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.datamodel;
23 import static org.testng.AssertJUnit.assertEquals;
24 import static org.testng.AssertJUnit.assertFalse;
25 import static org.testng.AssertJUnit.assertNotNull;
26 import static org.testng.AssertJUnit.assertNotSame;
27 import static org.testng.AssertJUnit.assertNull;
28 import static org.testng.AssertJUnit.assertSame;
29 import static org.testng.AssertJUnit.assertTrue;
31 import jalview.analysis.AlignmentGenerator;
32 import jalview.commands.EditCommand;
33 import jalview.commands.EditCommand.Action;
34 import jalview.datamodel.PDBEntry.Type;
35 import jalview.gui.JvOptionPane;
36 import jalview.util.MapList;
39 import java.util.ArrayList;
40 import java.util.Arrays;
41 import java.util.BitSet;
42 import java.util.Iterator;
43 import java.util.List;
44 import java.util.Vector;
46 import org.testng.Assert;
47 import org.testng.annotations.BeforeClass;
48 import org.testng.annotations.BeforeMethod;
49 import org.testng.annotations.Test;
51 import junit.extensions.PA;
53 public class SequenceTest
56 @BeforeClass(alwaysRun = true)
57 public void setUpJvOptionPane()
59 JvOptionPane.setInteractiveMode(false);
60 JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
65 @BeforeMethod(alwaysRun = true)
68 seq = new Sequence("FER1", "AKPNGVL");
71 @Test(groups = { "Functional" })
72 public void testInsertGapsAndGapmaps()
74 SequenceI aseq = seq.deriveSequence();
75 aseq.insertCharAt(2, 3, '-');
76 aseq.insertCharAt(6, 3, '-');
77 assertEquals("Gap insertions not correct", "AK---P---NGVL",
78 aseq.getSequenceAsString());
79 List<int[]> gapInt = aseq.getInsertions();
80 assertEquals("Gap interval 1 start wrong", 2, gapInt.get(0)[0]);
81 assertEquals("Gap interval 1 end wrong", 4, gapInt.get(0)[1]);
82 assertEquals("Gap interval 2 start wrong", 6, gapInt.get(1)[0]);
83 assertEquals("Gap interval 2 end wrong", 8, gapInt.get(1)[1]);
85 BitSet gapfield = aseq.getInsertionsAsBits();
86 BitSet expectedgaps = new BitSet();
87 expectedgaps.set(2, 5);
88 expectedgaps.set(6, 9);
90 assertEquals(6, expectedgaps.cardinality());
92 assertEquals("getInsertionsAsBits didn't mark expected number of gaps",
93 6, gapfield.cardinality());
95 assertEquals("getInsertionsAsBits not correct.", expectedgaps, gapfield);
98 @Test(groups = ("Functional"))
99 public void testIsProtein()
102 assertTrue(new Sequence("prot", "ASDFASDFASDF").isProtein());
104 assertFalse(new Sequence("prot", "ACGTACGTACGT").isProtein());
106 SequenceI sq = new Sequence("prot", "ACGUACGUACGU");
107 assertFalse(sq.isProtein());
108 // change sequence, should trigger an update of cached result
109 sq.setSequence("ASDFASDFADSF");
110 assertTrue(sq.isProtein());
113 @Test(groups = { "Functional" })
114 public void testGetAnnotation()
116 // initial state returns null not an empty array
117 assertNull(seq.getAnnotation());
118 AlignmentAnnotation ann = addAnnotation("label1", "desc1", "calcId1",
120 AlignmentAnnotation[] anns = seq.getAnnotation();
121 assertEquals(1, anns.length);
122 assertSame(ann, anns[0]);
124 // removing all annotations reverts array to null
125 seq.removeAlignmentAnnotation(ann);
126 assertNull(seq.getAnnotation());
129 @Test(groups = { "Functional" })
130 public void testGetAnnotation_forLabel()
132 AlignmentAnnotation ann1 = addAnnotation("label1", "desc1", "calcId1",
134 addAnnotation("label2", "desc2", "calcId2", 1f);
135 AlignmentAnnotation ann3 = addAnnotation("label1", "desc3", "calcId3",
137 AlignmentAnnotation[] anns = seq.getAnnotation("label1");
138 assertEquals(2, anns.length);
139 assertSame(ann1, anns[0]);
140 assertSame(ann3, anns[1]);
143 private AlignmentAnnotation addAnnotation(String label,
144 String description, String calcId, float value)
146 final AlignmentAnnotation annotation = new AlignmentAnnotation(label,
148 annotation.setCalcId(calcId);
149 seq.addAlignmentAnnotation(annotation);
153 @Test(groups = { "Functional" })
154 public void testGetAlignmentAnnotations_forCalcIdAndLabel()
156 addAnnotation("label1", "desc1", "calcId1", 1f);
157 AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
159 addAnnotation("label2", "desc3", "calcId3", 1f);
160 AlignmentAnnotation ann4 = addAnnotation("label2", "desc3", "calcId2",
162 addAnnotation("label5", "desc3", null, 1f);
163 addAnnotation(null, "desc3", "calcId3", 1f);
165 List<AlignmentAnnotation> anns = seq.getAlignmentAnnotations("calcId2",
167 assertEquals(2, anns.size());
168 assertSame(ann2, anns.get(0));
169 assertSame(ann4, anns.get(1));
171 assertTrue(seq.getAlignmentAnnotations("calcId2", "label3").isEmpty());
172 assertTrue(seq.getAlignmentAnnotations("calcId3", "label5").isEmpty());
173 assertTrue(seq.getAlignmentAnnotations("calcId2", null).isEmpty());
174 assertTrue(seq.getAlignmentAnnotations(null, "label3").isEmpty());
175 assertTrue(seq.getAlignmentAnnotations(null, null).isEmpty());
179 * Tests for addAlignmentAnnotation. Note this method has the side-effect of
180 * setting the sequenceRef on the annotation. Adding the same annotation twice
183 @Test(groups = { "Functional" })
184 public void testAddAlignmentAnnotation()
186 assertNull(seq.getAnnotation());
187 final AlignmentAnnotation annotation = new AlignmentAnnotation("a",
189 assertNull(annotation.sequenceRef);
190 seq.addAlignmentAnnotation(annotation);
191 assertSame(seq, annotation.sequenceRef);
192 AlignmentAnnotation[] anns = seq.getAnnotation();
193 assertEquals(1, anns.length);
194 assertSame(annotation, anns[0]);
196 // re-adding does nothing
197 seq.addAlignmentAnnotation(annotation);
198 anns = seq.getAnnotation();
199 assertEquals(1, anns.length);
200 assertSame(annotation, anns[0]);
202 // an identical but different annotation can be added
203 final AlignmentAnnotation annotation2 = new AlignmentAnnotation("a",
205 seq.addAlignmentAnnotation(annotation2);
206 anns = seq.getAnnotation();
207 assertEquals(2, anns.length);
208 assertSame(annotation, anns[0]);
209 assertSame(annotation2, anns[1]);
212 @Test(groups = { "Functional" })
213 public void testGetStartGetEnd()
215 SequenceI sq = new Sequence("test", "ABCDEF");
216 assertEquals(1, sq.getStart());
217 assertEquals(6, sq.getEnd());
219 sq = new Sequence("test", "--AB-C-DEF--");
220 assertEquals(1, sq.getStart());
221 assertEquals(6, sq.getEnd());
223 sq = new Sequence("test", "----");
224 assertEquals(1, sq.getStart());
225 assertEquals(0, sq.getEnd()); // ??
229 * Tests for the method that returns an alignment column position (base 1) for
230 * a given sequence position (base 1).
232 @Test(groups = { "Functional" })
233 public void testFindIndex()
236 * call sequenceChanged() after each test to invalidate any cursor,
237 * forcing the 1-arg findIndex to be executed
239 SequenceI sq = new Sequence("test", "ABCDEF");
240 assertEquals(0, sq.findIndex(0));
241 sq.sequenceChanged();
242 assertEquals(1, sq.findIndex(1));
243 sq.sequenceChanged();
244 assertEquals(5, sq.findIndex(5));
245 sq.sequenceChanged();
246 assertEquals(6, sq.findIndex(6));
247 sq.sequenceChanged();
248 assertEquals(6, sq.findIndex(9));
250 sq = new Sequence("test/8-13", "-A--B-C-D-E-F--");
251 assertEquals(2, sq.findIndex(8));
252 sq.sequenceChanged();
253 assertEquals(5, sq.findIndex(9));
254 sq.sequenceChanged();
255 assertEquals(7, sq.findIndex(10));
257 // before start returns 0
258 sq.sequenceChanged();
259 assertEquals(0, sq.findIndex(0));
260 sq.sequenceChanged();
261 assertEquals(0, sq.findIndex(-1));
263 // beyond end returns last residue column
264 sq.sequenceChanged();
265 assertEquals(13, sq.findIndex(99));
269 * Tests for the method that returns a dataset sequence position (start..) for
270 * an aligned column position (base 0).
