Performance improvements to SAM reading and processing (#2280)

* Performance fixes to sam reading and processing * Correct implementation of toString in SequenceDictionary Co-authored-by: Rahamim, Ben <brahamim@paypal.com>
bigdatagenomics · Nov 5, 2020 · 61c4809 · 61c4809
1 parent 2d9f1c8
commit 61c4809
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 7 deletions.
diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/models/Attribute.scala b/adam-core/src/main/scala/org/bdgenomics/adam/models/Attribute.scala
@@ -36,16 +36,20 @@ case class Attribute(tag: String, tagType: TagType.Value, value: Any) {
     val byteSequenceTypes = Array(TagType.NumericByteSequence, TagType.NumericUnsignedByteSequence)
     val intSequenceTypes = Array(TagType.NumericIntSequence, TagType.NumericUnsignedIntSequence)
     val shortSequenceTypes = Array(TagType.NumericShortSequence, TagType.NumericUnsignedShortSequence)
+    val sb = new StringBuilder
+    sb.append(tag)
+    sb.append(":")
+    sb.append(tagType)
     if (byteSequenceTypes contains tagType) {
-      "%s:%s,%s".format(tag, tagType, value.asInstanceOf[Array[Byte]].mkString(","))
+      sb.append(",").append(value.asInstanceOf[Array[Byte]].mkString(",")).toString()
     } else if (shortSequenceTypes contains tagType) {
-      "%s:%s,%s".format(tag, tagType, value.asInstanceOf[Array[Short]].mkString(","))
+      sb.append(",").append(value.asInstanceOf[Array[Short]].mkString(",")).toString()
     } else if (intSequenceTypes contains tagType) {
-      "%s:%s,%s".format(tag, tagType, value.asInstanceOf[Array[Int]].mkString(","))
+      sb.append(",").append(value.asInstanceOf[Array[Int]].mkString(",")).toString()
     } else if (tagType == TagType.NumericFloatSequence) {
-      "%s:%s,%s".format(tag, tagType, value.asInstanceOf[Array[Float]].mkString(","))
+      sb.append(",").append(value.asInstanceOf[Array[Float]].mkString(",")).toString()
     } else {
-      "%s:%s:%s".format(tag, tagType, value.toString)
+      sb.append(":").append(value).toString()
     }
   }
 }

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/models/SequenceDictionary.scala b/adam-core/src/main/scala/org/bdgenomics/adam/models/SequenceDictionary.scala
@@ -184,7 +184,7 @@ class SequenceDictionary(val records: Vector[SequenceRecord]) extends Serializab
    * @return Returns a SAM formatted sequence dictionary.
    */
   def toSAMSequenceDictionary: SAMSequenceDictionary = {
-    new SAMSequenceDictionary(records.iterator.map(_.toSAMSequenceRecord).toList)
+    new SAMSequenceDictionary(records.map(_.toSAMSequenceRecord).asJava)
   }
 
   /**
@@ -259,7 +259,7 @@ class SequenceDictionary(val records: Vector[SequenceRecord]) extends Serializab
   }
 
   override def toString: String = {
-    records.map(_.toString).fold("SequenceDictionary{")(_ + "\n" + _) + "}"
+    records.map(_.toString).mkString("SequenceDictionary{", "\n", "}")
   }
 
   private[adam] def toAvro: Seq[Reference] = {