[ADAM-1702] Validate read numbers in InterleavedFASTQInFormatter.

Resolves bigdatagenomics#1702.
fnothaft · Aug 30, 2017 · bac6c1d · bac6c1d
1 parent fcaca38
commit bac6c1d
Showing 1 changed file with 14 additions and 2 deletions.
diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/fragment/InterleavedFASTQInFormatter.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/fragment/InterleavedFASTQInFormatter.scala
@@ -81,8 +81,20 @@ class InterleavedFASTQInFormatter private (
         outputOriginalBaseQualities = writeOriginalQualities) + "\n"
 
       // write both to the output stream
-      os.write(fastq1.getBytes)
-      os.write(fastq2.getBytes)
+      // ensure that reads are ordered properly if ordering is known (see #1702)
+      if (read1.getReadInFragment == 0 &&
+        read2.getReadInFragment == 1) {
+        os.write(fastq1.getBytes)
+        os.write(fastq2.getBytes)
+      } else if (read1.getReadInFragment == 1 &&
+        read2.getReadInFragment == 0) {
+        os.write(fastq2.getBytes)
+        os.write(fastq1.getBytes)
+      } else {
+        if (enableLogging) {
+          log.warn("Improper pair of reads in fragment %s. Dropping...".format(p))
+        }
+      }
     })
   }
 }