272 @Test(groups = { "Functional" })
273 public void testFindPosition()
276 * call sequenceChanged() after each test to invalidate any cursor,
277 * forcing the 1-arg findPosition to be executed
279 SequenceI sq = new Sequence("test/8-13", "ABCDEF");
280 assertEquals(8, sq.findPosition(0));
281 // Sequence should now hold a cursor at [8, 0]
282 assertEquals("test:Pos8:Col1:startCol1:endCol0:tok0",
283 PA.getValue(sq, "cursor").toString());
284 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
285 int token = (int) PA.getValue(sq, "changeCount");
286 assertEquals(new SequenceCursor(sq, 8, 1, token), cursor);
288 sq.sequenceChanged();
291 * find F13 at column offset 5, cursor should update to [13, 6]
292 * endColumn is found and saved in cursor
294 assertEquals(13, sq.findPosition(5));
295 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
296 assertEquals(++token, (int) PA.getValue(sq, "changeCount"));
297 assertEquals(new SequenceCursor(sq, 13, 6, token), cursor);
298 assertEquals("test:Pos13:Col6:startCol1:endCol6:tok1",
299 PA.getValue(sq, "cursor").toString());
301 // assertEquals(-1, seq.findPosition(6)); // fails
303 sq = new Sequence("test/8-11", "AB-C-D--");
304 token = (int) PA.getValue(sq, "changeCount"); // 0
305 assertEquals(8, sq.findPosition(0));
306 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
307 assertEquals(new SequenceCursor(sq, 8, 1, token), cursor);
308 assertEquals("test:Pos8:Col1:startCol1:endCol0:tok0",
309 PA.getValue(sq, "cursor").toString());
311 sq.sequenceChanged();
312 assertEquals(9, sq.findPosition(1));
313 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
314 assertEquals(new SequenceCursor(sq, 9, 2, ++token), cursor);
315 assertEquals("test:Pos9:Col2:startCol1:endCol0:tok1",
316 PA.getValue(sq, "cursor").toString());
318 sq.sequenceChanged();
319 // gap position 'finds' residue to the right (not the left as per javadoc)
320 // cursor is set to the last residue position found [B 2]
321 assertEquals(10, sq.findPosition(2));
322 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
323 assertEquals(new SequenceCursor(sq, 9, 2, ++token), cursor);
324 assertEquals("test:Pos9:Col2:startCol1:endCol0:tok2",
325 PA.getValue(sq, "cursor").toString());
327 sq.sequenceChanged();
328 assertEquals(10, sq.findPosition(3));
329 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
330 assertEquals(new SequenceCursor(sq, 10, 4, ++token), cursor);
331 assertEquals("test:Pos10:Col4:startCol1:endCol0:tok3",
332 PA.getValue(sq, "cursor").toString());
334 sq.sequenceChanged();
335 // column[4] is the gap after C - returns D11
336 // cursor is set to [C 4]
337 assertEquals(11, sq.findPosition(4));
338 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
339 assertEquals(new SequenceCursor(sq, 10, 4, ++token), cursor);
340 assertEquals("test:Pos10:Col4:startCol1:endCol0:tok4",
341 PA.getValue(sq, "cursor").toString());
343 sq.sequenceChanged();
344 assertEquals(11, sq.findPosition(5)); // D
345 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
346 assertEquals(new SequenceCursor(sq, 11, 6, ++token), cursor);
347 // lastCol has been found and saved in the cursor
348 assertEquals("test:Pos11:Col6:startCol1:endCol6:tok5",
349 PA.getValue(sq, "cursor").toString());
351 sq.sequenceChanged();
352 // returns 1 more than sequence length if off the end ?!?
353 assertEquals(12, sq.findPosition(6));
355 sq.sequenceChanged();
356 assertEquals(12, sq.findPosition(7));
359 * first findPosition should also set firstResCol in cursor
361 sq = new Sequence("test/8-13", "--AB-C-DEF--");
362 assertEquals(8, sq.findPosition(0));
363 assertNull(PA.getValue(sq, "cursor"));
365 sq.sequenceChanged();
366 assertEquals(8, sq.findPosition(1));
367 assertNull(PA.getValue(sq, "cursor"));
369 sq.sequenceChanged();
370 assertEquals(8, sq.findPosition(2));
371 assertEquals("test:Pos8:Col3:startCol3:endCol0:tok2",
372 PA.getValue(sq, "cursor").toString());
374 sq.sequenceChanged();
375 assertEquals(9, sq.findPosition(3));
376 assertEquals("test:Pos9:Col4:startCol3:endCol0:tok3",
377 PA.getValue(sq, "cursor").toString());
379 sq.sequenceChanged();
380 // column[4] is a gap, returns next residue pos (C10)
381 // cursor is set to last residue found [B]
382 assertEquals(10, sq.findPosition(4));
383 assertEquals("test:Pos9:Col4:startCol3:endCol0:tok4",
384 PA.getValue(sq, "cursor").toString());
386 sq.sequenceChanged();
387 assertEquals(10, sq.findPosition(5));
388 assertEquals("test:Pos10:Col6:startCol3:endCol0:tok5",
389 PA.getValue(sq, "cursor").toString());
391 sq.sequenceChanged();
392 // column[6] is a gap, returns next residue pos (D11)
393 // cursor is set to last residue found [C]
394 assertEquals(11, sq.findPosition(6));
395 assertEquals("test:Pos10:Col6:startCol3:endCol0:tok6",
396 PA.getValue(sq, "cursor").toString());
398 sq.sequenceChanged();
399 assertEquals(11, sq.findPosition(7));
400 assertEquals("test:Pos11:Col8:startCol3:endCol0:tok7",
401 PA.getValue(sq, "cursor").toString());
403 sq.sequenceChanged();
404 assertEquals(12, sq.findPosition(8));
405 assertEquals("test:Pos12:Col9:startCol3:endCol0:tok8",
406 PA.getValue(sq, "cursor").toString());
409 * when the last residue column is found, it is set in the cursor
411 sq.sequenceChanged();
412 assertEquals(13, sq.findPosition(9));
413 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok9",
414 PA.getValue(sq, "cursor").toString());
416 sq.sequenceChanged();
417 assertEquals(14, sq.findPosition(10));
418 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok10",
419 PA.getValue(sq, "cursor").toString());
422 * findPosition for column beyond sequence length
423 * returns 1 more than last residue position
425 sq.sequenceChanged();
426 assertEquals(14, sq.findPosition(11));
427 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok11",
428 PA.getValue(sq, "cursor").toString());
430 sq.sequenceChanged();
431 assertEquals(14, sq.findPosition(99));
432 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok12",
433 PA.getValue(sq, "cursor").toString());
436 * gapped sequence ending in non-gap
438 sq = new Sequence("test/8-13", "--AB-C-DEF");
439 assertEquals(13, sq.findPosition(9));
440 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok0",
441 PA.getValue(sq, "cursor").toString());
442 sq.sequenceChanged();
443 assertEquals(12, sq.findPosition(8));
444 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
445 // sequenceChanged() invalidates cursor.lastResidueColumn
446 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
447 assertEquals("test:Pos12:Col9:startCol3:endCol0:tok1",
449 // findPosition with cursor accepts base 1 column values
450 assertEquals(13, ((Sequence) sq).findPosition(10, cursor));
451 assertEquals(13, sq.findPosition(9)); // F13
452 // lastResidueColumn has now been found and saved in cursor
453 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok1",
454 PA.getValue(sq, "cursor").toString());
457 @Test(groups = { "Functional" })
458 public void testDeleteChars()
463 SequenceI sq = new Sequence("test", "ABCDEF");
464 assertNull(PA.getValue(sq, "datasetSequence"));
465 assertEquals(1, sq.getStart());
466 assertEquals(6, sq.getEnd());
467 sq.deleteChars(2, 3);
468 assertEquals("ABDEF", sq.getSequenceAsString());
469 assertEquals(1, sq.getStart());
470 assertEquals(5, sq.getEnd());
471 assertNull(PA.getValue(sq, "datasetSequence"));
476 sq = new Sequence("test", "ABCDEF");
477 sq.deleteChars(0, 2);
478 assertEquals("CDEF", sq.getSequenceAsString());
479 assertEquals(3, sq.getStart());
480 assertEquals(6, sq.getEnd());
481 assertNull(PA.getValue(sq, "datasetSequence"));
486 sq = new Sequence("test", "ABCDEF");
487 sq.deleteChars(4, 6);
488 assertEquals("ABCD", sq.getSequenceAsString());
489 assertEquals(1, sq.getStart());
490 assertEquals(4, sq.getEnd());
491 assertNull(PA.getValue(sq, "datasetSequence"));
494 @Test(groups = { "Functional" })
495 public void testDeleteChars_withDbRefsAndFeatures()
498 * internal delete - new dataset sequence created
499 * gets a copy of any dbrefs
501 SequenceI sq = new Sequence("test", "ABCDEF");
502 sq.createDatasetSequence();
503 DBRefEntry dbr1 = new DBRefEntry("Uniprot", "0", "a123");
505 Object ds = PA.getValue(sq, "datasetSequence");
507 assertEquals(1, sq.getStart());
508 assertEquals(6, sq.getEnd());
509 sq.deleteChars(2, 3);
510 assertEquals("ABDEF", sq.getSequenceAsString());
511 assertEquals(1, sq.getStart());
512 assertEquals(5, sq.getEnd());
513 Object newDs = PA.getValue(sq, "datasetSequence");
514 assertNotNull(newDs);
515 assertNotSame(ds, newDs);
516 assertNotNull(sq.getDBRefs());
517 assertEquals(1, sq.getDBRefs().length);
518 assertNotSame(dbr1, sq.getDBRefs()[0]);
519 assertEquals(dbr1, sq.getDBRefs()[0]);
522 * internal delete with sequence features
523 * (failure case for JAL-2541)
525 sq = new Sequence("test", "ABCDEF");
526 sq.createDatasetSequence();
527 SequenceFeature sf1 = new SequenceFeature("Cath", "desc", 2, 4, 2f,
529 sq.addSequenceFeature(sf1);
530 ds = PA.getValue(sq, "datasetSequence");
532 assertEquals(1, sq.getStart());
533 assertEquals(6, sq.getEnd());
534 sq.deleteChars(2, 4);
535 assertEquals("ABEF", sq.getSequenceAsString());
536 assertEquals(1, sq.getStart());
537 assertEquals(4, sq.getEnd());
538 newDs = PA.getValue(sq, "datasetSequence");
539 assertNotNull(newDs);
540 assertNotSame(ds, newDs);
541 List<SequenceFeature> sfs = sq.getSequenceFeatures();
542 assertEquals(1, sfs.size());
543 assertNotSame(sf1, sfs.get(0));
544 assertEquals(sf1, sfs.get(0));
547 * delete at start - no new dataset sequence created
548 * any sequence features remain as before
550 sq = new Sequence("test", "ABCDEF");
551 sq.createDatasetSequence();
552 ds = PA.getValue(sq, "datasetSequence");
553 sf1 = new SequenceFeature("Cath", "desc", 2, 4, 2f, "CathGroup");
554 sq.addSequenceFeature(sf1);
555 sq.deleteChars(0, 2);
556 assertEquals("CDEF", sq.getSequenceAsString());
557 assertEquals(3, sq.getStart());
558 assertEquals(6, sq.getEnd());
559 assertSame(ds, PA.getValue(sq, "datasetSequence"));
560 sfs = sq.getSequenceFeatures();
562 assertEquals(1, sfs.size());
563 assertSame(sf1, sfs.get(0));
566 * delete at end - no new dataset sequence created
567 * any dbrefs remain as before
569 sq = new Sequence("test", "ABCDEF");
570 sq.createDatasetSequence();
571 ds = PA.getValue(sq, "datasetSequence");
572 dbr1 = new DBRefEntry("Uniprot", "0", "a123");
574 sq.deleteChars(4, 6);
575 assertEquals("ABCD", sq.getSequenceAsString());
576 assertEquals(1, sq.getStart());
577 assertEquals(4, sq.getEnd());
578 assertSame(ds, PA.getValue(sq, "datasetSequence"));
579 assertNotNull(sq.getDBRefs());
580 assertEquals(1, sq.getDBRefs().length);
581 assertSame(dbr1, sq.getDBRefs()[0]);
584 @Test(groups = { "Functional" })
585 public void testInsertCharAt()
587 // non-static methods:
588 SequenceI sq = new Sequence("test", "ABCDEF");
589 sq.insertCharAt(0, 'z');
590 assertEquals("zABCDEF", sq.getSequenceAsString());
591 sq.insertCharAt(2, 2, 'x');
592 assertEquals("zAxxBCDEF", sq.getSequenceAsString());
594 // for static method see StringUtilsTest
598 * Test the method that returns an array of aligned sequence positions where
599 * the array index is the data sequence position (both base 0).
