Per PR comments, change to returning a header line with length set to…

… SAMSequenceRecord.UNKNOWN_SEQUENCE_LENGTH
samtools · Oct 1, 2019 · 59679d8 · 59679d8
1 parent 16f6355
commit 59679d8
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 3 deletions.
diff --git a/src/main/java/htsjdk/variant/vcf/VCFContigHeaderLine.java b/src/main/java/htsjdk/variant/vcf/VCFContigHeaderLine.java
@@ -78,13 +78,21 @@ public Integer getContigIndex() {
 
     /**
      * Get the SAMSequenceRecord that corresponds to this VCF header line.
+     * If the VCF header line does not have a length tag, the SAMSequenceRecord returned will be set to have a length of
+     * SAMSequenceRecord.UNKNOWN_SEQUENCE_LENGTH. Records with unknown length will match any record with the same name
+     * when evaluated by SAMSequenceRecord.isSameSequence.
      * @return The SAMSequenceRecord containing the ID, length, assembly, and index of this contig. Returns null if the
      * contig header line does not have a length.
      */
 	public SAMSequenceRecord getSAMSequenceRecord() {
 		final String lengthString = this.getGenericFieldValue("length");
-		if (lengthString == null) return null;
-		final SAMSequenceRecord record = new SAMSequenceRecord(this.getID(), Integer.parseInt(lengthString));
+		final int length;
+		if (lengthString == null) {
+		    length = SAMSequenceRecord.UNKNOWN_SEQUENCE_LENGTH;
+        } else {
+		    length = Integer.parseInt(lengthString);
+        }
+		final SAMSequenceRecord record = new SAMSequenceRecord(this.getID(), length);
         record.setAssembly(this.getGenericFieldValue("assembly"));
 		record.setSequenceIndex(this.contigIndex);
 		return record;

diff --git a/src/test/java/htsjdk/variant/vcf/VCFHeaderUnitTest.java b/src/test/java/htsjdk/variant/vcf/VCFHeaderUnitTest.java
@@ -25,6 +25,8 @@
 
 package htsjdk.variant.vcf;
 
+import htsjdk.samtools.SAMSequenceDictionary;
+import htsjdk.samtools.SAMSequenceRecord;
 import htsjdk.samtools.util.CloseableIterator;
 import htsjdk.samtools.util.FileExtensions;
 import htsjdk.samtools.util.IOUtil;
@@ -247,7 +249,10 @@ public void testVCFHeaderContigLineMissingLength() {
         Assert.assertTrue(header.getContigLines().contains(contigLine), "Test contig line not found in contig header lines");
         Assert.assertTrue(header.getMetaDataInInputOrder().contains(contigLine), "Test contig line not found in set of all header lines");
 
-        Assert.assertNull(header.getSequenceDictionary());
+        final SAMSequenceDictionary sequenceDictionary = header.getSequenceDictionary();
+        Assert.assertNotNull(sequenceDictionary);
+        Assert.assertEquals(sequenceDictionary.getSequence("chr1").getSequenceLength(), SAMSequenceRecord.UNKNOWN_SEQUENCE_LENGTH);
+
     }
 
         @Test