Squashed #907 and ran format-sources

adam-apis/src/main/scala/org/bdgenomics/adam/apis/java/JavaAlignmentRecordRDD.scala

@@ -33,11 +33,12 @@ class JavaAlignmentRecordRDD(val jrdd: JavaRDD[AlignmentRecord]) extends Seriali
    * @param compressCodec Name of the compression codec to use.
    * @param disableDictionaryEncoding Whether or not to disable bit-packing.
    */
-  def adamSave(filePath: java.lang.String,
-               blockSize: java.lang.Integer,
-               pageSize: java.lang.Integer,
-               compressCodec: CompressionCodecName,
-               disableDictionaryEncoding: java.lang.Boolean) {
+  def adamSave(
+    filePath: java.lang.String,
+    blockSize: java.lang.Integer,
+    pageSize: java.lang.Integer,
+    compressCodec: CompressionCodecName,
+    disableDictionaryEncoding: java.lang.Boolean) {
     jrdd.rdd.adamParquetSave(
       filePath,
       blockSize,
@@ -62,8 +63,9 @@ class JavaAlignmentRecordRDD(val jrdd: JavaRDD[AlignmentRecord]) extends Seriali
    * @param filePath Path to save the file at.
    * @param asSam If true, saves as SAM. If false, saves as BAM.
    */
-  def adamSAMSave(filePath: java.lang.String,
-                  asSam: java.lang.Boolean) {
+  def adamSAMSave(
+    filePath: java.lang.String,
+    asSam: java.lang.Boolean) {
     jrdd.rdd.adamSAMSave(filePath, asSam)
   }
 

adam-cli/src/main/scala/org/bdgenomics/adam/cli/AlleleCount.scala

@@ -53,12 +53,14 @@ object AlleleCountHelper extends Serializable {
     }
 
   def countAlleles(adamVariants: RDD[Genotype], args: AlleleCountArgs) {
-    val usefulData = adamVariants.map(p => (p.getVariant.getContig.getContigName,
+    val usefulData = adamVariants.map(p => (
+      p.getVariant.getContig.getContigName,
       p.getVariant.getStart,
       p.getVariant.getReferenceAllele,
       p.getVariant.getAlternateAllele,
       p.getAlleles.get(0),
-      p.getAlleles.get(1)))
+      p.getAlleles.get(1)
+    ))
     val reduced_Variants = usefulData.flatMap(p => Seq((p._1, p._2, p._3, p._4, p._5), (p._1, p._2, p._3, p._4, p._6)))
     val alleles = reduced_Variants.flatMap(chooseAllele)
     alleles.groupBy(identity).map { case (a, b) => "%s\t%s\t%s\t%d".format(a._1, a._2, a._3, b.size) }

adam-cli/src/main/scala/org/bdgenomics/adam/cli/CalculateDepth.scala

@@ -108,7 +108,8 @@ class CalculateDepth(protected val args: CalculateDepthArgs) extends BDGSparkCom
         println("%20s\t%15s\t% 5d".format(
           "%s:%d".format(region.referenceName, region.start),
           variantNames(region),
-          count))
+          count
+        ))
     }
   }
 

adam-cli/src/main/scala/org/bdgenomics/adam/cli/CountReadKmers.scala

@@ -61,7 +61,8 @@ class CountReadKmers(protected val args: CountReadKmersArgs) extends BDGSparkCom
     // read from disk
     var adamRecords: RDD[AlignmentRecord] = sc.loadAlignments(
       args.inputPath,
-      projection = Some(Projection(AlignmentRecordField.sequence)))
+      projection = Some(Projection(AlignmentRecordField.sequence))
+    )
 
     if (args.repartition != -1) {
       log.info("Repartitioning reads to '%d' partitions".format(args.repartition))

adam-cli/src/main/scala/org/bdgenomics/adam/cli/FlagStat.scala

@@ -62,7 +62,8 @@ class FlagStat(protected val args: FlagStatArgs) extends BDGSparkCommand[FlagSta
       AlignmentRecordField.secondOfPair,
       AlignmentRecordField.properPair,
       AlignmentRecordField.mapq,
-      AlignmentRecordField.failedVendorQualityChecks)
+      AlignmentRecordField.failedVendorQualityChecks
+    )
 
     val adamFile: RDD[AlignmentRecord] = sc.loadAlignments(args.inputPath, projection = Some(projection))
 