601 @Test(groups = { "Functional" })
602 public void testGapMap()
604 SequenceI sq = new Sequence("test", "-A--B-CD-E--F-");
605 sq.createDatasetSequence();
606 assertEquals("[1, 4, 6, 7, 9, 12]", Arrays.toString(sq.gapMap()));
610 * Test the method that gets sequence features, either from the sequence or
613 @Test(groups = { "Functional" })
614 public void testGetSequenceFeatures()
616 SequenceI sq = new Sequence("test", "GATCAT");
617 sq.createDatasetSequence();
619 assertTrue(sq.getSequenceFeatures().isEmpty());
622 * SequenceFeature on sequence
624 SequenceFeature sf = new SequenceFeature("Cath", "desc", 2, 4, 2f, null);
625 sq.addSequenceFeature(sf);
626 List<SequenceFeature> sfs = sq.getSequenceFeatures();
627 assertEquals(1, sfs.size());
628 assertSame(sf, sfs.get(0));
631 * SequenceFeature on sequence and dataset sequence; returns that on
634 * Note JAL-2046: spurious: we have no use case for this at the moment.
635 * This test also buggy - as sf2.equals(sf), no new feature is added
637 SequenceFeature sf2 = new SequenceFeature("Cath", "desc", 2, 4, 2f,
639 sq.getDatasetSequence().addSequenceFeature(sf2);
640 sfs = sq.getSequenceFeatures();
641 assertEquals(1, sfs.size());
642 assertSame(sf, sfs.get(0));
645 * SequenceFeature on dataset sequence only
646 * Note JAL-2046: spurious: we have no use case for setting a non-dataset sequence's feature array to null at the moment.
648 sq.setSequenceFeatures(null);
649 assertTrue(sq.getDatasetSequence().getSequenceFeatures().isEmpty());
652 * Corrupt case - no SequenceFeature, dataset's dataset is the original
653 * sequence. Test shows no infinite loop results.
655 sq.getDatasetSequence().setSequenceFeatures(null);
657 * is there a usecase for this ? setDatasetSequence should throw an error if
658 * this actually occurs.
662 sq.getDatasetSequence().setDatasetSequence(sq); // loop!
663 Assert.fail("Expected Error to be raised when calling setDatasetSequence with self reference");
664 } catch (IllegalArgumentException e)
666 // TODO Jalview error/exception class for raising implementation errors
667 assertTrue(e.getMessage().toLowerCase()
668 .contains("implementation error"));
670 assertTrue(sq.getSequenceFeatures().isEmpty());
674 * Test the method that returns an array, indexed by sequence position, whose
675 * entries are the residue positions at the sequence position (or to the right
678 @Test(groups = { "Functional" })
679 public void testFindPositionMap()
682 * Note: Javadoc for findPosition says it returns the residue position to
683 * the left of a gapped position; in fact it returns the position to the
684 * right. Also it returns a non-existent residue position for a gap beyond
687 Sequence sq = new Sequence("TestSeq", "AB.C-D E.");
688 int[] map = sq.findPositionMap();
689 assertEquals(Arrays.toString(new int[] { 1, 2, 3, 3, 4, 4, 5, 5, 6 }),
690 Arrays.toString(map));
694 * Test for getSubsequence
696 @Test(groups = { "Functional" })
697 public void testGetSubsequence()
699 SequenceI sq = new Sequence("TestSeq", "ABCDEFG");
700 sq.createDatasetSequence();
702 // positions are base 0, end position is exclusive
703 SequenceI subseq = sq.getSubSequence(2, 4);
705 assertEquals("CD", subseq.getSequenceAsString());
706 // start/end are base 1 positions
707 assertEquals(3, subseq.getStart());
708 assertEquals(4, subseq.getEnd());
709 // subsequence shares the full dataset sequence
710 assertSame(sq.getDatasetSequence(), subseq.getDatasetSequence());
714 * test createDatasetSequence behaves to doc
716 @Test(groups = { "Functional" })
717 public void testCreateDatasetSequence()
719 SequenceI sq = new Sequence("my", "ASDASD");
720 sq.addSequenceFeature(new SequenceFeature("type", "desc", 1, 10, 1f,
722 sq.addDBRef(new DBRefEntry("source", "version", "accession"));
723 assertNull(sq.getDatasetSequence());
724 assertNotNull(PA.getValue(sq, "sequenceFeatureStore"));
725 assertNotNull(PA.getValue(sq, "dbrefs"));
727 SequenceI rds = sq.createDatasetSequence();
729 assertNull(rds.getDatasetSequence());
730 assertSame(sq.getDatasetSequence(), rds);
732 // sequence features and dbrefs transferred to dataset sequence
733 assertNull(PA.getValue(sq, "sequenceFeatureStore"));
734 assertNull(PA.getValue(sq, "dbrefs"));
735 assertNotNull(PA.getValue(rds, "sequenceFeatureStore"));
736 assertNotNull(PA.getValue(rds, "dbrefs"));
740 * Test for deriveSequence applied to a sequence with a dataset
742 @Test(groups = { "Functional" })
743 public void testDeriveSequence_existingDataset()
745 Sequence sq = new Sequence("Seq1", "CD");
746 sq.setDatasetSequence(new Sequence("Seq1", "ABCDEF"));
747 sq.getDatasetSequence().addSequenceFeature(
748 new SequenceFeature("", "", 1, 2, 0f, null));
752 sq.setDescription("Test sequence description..");
753 sq.setVamsasId("TestVamsasId");
754 sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
756 sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
757 sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
758 sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
759 sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
761 sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
762 sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
763 sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
764 sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
766 // these are the same as ones already added
767 DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
768 DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version2", "2PDB");
770 List<DBRefEntry> primRefs = Arrays.asList(new DBRefEntry[] { pdb1pdb,
773 sq.getDatasetSequence().addDBRef(pdb1pdb); // should do nothing
774 sq.getDatasetSequence().addDBRef(pdb2pdb); // should do nothing
775 sq.getDatasetSequence().addDBRef(
776 new DBRefEntry("PDB", "version3", "3PDB")); // should do nothing
777 sq.getDatasetSequence().addDBRef(
778 new DBRefEntry("PDB", "version4", "4PDB")); // should do nothing
780 PDBEntry pdbe1a = new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
781 PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
782 PDBEntry pdbe2a = new PDBEntry("2PDB", "A", Type.MMCIF,
784 PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF,
786 sq.getDatasetSequence().addPDBId(pdbe1a);
787 sq.getDatasetSequence().addPDBId(pdbe1b);
788 sq.getDatasetSequence().addPDBId(pdbe2a);
789 sq.getDatasetSequence().addPDBId(pdbe2b);
792 * test we added pdb entries to the dataset sequence
794 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(), Arrays
795 .asList(new PDBEntry[] { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
796 "PDB Entries were not found on dataset sequence.");
799 * we should recover a pdb entry that is on the dataset sequence via PDBEntry
801 Assert.assertEquals(pdbe1a,
802 sq.getDatasetSequence().getPDBEntry("1PDB"),
803 "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
804 ArrayList<Annotation> annotsList = new ArrayList<>();
805 System.out.println(">>>>>> " + sq.getSequenceAsString().length());
806 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
807 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
808 Annotation[] annots = annotsList.toArray(new Annotation[0]);
809 sq.addAlignmentAnnotation(new AlignmentAnnotation("Test annot",
810 "Test annot description", annots));
811 sq.getDatasetSequence().addAlignmentAnnotation(
812 new AlignmentAnnotation("Test annot", "Test annot description",
814 Assert.assertEquals(sq.getDescription(), "Test sequence description..");
815 Assert.assertEquals(sq.getDBRefs().length, 5); // DBRefs are on dataset
817 Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
818 Assert.assertNotNull(sq.getAnnotation());
819 Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
820 Assert.assertEquals(sq.getDatasetSequence().getDBRefs().length, 5); // same
823 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries().size(),
825 Assert.assertNotNull(sq.getDatasetSequence().getAnnotation());
827 Sequence derived = (Sequence) sq.deriveSequence();
829 Assert.assertEquals(derived.getDescription(),
830 "Test sequence description..");
831 Assert.assertEquals(derived.getDBRefs().length, 5); // come from dataset
832 Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
833 Assert.assertNotNull(derived.getAnnotation());
