();
92 assertEquals(1, anns.length);
93 assertEquals(3d, anns[0].getScore(), 0.001d);
94 anns = al.getSequenceAt(3).getAnnotation();
95 assertEquals(1, anns.length);
96 assertEquals(4d, anns[0].getScore(), 0.001d);
100 * Test with a description pattern that matches any string (or none), followed
101 * by a 'number character' (0-9+.), followed by at least one separator
102 * character, followed by at least one 'number character', then any trailing
105 @Test(groups = { "Functional" })
106 public void testGetScoresFromDescription_twoScores()
108 String regex = ".*([-0-9.+]+).+([-0-9.+]+).*";
109 final int count = pp.getScoresFromDescription("my Score",
110 "my Score Description", regex, true);
111 System.out.println("Matched " + count + " for " + regex);
112 assertEquals(3, count);
115 * Seq1 has two score values parsed out
117 AlignmentAnnotation[] anns = al.getSequenceAt(0).getAnnotation();
118 assertEquals(2, anns.length);
119 assertEquals(1d, anns[0].getScore(), 0.001d);
120 assertEquals("my Score Description", anns[0].description);
121 assertEquals("my Score", anns[0].label);
122 assertEquals(1d, anns[1].getScore(), 0.001d);
123 assertEquals("my Score Description (column 1)", anns[1].description);
124 assertEquals("my Score_1", anns[1].label);
127 * Seq2 has no score parsed out (is this right?)
129 assertNull(al.getSequenceAt(1).getAnnotation());
132 * Seq3 has two score values parsed out
134 // TODO parsed values (1.0 and 3.0) look wrong v description
135 // would expect 2.0 and 0.1
136 // undesired 'greedy' behaviour of regex?
137 anns = al.getSequenceAt(2).getAnnotation();
138 assertEquals(2, anns.length);
139 assertEquals(1d, anns[0].getScore(), 0.001d);
140 assertEquals("my Score Description", anns[0].description);
141 assertEquals("my Score", anns[0].label);
142 assertEquals(3d, anns[1].getScore(), 0.001d);
143 assertEquals("my Score Description (column 1)", anns[1].description);
144 assertEquals("my Score_1", anns[1].label);
147 * Seq3 has two score values parsed out
149 // TODO parsed values (1.0 and 4.0) look wrong v description
150 // would expect 3 and 0.01
151 anns = al.getSequenceAt(3).getAnnotation();
152 assertEquals(2, anns.length);
153 assertEquals(1d, anns[0].getScore(), 0.001d);
154 assertEquals("my Score Description", anns[0].description);
155 assertEquals("my Score", anns[0].label);
156 assertEquals(4d, anns[1].getScore(), 0.001d);
157 assertEquals("my Score Description (column 1)", anns[1].description);
158 assertEquals("my Score_1", anns[1].label);
162 * Test with a regex that looks for numbers separated by words - as currently
163 * used in Jalview (May 2015)
165 * @see AlignFrame.extractScores_actionPerformed
167 @Test(groups = { "Functional" })
168 public void testGetScoresFromDescription_wordBoundaries()
170 String regex = "\\W*([-+eE0-9.]+)";
171 List<SequenceI> seqs = al.getSequences();
172 seqs.get(0).setDescription("Ferredoxin");
173 seqs.get(1).setDescription(" Ferredoxin-1, chloroplast precursor");
174 seqs.get(2).setDescription("GH28E30p");
175 seqs.get(3).setDescription("At1g10960/T19D16_12");
176 final int count = pp.getScoresFromDescription("description column",
177 "score in description column ", regex, true);
178 assertEquals(3, count);
181 * No score parsable from seq1 description
183 AlignmentAnnotation[] anns = al.getSequenceAt(0).getAnnotation();
187 * Seq2 description has a '1' in it
189 anns = al.getSequenceAt(1).getAnnotation();
190 assertEquals(1, anns.length);
191 assertEquals(1d, anns[0].getScore(), 0.001d);
194 * Seq3 description has '28E30' in it
196 * Note: 1.8E308 or larger would result in 'Infinity'
198 anns = al.getSequenceAt(2).getAnnotation();
199 assertEquals(1, anns.length);
200 assertEquals(2.8E31d, anns[0].getScore(), 0.001d);
203 * Seq4 description has several numbers in it
205 anns = al.getSequenceAt(3).getAnnotation();
206 assertEquals(5, anns.length);
207 assertEquals(1d, anns[0].getScore(), 0.001d);
208 assertEquals(10960d, anns[1].getScore(), 0.001d);
209 assertEquals(19d, anns[2].getScore(), 0.001d);
210 assertEquals(16d, anns[3].getScore(), 0.001d);
211 assertEquals(12d, anns[4].getScore(), 0.001d);