@@ -113,7 +114,8 @@ class FlagStat(protected val args: FlagStatArgs) extends BDGSparkCommand[FlagSta
       percent(passedVendorQuality.singleton, passedVendorQuality.total),
       percent(failedVendorQuality.singleton, failedVendorQuality.total),
       passedVendorQuality.withMateMappedToDiffChromosome, failedVendorQuality.withMateMappedToDiffChromosome,
-      passedVendorQuality.withMateMappedToDiffChromosomeMapQ5, failedVendorQuality.withMateMappedToDiffChromosomeMapQ5)
+      passedVendorQuality.withMateMappedToDiffChromosomeMapQ5, failedVendorQuality.withMateMappedToDiffChromosomeMapQ5
+    )
 
     Option(args.outputPath) match {
       case Some(outputPath) =>

adam-cli/src/main/scala/org/bdgenomics/adam/cli/Flatten.scala

@@ -75,6 +75,7 @@ class Flatten(val args: FlattenArgs) extends BDGSparkCommand[FlattenArgs] with L
         args.pageSize,
         args.compressionCodec,
         args.disableDictionaryEncoding,
-        Some(flatSchema))
+        Some(flatSchema)
+      )
   }
 }

adam-cli/src/main/scala/org/bdgenomics/adam/cli/PrintGenes.scala

@@ -64,6 +64,7 @@ class PrintGenes(protected val args: PrintGenesArgs)
       transcript.region.referenceName,
       transcript.region.start, transcript.region.end,
       if (transcript.strand) "+" else "-",
-      transcript.exons.size)
+      transcript.exons.size
+    )
   }
 }

adam-cli/src/main/scala/org/bdgenomics/adam/cli/Transform.scala

@@ -145,7 +145,8 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
       log.info("Locally realigning indels.")
       val consensusGenerator = Option(args.knownIndelsFile)
         .fold(new ConsensusGeneratorFromReads().asInstanceOf[ConsensusGenerator])(
-          new ConsensusGeneratorFromKnowns(_, sc).asInstanceOf[ConsensusGenerator])
+          new ConsensusGeneratorFromKnowns(_, sc).asInstanceOf[ConsensusGenerator]
+        )
 
       adamRecords = oldRdd.adamRealignIndels(
         consensusGenerator,
@@ -227,7 +228,8 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
     if ((args.useAlignedReadPredicate || args.limitProjection) &&
       (args.forceLoadBam || args.forceLoadFastq || args.forceLoadIFastq)) {
       throw new IllegalArgumentException(
-        "-aligned_read_predicate and -limit_projection only apply to Parquet files, but a non-Parquet force load flag was passed.")
+        "-aligned_read_predicate and -limit_projection only apply to Parquet files, but a non-Parquet force load flag was passed."
+      )
     }
 
     val rdd =
@@ -246,7 +248,8 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
           None
         }
         val proj = if (args.limitProjection) {
-          Some(Projection(AlignmentRecordField.contig,
+          Some(Projection(
+            AlignmentRecordField.contig,
             AlignmentRecordField.start,
             AlignmentRecordField.end,
             AlignmentRecordField.mapq,
@@ -265,13 +268,16 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
             AlignmentRecordField.duplicateRead,
             AlignmentRecordField.mismatchingPositions,
             AlignmentRecordField.secondaryAlignment,
-            AlignmentRecordField.supplementaryAlignment))
+            AlignmentRecordField.supplementaryAlignment
+          ))
         } else {
           None
         }
-        sc.loadParquetAlignments(args.inputPath,
+        sc.loadParquetAlignments(
+          args.inputPath,
           predicate = pred,
-          projection = proj)
+          projection = proj
+        )
       } else {
         sc.loadAlignments(
           args.inputPath,
@@ -297,8 +303,7 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
             concatFilename,
             recordGroupOpt = Option(args.fastqRecordGroup)
           )
-        }
-      )
+        })
 
     this.apply(concatRddOpt match {
       case Some(concatRdd) => rdd ++ concatRdd

adam-cli/src/main/scala/org/bdgenomics/adam/cli/View.scala

@@ -36,41 +36,47 @@ class ViewArgs extends Args4jBase with ParquetArgs with ADAMSaveAnyArgs {
     required = false,
     name = "-f",
     metaVar = "N",
-    usage = "Restrict to reads that match all of the bits in <N>")
+    usage = "Restrict to reads that match all of the bits in <N>"
+  )
   var matchAllBits: Int = 0
 