834 Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
835 Assert.assertEquals(derived.getDatasetSequence().getDBRefs().length, 5);
836 Assert.assertEquals(derived.getDatasetSequence().getAllPDBEntries()
838 Assert.assertNotNull(derived.getDatasetSequence().getAnnotation());
840 assertEquals("CD", derived.getSequenceAsString());
841 assertSame(sq.getDatasetSequence(), derived.getDatasetSequence());
843 // derived sequence should access dataset sequence features
844 assertNotNull(sq.getSequenceFeatures());
845 assertEquals(sq.getSequenceFeatures(), derived.getSequenceFeatures());
848 * verify we have primary db refs *just* for PDB IDs with associated
852 assertEquals(primRefs, sq.getPrimaryDBRefs());
853 assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
855 assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
860 * Test for deriveSequence applied to an ungapped sequence with no dataset
862 @Test(groups = { "Functional" })
863 public void testDeriveSequence_noDatasetUngapped()
865 SequenceI sq = new Sequence("Seq1", "ABCDEF");
866 assertEquals(1, sq.getStart());
867 assertEquals(6, sq.getEnd());
868 SequenceI derived = sq.deriveSequence();
869 assertEquals("ABCDEF", derived.getSequenceAsString());
870 assertEquals("ABCDEF", derived.getDatasetSequence()
871 .getSequenceAsString());
875 * Test for deriveSequence applied to a gapped sequence with no dataset
877 @Test(groups = { "Functional" })
878 public void testDeriveSequence_noDatasetGapped()
880 SequenceI sq = new Sequence("Seq1", "AB-C.D EF");
881 assertEquals(1, sq.getStart());
882 assertEquals(6, sq.getEnd());
883 assertNull(sq.getDatasetSequence());
884 SequenceI derived = sq.deriveSequence();
885 assertEquals("AB-C.D EF", derived.getSequenceAsString());
886 assertEquals("ABCDEF", derived.getDatasetSequence()
887 .getSequenceAsString());
890 @Test(groups = { "Functional" })
891 public void testCopyConstructor_noDataset()
893 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
894 seq1.setDescription("description");
895 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
897 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
899 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
900 seq1.addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
902 SequenceI copy = new Sequence(seq1);
904 assertNull(copy.getDatasetSequence());
906 verifyCopiedSequence(seq1, copy);
908 // copy has a copy of the DBRefEntry
909 // this is murky - DBrefs are only copied for dataset sequences
910 // where the test for 'dataset sequence' is 'dataset is null'
911 // but that doesn't distinguish it from an aligned sequence
912 // which has not yet generated a dataset sequence
913 // NB getDBRef looks inside dataset sequence if not null
914 DBRefEntry[] dbrefs = copy.getDBRefs();
915 assertEquals(1, dbrefs.length);
916 assertFalse(dbrefs[0] == seq1.getDBRefs()[0]);
917 assertTrue(dbrefs[0].equals(seq1.getDBRefs()[0]));
920 @Test(groups = { "Functional" })
921 public void testCopyConstructor_withDataset()
923 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
924 seq1.createDatasetSequence();
925 seq1.setDescription("description");
926 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
928 // JAL-2046 - what is the contract for using a derived sequence's
929 // addSequenceFeature ?
930 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
932 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
933 // here we add DBRef to the dataset sequence:
934 seq1.getDatasetSequence().addDBRef(
935 new DBRefEntry("EMBL", "1.2", "AZ12345"));
937 SequenceI copy = new Sequence(seq1);
939 assertNotNull(copy.getDatasetSequence());
940 assertSame(copy.getDatasetSequence(), seq1.getDatasetSequence());
942 verifyCopiedSequence(seq1, copy);
944 // getDBRef looks inside dataset sequence and this is shared,
945 // so holds the same dbref objects
946 DBRefEntry[] dbrefs = copy.getDBRefs();
947 assertEquals(1, dbrefs.length);
948 assertSame(dbrefs[0], seq1.getDBRefs()[0]);
952 * Helper to make assertions about a copied sequence
957 protected void verifyCopiedSequence(SequenceI seq1, SequenceI copy)
959 // verify basic properties:
960 assertEquals(copy.getName(), seq1.getName());
961 assertEquals(copy.getDescription(), seq1.getDescription());
962 assertEquals(copy.getStart(), seq1.getStart());
963 assertEquals(copy.getEnd(), seq1.getEnd());
964 assertEquals(copy.getSequenceAsString(), seq1.getSequenceAsString());
966 // copy has a copy of the annotation:
967 AlignmentAnnotation[] anns = copy.getAnnotation();
968 assertEquals(1, anns.length);
969 assertFalse(anns[0] == seq1.getAnnotation()[0]);
970 assertEquals(anns[0].label, seq1.getAnnotation()[0].label);
971 assertEquals(anns[0].description, seq1.getAnnotation()[0].description);
972 assertEquals(anns[0].score, seq1.getAnnotation()[0].score);
974 // copy has a copy of the sequence feature:
975 List<SequenceFeature> sfs = copy.getSequenceFeatures();
976 assertEquals(1, sfs.size());
977 if (seq1.getDatasetSequence() != null
978 && copy.getDatasetSequence() == seq1.getDatasetSequence())
980 assertSame(sfs.get(0), seq1.getSequenceFeatures().get(0));
984 assertNotSame(sfs.get(0), seq1.getSequenceFeatures().get(0));
986 assertEquals(sfs.get(0), seq1.getSequenceFeatures().get(0));
988 // copy has a copy of the PDB entry
989 Vector<PDBEntry> pdbs = copy.getAllPDBEntries();
990 assertEquals(1, pdbs.size());
991 assertFalse(pdbs.get(0) == seq1.getAllPDBEntries().get(0));
992 assertTrue(pdbs.get(0).equals(seq1.getAllPDBEntries().get(0)));
995 @Test(groups = "Functional")
996 public void testGetCharAt()
998 SequenceI sq = new Sequence("", "abcde");
999 assertEquals('a', sq.getCharAt(0));
1000 assertEquals('e', sq.getCharAt(4));
1001 assertEquals(' ', sq.getCharAt(5));
1002 assertEquals(' ', sq.getCharAt(-1));
1005 @Test(groups = { "Functional" })
1006 public void testAddSequenceFeatures()
1008 SequenceI sq = new Sequence("", "abcde");
1009 // type may not be null
1010 assertFalse(sq.addSequenceFeature(new SequenceFeature(null, "desc", 4,
1012 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
1014 // can't add a duplicate feature
1015 assertFalse(sq.addSequenceFeature(new SequenceFeature("Cath", "desc",
1017 // can add a different feature
1018 assertTrue(sq.addSequenceFeature(new SequenceFeature("Scop", "desc", 4,
1019 8, 0f, null))); // different type
1020 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath",
1021 "description", 4, 8, 0f, null)));// different description
1022 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 3,
1023 8, 0f, null))); // different start position
1024 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
1025 9, 0f, null))); // different end position
1026 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
1027 8, 1f, null))); // different score
1028 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
1029 8, Float.NaN, null))); // score NaN
1030 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
1031 8, 0f, "Metal"))); // different group
1032 assertEquals(8, sq.getFeatures().getAllFeatures().size());
1036 * Tests for adding (or updating) dbrefs
1038 * @see DBRefEntry#updateFrom(DBRefEntry)
1040 @Test(groups = { "Functional" })
1041 public void testAddDBRef()
1043 SequenceI sq = new Sequence("", "abcde");
1044 assertNull(sq.getDBRefs());
1045 DBRefEntry dbref = new DBRefEntry("Uniprot", "1", "P00340");
1047 assertEquals(1, sq.getDBRefs().length);
1048 assertSame(dbref, sq.getDBRefs()[0]);
1051 * change of version - new entry
1053 DBRefEntry dbref2 = new DBRefEntry("Uniprot", "2", "P00340");
1054 sq.addDBRef(dbref2);
1055 assertEquals(2, sq.getDBRefs().length);
1056 assertSame(dbref, sq.getDBRefs()[0]);
1057 assertSame(dbref2, sq.getDBRefs()[1]);
1060 * matches existing entry - not added
1062 sq.addDBRef(new DBRefEntry("UNIPROT", "1", "p00340"));
1063 assertEquals(2, sq.getDBRefs().length);
1066 * different source = new entry
1068 DBRefEntry dbref3 = new DBRefEntry("UniRef", "1", "p00340");
1069 sq.addDBRef(dbref3);
1070 assertEquals(3, sq.getDBRefs().length);
1071 assertSame(dbref3, sq.getDBRefs()[2]);
1074 * different ref = new entry
1076 DBRefEntry dbref4 = new DBRefEntry("UniRef", "1", "p00341");
1077 sq.addDBRef(dbref4);
1078 assertEquals(4, sq.getDBRefs().length);
