+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.io;
import static org.testng.Assert.assertEquals;
import static org.testng.Assert.assertTrue;
import static org.testng.AssertJUnit.assertNotNull;
+import static org.testng.AssertJUnit.assertNull;
import static org.testng.AssertJUnit.assertSame;
import static org.testng.AssertJUnit.fail;
-import static org.testng.AssertJUnit.assertNull;
import java.io.File;
import java.io.IOException;
import java.util.List;
import java.util.Set;
+import org.testng.annotations.BeforeClass;
import org.testng.annotations.Test;
+import jalview.bin.Console;
import jalview.datamodel.DBRefEntry;
import jalview.datamodel.Mapping;
import jalview.datamodel.Sequence.DBModList;
public class EmblFlatFileTest
{
+ @BeforeClass(alwaysRun = true)
+ public void setUp()
+ {
+ Console.initLogger();
+ }
+
/**
* A fairly tough test, using J03321 (circular DNA), which has 8 CDS features,
* one of them reverse strand
File dataFile = new File("test/jalview/io/J03321.embl.txt");
FileParse fp = new FileParse(dataFile, DataSourceType.FILE);
EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
- parser.parse();
List<SequenceI> seqs = parser.getSeqs();
assertEquals(seqs.size(), 1);
{
assertEquals((ranges = map.getFromRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1579);
- assertEquals(ranges.get(0)[1], 2934);
+ assertEquals(ranges.get(0)[1], 2931); // excludes stop 2934
assertEquals((ranges = map.getToRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1);
assertEquals(ranges.get(0)[1], 451);
{
assertEquals((ranges = map.getFromRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 2928);
- assertEquals(ranges.get(0)[1], 3992);
+ assertEquals(ranges.get(0)[1], 3989); // excludes stop 3992
assertEquals((ranges = map.getToRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1);
assertEquals(ranges.get(0)[1], 354);
{
assertEquals((ranges = map.getFromRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 4054);
- assertEquals(ranges.get(0)[1], 4848);
+ assertEquals(ranges.get(0)[1], 4845); // excludes stop 4848
assertEquals((ranges = map.getToRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1);
assertEquals(ranges.get(0)[1], 264);
assertEquals(ranges.get(0)[0], 7022);
assertEquals(ranges.get(0)[1], 7502);
assertEquals(ranges.get(1)[0], 1);
- assertEquals(ranges.get(1)[1], 437);
+ assertEquals(ranges.get(1)[1], 434); // excludes stop at 437
assertEquals((ranges = map.getToRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1);
assertEquals(ranges.get(0)[1], 305);
// complement(488..1480)
assertEquals((ranges = map.getFromRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1480);
- assertEquals(ranges.get(0)[1], 488);
+ assertEquals(ranges.get(0)[1], 491); // // excludes stop at 488
assertEquals((ranges = map.getToRanges()).size(), 1);
assertEquals(ranges.get(0)[0], 1);
assertEquals(ranges.get(0)[1], 330);
assertEquals(uniprotCount, 8);
}
+ /**
+ * A fairly tough test, using J03321 (circular DNA), which has 8 CDS features,
+ * one of them reverse strand
+ *
+ * @throws MalformedURLException
+ * @throws IOException
+ */
+ @Test(groups = "Functional")
+ public void testParseToRNA() throws MalformedURLException, IOException
+ {
+ File dataFile = new File("test/jalview/io/J03321_rna.embl.txt");
+ FileParse fp = new FileParse(dataFile, DataSourceType.FILE);
+ EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
+ List<SequenceI> seqs = parser.getSeqs();
+ assertTrue(seqs.get(0).getSequenceAsString().indexOf("u") > -1);
+ }
+
@Test(groups = "Functional")
public void testParse_codonStartNot1()
{