1079 assertSame(dbref4, sq.getDBRefs()[3]);
1082 * matching ref with a mapping - map updated
1084 DBRefEntry dbref5 = new DBRefEntry("UniRef", "1", "p00341");
1085 Mapping map = new Mapping(new MapList(new int[] { 1, 3 }, new int[] {
1088 sq.addDBRef(dbref5);
1089 assertEquals(4, sq.getDBRefs().length);
1090 assertSame(dbref4, sq.getDBRefs()[3]);
1091 assertSame(map, dbref4.getMap());
1094 * 'real' version replaces "0" version
1096 dbref2.setVersion("0");
1097 DBRefEntry dbref6 = new DBRefEntry(dbref2.getSource(), "3",
1098 dbref2.getAccessionId());
1099 sq.addDBRef(dbref6);
1100 assertEquals(4, sq.getDBRefs().length);
1101 assertSame(dbref2, sq.getDBRefs()[1]);
1102 assertEquals("3", dbref2.getVersion());
1105 * 'real' version replaces "source:0" version
1107 dbref3.setVersion("Uniprot:0");
1108 DBRefEntry dbref7 = new DBRefEntry(dbref3.getSource(), "3",
1109 dbref3.getAccessionId());
1110 sq.addDBRef(dbref7);
1111 assertEquals(4, sq.getDBRefs().length);
1112 assertSame(dbref3, sq.getDBRefs()[2]);
1113 assertEquals("3", dbref2.getVersion());
1116 @Test(groups = { "Functional" })
1117 public void testGetPrimaryDBRefs_peptide()
1119 SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
1122 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
1123 assertTrue(primaryDBRefs.isEmpty());
1126 sq.setDBRefs(new DBRefEntry[] {});
1127 primaryDBRefs = sq.getPrimaryDBRefs();
1128 assertTrue(primaryDBRefs.isEmpty());
1130 // primary - uniprot
1131 DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
1132 sq.addDBRef(upentry1);
1134 // primary - uniprot with congruent map
1135 DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
1136 upentry2.setMap(new Mapping(null, new MapList(new int[] { 10, 22 },
1137 new int[] { 10, 22 }, 1, 1)));
1138 sq.addDBRef(upentry2);
1140 // primary - uniprot with map of enclosing sequence
1141 DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
1142 upentry3.setMap(new Mapping(null, new MapList(new int[] { 8, 24 },
1143 new int[] { 8, 24 }, 1, 1)));
1144 sq.addDBRef(upentry3);
1146 // not primary - uniprot with map of sub-sequence (5')
1147 DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
1148 upentry4.setMap(new Mapping(null, new MapList(new int[] { 10, 18 },
1149 new int[] { 10, 18 }, 1, 1)));
1150 sq.addDBRef(upentry4);
1152 // not primary - uniprot with map that overlaps 3'
1153 DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
1154 upentry5.setMap(new Mapping(null, new MapList(new int[] { 12, 22 },
1155 new int[] { 12, 22 }, 1, 1)));
1156 sq.addDBRef(upentry5);
1158 // not primary - uniprot with map to different coordinates frame
1159 DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
1160 upentry6.setMap(new Mapping(null, new MapList(new int[] { 12, 18 },
1161 new int[] { 112, 118 }, 1, 1)));
1162 sq.addDBRef(upentry6);
1164 // not primary - dbref to 'non-core' database
1165 DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
1166 sq.addDBRef(upentry7);
1168 // primary - type is PDB
1169 DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
1170 sq.addDBRef(pdbentry);
1172 // not primary - PDBEntry has no file
1173 sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
1175 // not primary - no PDBEntry
1176 sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
1178 // add corroborating PDB entry for primary DBref -
1179 // needs to have a file as well as matching ID
1180 // note PDB ID is not treated as case sensitive
1181 sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB, new File("/blah")
1184 // not valid DBRef - no file..
1185 sq.addPDBId(new PDBEntry("1AAA", null, null, null));
1187 primaryDBRefs = sq.getPrimaryDBRefs();
1188 assertEquals(4, primaryDBRefs.size());
1189 assertTrue("Couldn't find simple primary reference (UNIPROT)",
1190 primaryDBRefs.contains(upentry1));
1191 assertTrue("Couldn't find mapped primary reference (UNIPROT)",
1192 primaryDBRefs.contains(upentry2));
1193 assertTrue("Couldn't find mapped context reference (UNIPROT)",
1194 primaryDBRefs.contains(upentry3));
1195 assertTrue("Couldn't find expected PDB primary reference",
1196 primaryDBRefs.contains(pdbentry));
1199 @Test(groups = { "Functional" })
1200 public void testGetPrimaryDBRefs_nucleotide()
1202 SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10, 34);
1204 // primary - Ensembl
1205 DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
1208 // not primary - Ensembl 'transcript' mapping of sub-sequence
1209 DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
1210 dbr2.setMap(new Mapping(null, new MapList(new int[] { 15, 25 },
1211 new int[] { 1, 11 }, 1, 1)));
1214 // primary - EMBL with congruent map
1215 DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
1216 dbr3.setMap(new Mapping(null, new MapList(new int[] { 10, 34 },
1217 new int[] { 10, 34 }, 1, 1)));
1220 // not primary - to non-core database
1221 DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
1224 // not primary - to protein
1225 DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
1228 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
1229 assertEquals(2, primaryDBRefs.size());
1230 assertTrue(primaryDBRefs.contains(dbr1));
1231 assertTrue(primaryDBRefs.contains(dbr3));
1235 * Test the method that updates the list of PDBEntry from any new DBRefEntry
1238 @Test(groups = { "Functional" })
1239 public void testUpdatePDBIds()
1241 PDBEntry pdbe1 = new PDBEntry("3A6S", null, null, null);
1242 seq.addPDBId(pdbe1);
1243 seq.addDBRef(new DBRefEntry("Ensembl", "8", "ENST1234"));
1244 seq.addDBRef(new DBRefEntry("PDB", "0", "1A70"));
1245 seq.addDBRef(new DBRefEntry("PDB", "0", "4BQGa"));
1246 seq.addDBRef(new DBRefEntry("PDB", "0", "3a6sB"));
1247 // 7 is not a valid chain code:
1248 seq.addDBRef(new DBRefEntry("PDB", "0", "2GIS7"));
1251 List<PDBEntry> pdbIds = seq.getAllPDBEntries();
1252 assertEquals(4, pdbIds.size());
1253 assertSame(pdbe1, pdbIds.get(0));
1254 // chain code got added to 3A6S:
1255 assertEquals("B", pdbe1.getChainCode());
1256 assertEquals("1A70", pdbIds.get(1).getId());
1257 // 4BQGA is parsed into id + chain
1258 assertEquals("4BQG", pdbIds.get(2).getId());
1259 assertEquals("a", pdbIds.get(2).getChainCode());
1260 assertEquals("2GIS7", pdbIds.get(3).getId());
1261 assertNull(pdbIds.get(3).getChainCode());
1265 * Test the method that either adds a pdbid or updates an existing one
1267 @Test(groups = { "Functional" })
1268 public void testAddPDBId()
1270 PDBEntry pdbe = new PDBEntry("3A6S", null, null, null);
1272 assertEquals(1, seq.getAllPDBEntries().size());
1273 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1274 assertSame(pdbe, seq.getPDBEntry("3a6s")); // case-insensitive
1276 // add the same entry
1278 assertEquals(1, seq.getAllPDBEntries().size());
1279 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1281 // add an identical entry
1282 seq.addPDBId(new PDBEntry("3A6S", null, null, null));
1283 assertEquals(1, seq.getAllPDBEntries().size());
1284 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1286 // add a different entry
1287 PDBEntry pdbe2 = new PDBEntry("1A70", null, null, null);
1288 seq.addPDBId(pdbe2);
1289 assertEquals(2, seq.getAllPDBEntries().size());
1290 assertSame(pdbe, seq.getAllPDBEntries().get(0));
1291 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
1293 // update pdbe with chain code, file, type
1294 PDBEntry pdbe3 = new PDBEntry("3a6s", "A", Type.PDB, "filepath");
1295 seq.addPDBId(pdbe3);
1296 assertEquals(2, seq.getAllPDBEntries().size());
1297 assertSame(pdbe, seq.getAllPDBEntries().get(0)); // updated in situ
1298 assertEquals("3A6S", pdbe.getId()); // unchanged
1299 assertEquals("A", pdbe.getChainCode()); // updated
1300 assertEquals(Type.PDB.toString(), pdbe.getType()); // updated
1301 assertEquals("filepath", pdbe.getFile()); // updated
1302 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
1304 // add with a different file path
1305 PDBEntry pdbe4 = new PDBEntry("3a6s", "A", Type.PDB, "filepath2");
1306 seq.addPDBId(pdbe4);
1307 assertEquals(3, seq.getAllPDBEntries().size());
1308 assertSame(pdbe4, seq.getAllPDBEntries().get(2));
1310 // add with a different chain code
1311 PDBEntry pdbe5 = new PDBEntry("3a6s", "B", Type.PDB, "filepath");
1312 seq.addPDBId(pdbe5);