public void testParse_noUniprotXref() throws IOException
{
// MN908947 cut down to 40BP, one CDS, length 5 peptide for test purposes
+ // plus an additional (invented) test case:
+ // - multi-line /product qualifier including escaped quotes
String data = "ID MN908947; SV 3; linear; genomic RNA; STD; VRL; 20 BP.\n"
+ "DE Severe acute respiratory syndrome coronavirus 2 isolate Wuhan-Hu-1,\n"
+ "FT CDS 3..17\n"
+ "FT /protein_id=\"QHD43415.1\"\n"
- + "FT /product=\"orf1ab polyprotein\"\n"
+ + "FT /product=\"orf1ab polyprotein\n"
+ + "FT \"\"foobar\"\" \"\n"
+ "FT /translation=\"MRKLD\n"
+ "SQ Sequence 7496 BP; 2450 A; 1290 C; 1434 G; 2322 T; 0 other;\n"
+ " ggatGcgtaa gttagacgaa attttgtctt tgcgcacaga 40\n";
FileParse fp = new FileParse(data, DataSourceType.PASTE);
EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
- parser.parse();
List<SequenceI> seqs = parser.getSeqs();
assertEquals(seqs.size(), 1);
SequenceI seq = seqs.get(0);
* dna should have dbref to itself, and to inferred EMBLCDSPROTEIN:QHD43415.1
*/
assertEquals(dbrefs.size(), 2);
-
+
// dbref to self
DBRefEntry dbref = dbrefs.get(0);
assertEquals(dbref.getSource(), "EMBLTEST");
assertEquals(map.getToHighest(), 40);
assertEquals(map.getFromRatio(), 1);
assertEquals(map.getToRatio(), 1);
-
+
// dbref to inferred EMBLCDSPROTEIN:
dbref = dbrefs.get(1);
assertEquals(dbref.getSource(), "EMBLCDSPROTEIN");
mapping = dbref.getMap();
SequenceI mapTo = mapping.getTo();
assertEquals(mapTo.getName(), "QHD43415.1");
- assertEquals(mapTo.getDescription(), "orf1ab polyprotein");
+ // the /product qualifier transfers to protein product description
+ assertEquals(mapTo.getDescription(), "orf1ab polyprotein \"foobar\"");
assertEquals(mapTo.getSequenceAsString(), "MRKLD");
map = mapping.getMap();
assertEquals(map.getFromLowest(), 3);
// exact length match:
assertSame(exons, EmblFlatFile.adjustForProteinLength(6, exons));
+ // patch from JAL-3725 in EmblXmlSource propagated to Flatfile
// match if we assume exons include stop codon not in protein:
- assertSame(exons, EmblFlatFile.adjustForProteinLength(5, exons));
+ int[] truncated = EmblFlatFile.adjustForProteinLength(5, exons);
+ assertEquals(Arrays.toString(truncated), "[11, 15, 21, 25, 31, 35]");
// truncate last exon by 6bp
- int[] truncated = EmblFlatFile.adjustForProteinLength(4, exons);
- assertEquals("[11, 15, 21, 25, 31, 32]", Arrays.toString(truncated));
+ truncated = EmblFlatFile.adjustForProteinLength(4, exons);
+ assertEquals(Arrays.toString(truncated), "[11, 15, 21, 25, 31, 32]");
// remove last exon and truncate preceding by 1bp (so 3bp in total)
truncated = EmblFlatFile.adjustForProteinLength(3, exons);
- assertEquals("[11, 15, 21, 24]", Arrays.toString(truncated));
+ assertEquals(Arrays.toString(truncated), "[11, 15, 21, 24]");
// exact removal of exon case:
exons = new int[] { 11, 15, 21, 27, 33, 38 }; // 18 bp
truncated = EmblFlatFile.adjustForProteinLength(4, exons);
- assertEquals("[11, 15, 21, 27]", Arrays.toString(truncated));
+ assertEquals(Arrays.toString(truncated), "[11, 15, 21, 27]");
// what if exons are too short for protein?
truncated = EmblFlatFile.adjustForProteinLength(7, exons);
assertSame(exons, truncated);
}
+
+ @Test(groups = "Functional")
+ public void testRemoveQuotes()
+ {
+ assertNull(EmblFlatFile.removeQuotes(null));
+ assertEquals(EmblFlatFile.removeQuotes("No quotes here"),
+ "No quotes here");
+ assertEquals(EmblFlatFile.removeQuotes("\"Enclosing quotes\""),
+ "Enclosing quotes");
+ assertEquals(
+ EmblFlatFile.removeQuotes("\"Escaped \"\"quotes\"\" example\""),
+ "Escaped \"quotes\" example");
+ }
}