1313 assertEquals(4, seq.getAllPDBEntries().size());
1314 assertSame(pdbe5, seq.getAllPDBEntries().get(3));
1318 groups = { "Functional" },
1319 expectedExceptions = { IllegalArgumentException.class })
1320 public void testSetDatasetSequence_toSelf()
1322 seq.setDatasetSequence(seq);
1326 groups = { "Functional" },
1327 expectedExceptions = { IllegalArgumentException.class })
1328 public void testSetDatasetSequence_cascading()
1330 SequenceI seq2 = new Sequence("Seq2", "xyz");
1331 seq2.createDatasetSequence();
1332 seq.setDatasetSequence(seq2);
1335 @Test(groups = { "Functional" })
1336 public void testFindFeatures()
1338 SequenceI sq = new Sequence("test/8-16", "-ABC--DEF--GHI--");
1339 sq.createDatasetSequence();
1341 assertTrue(sq.findFeatures(1, 99).isEmpty());
1343 // add non-positional feature
1344 SequenceFeature sf0 = new SequenceFeature("Cath", "desc", 0, 0, 2f,
1346 sq.addSequenceFeature(sf0);
1347 // add feature on BCD
1348 SequenceFeature sfBCD = new SequenceFeature("Cath", "desc", 9, 11, 2f,
1350 sq.addSequenceFeature(sfBCD);
1351 // add feature on DE
1352 SequenceFeature sfDE = new SequenceFeature("Cath", "desc", 11, 12, 2f,
1354 sq.addSequenceFeature(sfDE);
1355 // add contact feature at [B, H]
1356 SequenceFeature sfContactBH = new SequenceFeature("Disulphide bond",
1357 "desc", 9, 15, 2f, null);
1358 sq.addSequenceFeature(sfContactBH);
1359 // add contact feature at [F, G]
1360 SequenceFeature sfContactFG = new SequenceFeature("Disulfide Bond",
1361 "desc", 13, 14, 2f, null);
1362 sq.addSequenceFeature(sfContactFG);
1363 // add single position feature at [I]
1364 SequenceFeature sfI = new SequenceFeature("Disulfide Bond",
1365 "desc", 16, 16, null);
1366 sq.addSequenceFeature(sfI);
1368 // no features in columns 1-2 (-A)
1369 List<SequenceFeature> found = sq.findFeatures(1, 2);
1370 assertTrue(found.isEmpty());
1372 // columns 1-6 (-ABC--) includes BCD and B/H feature but not DE
1373 found = sq.findFeatures(1, 6);
1374 assertEquals(2, found.size());
1375 assertTrue(found.contains(sfBCD));
1376 assertTrue(found.contains(sfContactBH));
1378 // columns 5-6 (--) includes (enclosing) BCD but not (contact) B/H feature
1379 found = sq.findFeatures(5, 6);
1380 assertEquals(1, found.size());
1381 assertTrue(found.contains(sfBCD));
1383 // columns 7-10 (DEF-) includes BCD, DE, F/G but not B/H feature
1384 found = sq.findFeatures(7, 10);
1385 assertEquals(3, found.size());
1386 assertTrue(found.contains(sfBCD));
1387 assertTrue(found.contains(sfDE));
1388 assertTrue(found.contains(sfContactFG));
1390 // columns 10-11 (--) should find nothing
1391 found = sq.findFeatures(10, 11);
1392 assertEquals(0, found.size());
1394 // columns 14-14 (I) should find variant feature
1395 found = sq.findFeatures(14, 14);
1396 assertEquals(1, found.size());
1397 assertTrue(found.contains(sfI));
1400 @Test(groups = { "Functional" })
1401 public void testFindIndex_withCursor()
1403 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1406 assertEquals(10, sq.findIndex(13, new SequenceCursor(sq, 8, 2, 0)));
1409 assertEquals(2, sq.findIndex(8, new SequenceCursor(sq, 13, 10, 0)));
1412 assertEquals(6, sq.findIndex(10, new SequenceCursor(sq, 10, 6, 0)));
1415 @Test(groups = { "Functional" })
1416 public void testFindPosition_withCursor()
1418 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1420 // find F pos given A - lastCol gets set in cursor
1421 assertEquals(13, sq.findPosition(10, new SequenceCursor(sq, 8, 2, 0)));
1422 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok0",
1423 PA.getValue(sq, "cursor").toString());
1425 // find A pos given F - first residue column is saved in cursor
1426 assertEquals(8, sq.findPosition(2, new SequenceCursor(sq, 13, 10, 0)));
1427 assertEquals("test:Pos8:Col2:startCol2:endCol10:tok0",
1428 PA.getValue(sq, "cursor").toString());
1430 // find C pos given C (neither startCol nor endCol is set)
1431 assertEquals(10, sq.findPosition(6, new SequenceCursor(sq, 10, 6, 0)));
1432 assertEquals("test:Pos10:Col6:startCol0:endCol0:tok0",
1433 PA.getValue(sq, "cursor").toString());
1435 // now the grey area - what residue position for a gapped column? JAL-2562
1437 // find 'residue' for column 3 given cursor for D (so working left)
1438 // returns B9; cursor is updated to [B 5]
1439 assertEquals(9, sq.findPosition(3, new SequenceCursor(sq, 11, 7, 0)));
1440 assertEquals("test:Pos9:Col5:startCol0:endCol0:tok0",
1441 PA.getValue(sq, "cursor").toString());
1443 // find 'residue' for column 8 given cursor for D (so working right)
1444 // returns E12; cursor is updated to [D 7]
1445 assertEquals(12, sq.findPosition(8, new SequenceCursor(sq, 11, 7, 0)));
1446 assertEquals("test:Pos11:Col7:startCol0:endCol0:tok0",
1447 PA.getValue(sq, "cursor").toString());
1449 // find 'residue' for column 12 given cursor for B
1450 // returns 1 more than last residue position; cursor is updated to [F 10]
1451 // lastCol position is saved in cursor
1452 assertEquals(14, sq.findPosition(12, new SequenceCursor(sq, 9, 5, 0)));
1453 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok0",
1454 PA.getValue(sq, "cursor").toString());
1457 * findPosition for column beyond length of sequence
1458 * returns 1 more than the last residue position
1459 * cursor is set to last real residue position [F 10]
1461 assertEquals(14, sq.findPosition(99, new SequenceCursor(sq, 8, 2, 0)));
1462 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok0",
1463 PA.getValue(sq, "cursor").toString());
1466 * and the case without a trailing gap
1468 sq = new Sequence("test/8-13", "-A--BCD-EF");
1469 // first find C from A
1470 assertEquals(10, sq.findPosition(6, new SequenceCursor(sq, 8, 2, 0)));
1471 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1472 assertEquals("test:Pos10:Col6:startCol0:endCol0:tok0",
1474 // now 'find' 99 from C
1475 // cursor is set to [F 10] and saved lastCol
1476 assertEquals(14, sq.findPosition(99, cursor));
1477 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok0",
1478 PA.getValue(sq, "cursor").toString());
1482 public void testIsValidCursor()
1484 Sequence sq = new Sequence("Seq", "ABC--DE-F", 8, 13);
1485 assertFalse(sq.isValidCursor(null));
1488 * cursor is valid if it has valid sequence ref and changeCount token
1489 * and positions within the range of the sequence
1491 int changeCount = (int) PA.getValue(sq, "changeCount");
1492 SequenceCursor cursor = new SequenceCursor(sq, 13, 1, changeCount);
1493 assertTrue(sq.isValidCursor(cursor));
1496 * column position outside [0 - length] is rejected
1498 cursor = new SequenceCursor(sq, 13, -1, changeCount);
1499 assertFalse(sq.isValidCursor(cursor));
1500 cursor = new SequenceCursor(sq, 13, 10, changeCount);
1501 assertFalse(sq.isValidCursor(cursor));
1502 cursor = new SequenceCursor(sq, 7, 8, changeCount);
1503 assertFalse(sq.isValidCursor(cursor));
1504 cursor = new SequenceCursor(sq, 14, 2, changeCount);
1505 assertFalse(sq.isValidCursor(cursor));
1508 * wrong sequence is rejected
1510 cursor = new SequenceCursor(null, 13, 1, changeCount);
1511 assertFalse(sq.isValidCursor(cursor));
1512 cursor = new SequenceCursor(new Sequence("Seq", "abc"), 13, 1,
1514 assertFalse(sq.isValidCursor(cursor));
1517 * wrong token value is rejected
1519 cursor = new SequenceCursor(sq, 13, 1, changeCount + 1);
1520 assertFalse(sq.isValidCursor(cursor));
1521 cursor = new SequenceCursor(sq, 13, 1, changeCount - 1);
1522 assertFalse(sq.isValidCursor(cursor));
1525 @Test(groups = { "Functional" })
1526 public void testFindPosition_withCursorAndEdits()
1528 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1530 // find F pos given A
1531 assertEquals(13, sq.findPosition(10, new SequenceCursor(sq, 8, 2, 0)));
1532 int token = (int) PA.getValue(sq, "changeCount"); // 0
1533 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1534 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1537 * setSequence should invalidate the cursor cached by the sequence
1539 sq.setSequence("-A-BCD-EF---"); // one gap removed
1540 assertEquals(8, sq.getStart()); // sanity check
1541 assertEquals(11, sq.findPosition(5)); // D11
1542 // cursor should now be at [D 6]
1543 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1544 assertEquals(new SequenceCursor(sq, 11, 6, ++token), cursor);
1547 * deleteChars should invalidate the cached cursor
1549 sq.deleteChars(2, 5); // delete -BC
1550 assertEquals("-AD-EF---", sq.getSequenceAsString());
1551 assertEquals(8, sq.getStart()); // sanity check
1552 assertEquals(10, sq.findPosition(4)); // E10
1553 // cursor should now be at [E 5]
1554 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1555 assertEquals(new SequenceCursor(sq, 10, 5, ++token), cursor);
1558 * Edit to insert gaps should invalidate the cached cursor
1559 * insert 2 gaps at column[3] to make -AD---EF---
1561 SequenceI[] seqs = new SequenceI[] { sq };
1562 AlignmentI al = new Alignment(seqs);
1563 new EditCommand().appendEdit(Action.INSERT_GAP, seqs, 3, 2, al, true);
1564 assertEquals("-AD---EF---", sq.getSequenceAsString());
1565 assertEquals(10, sq.findPosition(4)); // E10
1566 // cursor should now be at [D 3]
1567 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1568 assertEquals(new SequenceCursor(sq, 9, 3, ++token), cursor);
1571 * insertCharAt should invalidate the cached cursor
1572 * insert CC at column[4] to make -AD-CC--EF---
1574 sq.insertCharAt(4, 2, 'C');
1575 assertEquals("-AD-CC--EF---", sq.getSequenceAsString());
1576 assertEquals(13, sq.findPosition(9)); // F13
1577 // cursor should now be at [F 10]
1578 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1579 assertEquals(new SequenceCursor(sq, 13, 10, ++token), cursor);
1582 @Test(groups = { "Functional" })
1583 public void testGetSequence()
1585 String seqstring = "-A--BCD-EF--";
1586 Sequence sq = new Sequence("test/8-13", seqstring);
1587 sq.createDatasetSequence();
1588 assertTrue(Arrays.equals(sq.getSequence(), seqstring.toCharArray()));
1589 assertTrue(Arrays.equals(sq.getDatasetSequence().getSequence(),
1590 "ABCDEF".toCharArray()));
1592 // verify a copy of the sequence array is returned
1593 char[] theSeq = (char[]) PA.getValue(sq, "sequence");
1594 assertNotSame(theSeq, sq.getSequence());
1595 theSeq = (char[]) PA.getValue(sq.getDatasetSequence(), "sequence");
1596 assertNotSame(theSeq, sq.getDatasetSequence().getSequence());
1599 @Test(groups = { "Functional" })
1600 public void testReplace()
1602 String seqstring = "-A--BCD-EF--";
1603 SequenceI sq = new Sequence("test/8-13", seqstring);
1604 assertEquals(0, PA.getValue(sq, "changeCount"));
1606 assertEquals(0, sq.replace('A', 'A')); // same char
1607 assertEquals(seqstring, sq.getSequenceAsString());
1608 assertEquals(0, PA.getValue(sq, "changeCount"));
1610 assertEquals(0, sq.replace('X', 'Y')); // not there
1611 assertEquals(seqstring, sq.getSequenceAsString());
1612 assertEquals(0, PA.getValue(sq, "changeCount"));
1614 assertEquals(1, sq.replace('A', 'K'));
1615 assertEquals("-K--BCD-EF--", sq.getSequenceAsString());
1616 assertEquals(1, PA.getValue(sq, "changeCount"));
1618 assertEquals(6, sq.replace('-', '.'));
1619 assertEquals(".K..BCD.EF..", sq.getSequenceAsString());
1620 assertEquals(2, PA.getValue(sq, "changeCount"));
1623 @Test(groups = { "Functional" })
1624 public void testFindPositions()
1626 SequenceI sq = new Sequence("test/8-13", "-ABC---DE-F--");
1631 assertNull(sq.findPositions(6, 5));
1632 assertNull(sq.findPositions(0, 5));
1633 assertNull(sq.findPositions(-1, 5));
1638 assertNull(sq.findPositions(1, 1)); // 1-based columns
1639 assertNull(sq.findPositions(5, 5));
1640 assertNull(sq.findPositions(5, 6));
1641 assertNull(sq.findPositions(5, 7));
1644 * all ungapped ranges
1646 assertEquals(new Range(8, 8), sq.findPositions(2, 2)); // A
1647 assertEquals(new Range(8, 9), sq.findPositions(2, 3)); // AB
1648 assertEquals(new Range(8, 10), sq.findPositions(2, 4)); // ABC
1649 assertEquals(new Range(9, 10), sq.findPositions(3, 4)); // BC
1652 * gap to ungapped range
1654 assertEquals(new Range(8, 10), sq.findPositions(1, 4)); // ABC
1655 assertEquals(new Range(11, 12), sq.findPositions(6, 9)); // DE
1658 * ungapped to gapped range
1660 assertEquals(new Range(10, 10), sq.findPositions(4, 5)); // C
1661 assertEquals(new Range(9, 13), sq.findPositions(3, 11)); // BCDEF
1664 * ungapped to ungapped enclosing gaps
1666 assertEquals(new Range(10, 11), sq.findPositions(4, 8)); // CD
1667 assertEquals(new Range(8, 13), sq.findPositions(2, 11)); // ABCDEF
1670 * gapped to gapped enclosing ungapped
1672 assertEquals(new Range(8, 10), sq.findPositions(1, 5)); // ABC
1673 assertEquals(new Range(11, 12), sq.findPositions(5, 10)); // DE
1674 assertEquals(new Range(8, 13), sq.findPositions(1, 13)); // the lot
1675 assertEquals(new Range(8, 13), sq.findPositions(1, 99));
1678 @Test(groups = { "Functional" })
1679 public void testGapBitset()
1681 SequenceI sq = new Sequence("test/8-13", "-ABC---DE-F--");
1682 BitSet bs = sq.gapBitset();
1683 BitSet expected = new BitSet();
1687 expected.set(11, 13);
1689 assertTrue(bs.equals(expected));
1693 public void testFindFeatures_largeEndPos()
1696 * imitate a PDB sequence where end is larger than end position
1698 SequenceI sq = new Sequence("test", "-ABC--DEF--", 1, 20);
1699 sq.createDatasetSequence();
1701 assertTrue(sq.findFeatures(1, 9).isEmpty());
1702 // should be no array bounds exception - JAL-2772
1703 assertTrue(sq.findFeatures(1, 15).isEmpty());
1705 // add feature on BCD
1706 SequenceFeature sfBCD = new SequenceFeature("Cath", "desc", 2, 4, 2f,
1708 sq.addSequenceFeature(sfBCD);
1710 // no features in columns 1-2 (-A)
1711 List<SequenceFeature> found = sq.findFeatures(1, 2);
1712 assertTrue(found.isEmpty());
1714 // columns 1-6 (-ABC--) includes BCD
1715 found = sq.findFeatures(1, 6);
1716 assertEquals(1, found.size());
1717 assertTrue(found.contains(sfBCD));
1719 // columns 10-11 (--) should find nothing
1720 found = sq.findFeatures(10, 11);
1721 assertEquals(0, found.size());
1724 @Test(groups = { "Functional" })
1725 public void testSetName()
1727 SequenceI sq = new Sequence("test", "-ABC---DE-F--");
1728 assertEquals("test", sq.getName());
1729 assertEquals(1, sq.getStart());
1730 assertEquals(6, sq.getEnd());
1732 sq.setName("testing");
1733 assertEquals("testing", sq.getName());
1735 sq.setName("test/8-10");
1736 assertEquals("test", sq.getName());
1737 assertEquals(8, sq.getStart());
1738 assertEquals(13, sq.getEnd()); // note end is recomputed
1740 sq.setName("testing/7-99");
1741 assertEquals("testing", sq.getName());
1742 assertEquals(7, sq.getStart());
1743 assertEquals(99, sq.getEnd()); // end may be beyond physical end
1746 assertEquals("", sq.getName());
1747 assertEquals(2, sq.getStart());
1748 assertEquals(7, sq.getEnd());
1750 sq.setName("test/"); // invalid
1751 assertEquals("test/", sq.getName());
1752 assertEquals(2, sq.getStart());
1753 assertEquals(7, sq.getEnd());
1755 sq.setName("test/6-13/7-99");
1756 assertEquals("test/6-13", sq.getName());
1757 assertEquals(7, sq.getStart());
1758 assertEquals(99, sq.getEnd());
1760 sq.setName("test/0-5"); // 0 is invalid - ignored
1761 assertEquals("test/0-5", sq.getName());
1762 assertEquals(7, sq.getStart());
1763 assertEquals(99, sq.getEnd());
1765 sq.setName("test/a-5"); // a is invalid - ignored
1766 assertEquals("test/a-5", sq.getName());
1767 assertEquals(7, sq.getStart());
1768 assertEquals(99, sq.getEnd());
1770 sq.setName("test/6-5"); // start > end is invalid - ignored
1771 assertEquals("test/6-5", sq.getName());
1772 assertEquals(7, sq.getStart());
1773 assertEquals(99, sq.getEnd());
1775 sq.setName("test/5"); // invalid - ignored
1776 assertEquals("test/5", sq.getName());
1777 assertEquals(7, sq.getStart());
1778 assertEquals(99, sq.getEnd());
1780 sq.setName("test/-5"); // invalid - ignored
1781 assertEquals("test/-5", sq.getName());
1782 assertEquals(7, sq.getStart());
1783 assertEquals(99, sq.getEnd());
1785 sq.setName("test/5-"); // invalid - ignored
1786 assertEquals("test/5-", sq.getName());
1787 assertEquals(7, sq.getStart());
1788 assertEquals(99, sq.getEnd());
1790 sq.setName("test/5-6-7"); // invalid - ignored
1791 assertEquals("test/5-6-7", sq.getName());
1792 assertEquals(7, sq.getStart());
1793 assertEquals(99, sq.getEnd());
1795 sq.setName(null); // invalid, gets converted to space
1796 assertEquals("", sq.getName());
1797 assertEquals(7, sq.getStart());
1798 assertEquals(99, sq.getEnd());
1801 @Test(groups = { "Functional" })
1802 public void testCheckValidRange()
1804 Sequence sq = new Sequence("test/7-12", "-ABC---DE-F--");
1805 assertEquals(7, sq.getStart());
1806 assertEquals(12, sq.getEnd());
1809 * checkValidRange ensures end is at least the last residue position
1811 PA.setValue(sq, "end", 2);
1812 sq.checkValidRange();
1813 assertEquals(12, sq.getEnd());
1816 * end may be beyond the last residue position
1818 PA.setValue(sq, "end", 22);
1819 sq.checkValidRange();
1820 assertEquals(22, sq.getEnd());
1823 @Test(groups = { "Functional" })
1824 public void testDeleteChars_withGaps()
1829 SequenceI sq = new Sequence("test/8-10", "A-B-C");
1830 sq.createDatasetSequence();
1831 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
1832 sq.deleteChars(1, 2); // delete first gap
1833 assertEquals("AB-C", sq.getSequenceAsString());
1834 assertEquals(8, sq.getStart());
1835 assertEquals(10, sq.getEnd());
1836 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
1839 * delete gaps and residues at start (no new dataset sequence)
1841 sq = new Sequence("test/8-10", "A-B-C");
1842 sq.createDatasetSequence();
1843 sq.deleteChars(0, 3); // delete A-B
1844 assertEquals("-C", sq.getSequenceAsString());
1845 assertEquals(10, sq.getStart());
1846 assertEquals(10, sq.getEnd());
1847 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
1850 * delete gaps and residues at end (no new dataset sequence)
1852 sq = new Sequence("test/8-10", "A-B-C");
1853 sq.createDatasetSequence();
1854 sq.deleteChars(2, 5); // delete B-C
1855 assertEquals("A-", sq.getSequenceAsString());
1856 assertEquals(8, sq.getStart());
1857 assertEquals(8, sq.getEnd());
1858 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
1861 * delete gaps and residues internally (new dataset sequence)
1862 * first delete from gap to residue
1864 sq = new Sequence("test/8-10", "A-B-C");
1865 sq.createDatasetSequence();
1866 sq.deleteChars(1, 3); // delete -B
1867 assertEquals("A-C", sq.getSequenceAsString());
1868 assertEquals(8, sq.getStart());
1869 assertEquals(9, sq.getEnd());
1870 assertEquals("AC", sq.getDatasetSequence().getSequenceAsString());
1871 assertEquals(8, sq.getDatasetSequence().getStart());
1872 assertEquals(9, sq.getDatasetSequence().getEnd());
1875 * internal delete from gap to gap
1877 sq = new Sequence("test/8-10", "A-B-C");
1878 sq.createDatasetSequence();
1879 sq.deleteChars(1, 4); // delete -B-
1880 assertEquals("AC", sq.getSequenceAsString());
1881 assertEquals(8, sq.getStart());
1882 assertEquals(9, sq.getEnd());
1883 assertEquals("AC", sq.getDatasetSequence().getSequenceAsString());
1884 assertEquals(8, sq.getDatasetSequence().getStart());
1885 assertEquals(9, sq.getDatasetSequence().getEnd());
1888 * internal delete from residue to residue
1890 sq = new Sequence("test/8-10", "A-B-C");
1891 sq.createDatasetSequence();
1892 sq.deleteChars(2, 3); // delete B
1893 assertEquals("A--C", sq.getSequenceAsString());
1894 assertEquals(8, sq.getStart());
1895 assertEquals(9, sq.getEnd());
1896 assertEquals("AC", sq.getDatasetSequence().getSequenceAsString());
1897 assertEquals(8, sq.getDatasetSequence().getStart());
1898 assertEquals(9, sq.getDatasetSequence().getEnd());
1902 * Test the code used to locate the reference sequence ruler origin
1904 @Test(groups = { "Functional" })
1905 public void testLocateVisibleStartofSequence()
1907 // create random alignment
1908 AlignmentGenerator gen = new AlignmentGenerator(false);
1909 AlignmentI al = gen.generate(50, 20, 123, 5, 5);
1911 HiddenColumns cs = al.getHiddenColumns();
1912 ColumnSelection colsel = new ColumnSelection();
1914 SequenceI seq = new Sequence("RefSeq", "-A-SD-ASD--E---");
1915 assertEquals(2, seq.findIndex(seq.getStart()));
1917 // no hidden columns
1918 assertEquals(seq.findIndex(seq.getStart()) - 1,
1919 seq.firstResidueOutsideIterator(cs.iterator()));
1921 // hidden column on gap after end of sequence - should not affect bounds
1922 colsel.hideSelectedColumns(13, al.getHiddenColumns());
1923 assertEquals(seq.findIndex(seq.getStart()) - 1,
1924 seq.firstResidueOutsideIterator(cs.iterator()));
1926 cs.revealAllHiddenColumns(colsel);
1927 // hidden column on gap before beginning of sequence - should vis bounds by
1929 colsel.hideSelectedColumns(0, al.getHiddenColumns());
1930 assertEquals(seq.findIndex(seq.getStart()) - 2,
1931 cs.absoluteToVisibleColumn(
1932 seq.firstResidueOutsideIterator(cs.iterator())));
1934 cs.revealAllHiddenColumns(colsel);
1935 // hide columns around most of sequence - leave one residue remaining
1936 cs.hideColumns(1, 3);
1937 cs.hideColumns(6, 11);
1939 Iterator<int[]> it = cs.getVisContigsIterator(0, 6, false);
1941 assertEquals("-D", seq.getSequenceStringFromIterator(it));
1942 // cs.getVisibleSequenceStrings(0, 5, new SequenceI[]
1945 assertEquals(4, seq.firstResidueOutsideIterator(cs.iterator()));
1946 cs.revealAllHiddenColumns(colsel);
1948 // hide whole sequence - should just get location of hidden region
1949 // containing sequence
1950 cs.hideColumns(1, 11);
1951 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
1953 cs.revealAllHiddenColumns(colsel);
1954 cs.hideColumns(0, 15);
1955 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
1957 SequenceI seq2 = new Sequence("RefSeq2", "-------A-SD-ASD--E---");
1959 cs.revealAllHiddenColumns(colsel);
1960 cs.hideColumns(7, 17);
1961 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
1963 cs.revealAllHiddenColumns(colsel);
1964 cs.hideColumns(3, 17);
1965 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
1967 cs.revealAllHiddenColumns(colsel);
1968 cs.hideColumns(3, 19);
1969 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
1971 cs.revealAllHiddenColumns(colsel);
1972 cs.hideColumns(0, 0);
1973 assertEquals(1, seq.firstResidueOutsideIterator(cs.iterator()));
1975 cs.revealAllHiddenColumns(colsel);
1976 cs.hideColumns(0, 1);
1977 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
1979 cs.revealAllHiddenColumns(colsel);
1980 cs.hideColumns(0, 2);
1981 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
1983 cs.revealAllHiddenColumns(colsel);
1984 cs.hideColumns(1, 1);
1985 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
1987 cs.revealAllHiddenColumns(colsel);
1988 cs.hideColumns(1, 2);
1989 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
1991 cs.revealAllHiddenColumns(colsel);
1992 cs.hideColumns(1, 3);
1993 assertEquals(4, seq.firstResidueOutsideIterator(cs.iterator()));
1995 cs.revealAllHiddenColumns(colsel);
1996 cs.hideColumns(0, 2);
1997 cs.hideColumns(5, 6);
1998 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2000 cs.revealAllHiddenColumns(colsel);
2001 cs.hideColumns(0, 2);
2002 cs.hideColumns(5, 6);
2003 cs.hideColumns(9, 10);
2004 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2006 cs.revealAllHiddenColumns(colsel);
2007 cs.hideColumns(0, 2);
2008 cs.hideColumns(7, 11);
2009 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2011 cs.revealAllHiddenColumns(colsel);
2012 cs.hideColumns(2, 4);
2013 cs.hideColumns(7, 11);
2014 assertEquals(1, seq.firstResidueOutsideIterator(cs.iterator()));
2016 cs.revealAllHiddenColumns(colsel);
2017 cs.hideColumns(2, 4);
2018 cs.hideColumns(7, 12);
2019 assertEquals(1, seq.firstResidueOutsideIterator(cs.iterator()));
2021 cs.revealAllHiddenColumns(colsel);
2022 cs.hideColumns(1, 11);
2023 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2025 cs.revealAllHiddenColumns(colsel);
2026 cs.hideColumns(0, 12);
2027 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2029 cs.revealAllHiddenColumns(colsel);
2030 cs.hideColumns(0, 4);
2031 cs.hideColumns(6, 12);
2032 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2034 cs.revealAllHiddenColumns(colsel);
2035 cs.hideColumns(0, 1);
2036 cs.hideColumns(3, 12);
2037 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2039 cs.revealAllHiddenColumns(colsel);
2040 cs.hideColumns(3, 14);
2041 cs.hideColumns(17, 19);
2042 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2044 cs.revealAllHiddenColumns(colsel);
2045 cs.hideColumns(3, 7);
2046 cs.hideColumns(9, 14);
2047 cs.hideColumns(17, 19);
2048 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2050 cs.revealAllHiddenColumns(colsel);
2051 cs.hideColumns(0, 1);
2052 cs.hideColumns(3, 4);
2053 cs.hideColumns(6, 8);
2054 cs.hideColumns(10, 12);
2055 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));