   @Args4jOption(
     required = false,
     name = "-F",
     metaVar = "N",
-    usage = "Restrict to reads that match none of the bits in <N>")
+    usage = "Restrict to reads that match none of the bits in <N>"
+  )
   var mismatchAllBits: Int = 0
 
   @Args4jOption(
     required = false,
     name = "-g",
     metaVar = "N",
-    usage = "Restrict to reads that match any of the bits in <N>")
+    usage = "Restrict to reads that match any of the bits in <N>"
+  )
   var matchSomeBits: Int = 0
 
   @Args4jOption(
     required = false,
     name = "-G",
     metaVar = "N",
-    usage = "Restrict to reads that mismatch at least one of the bits in <N>")
+    usage = "Restrict to reads that mismatch at least one of the bits in <N>"
+  )
   var mismatchSomeBits: Int = 0
 
   @Args4jOption(
     required = false,
     name = "-c",
-    usage = "Print count of matching records, instead of the records themselves")
+    usage = "Print count of matching records, instead of the records themselves"
+  )
   var printCount: Boolean = false
 
   @Args4jOption(
     required = false,
     name = "-o",
     metaVar = "<FILE>",
-    usage = "Output to <FILE>; can also pass <FILE> as the second argument")
+    usage = "Output to <FILE>; can also pass <FILE> as the second argument"
+  )
   var outputPathArg: String = null
 
   @Args4jOption(required = false, name = "-sort_fastq_output", usage = "Sets whether to sort the FASTQ output, if saving as FASTQ. False by default. Ignored if not saving as FASTQ.")
@@ -148,8 +154,7 @@ class View(val args: ViewArgs) extends BDGSparkCommand[ViewArgs] {
       reads.filter(read =>
         allFilters.forall(_(read)) &&
           (matchSomeFilters.isEmpty || matchSomeFilters.exists(_(read))) &&
-          (mismatchSomeFilters.isEmpty || mismatchSomeFilters.exists(_(read)))
-      )
+          (mismatchSomeFilters.isEmpty || mismatchSomeFilters.exists(_(read))))
     } else
       reads
   }

adam-core/src/main/java/org/bdgenomics/adam/io/IndexedBamInputFormat.scala

@@ -57,7 +57,7 @@ class IndexedBamInputFormat extends BAMInputFormat {
   override def createRecordReader(split: InputSplit, ctx: TaskAttemptContext): RecordReader[LongWritable, SAMRecordWritable] = {
     val rr: RecordReader[LongWritable, SAMRecordWritable] = new BAMFilteredRecordReader()
     assert(IndexedBamInputFormat.optViewRegion.isDefined)
-    BAMFilteredRecordReader.setRegion(IndexedBamInputFormat.optViewRegion.get)
+    IndexedBamInputFormat.optViewRegion.foreach { (refReg) => BAMFilteredRecordReader.setRegion(refReg) }
     rr.initialize(split, ctx)
     rr
   }

adam-core/src/main/scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGenerator.scala

@@ -39,9 +39,10 @@ abstract class ConsensusGenerator extends Serializable {
    * @param reads Reads to preprocess.
    * @return Preprocessed reads.
    */
-  def preprocessReadsForRealignment(reads: Iterable[RichAlignmentRecord],
-                                    reference: String,
-                                    region: ReferenceRegion): Iterable[RichAlignmentRecord]
+  def preprocessReadsForRealignment(
+    reads: Iterable[RichAlignmentRecord],
+    reference: String,
+    region: ReferenceRegion): Iterable[RichAlignmentRecord]
 
   /**
    * For all reads in this region, generates the list of consensus sequences for realignment.

adam-core/src/main/scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromKnowns.scala

@@ -51,9 +51,10 @@ class ConsensusGeneratorFromKnowns(file: String, @transient sc: SparkContext) ex
    * @param reads Reads to preprocess.
    * @return Preprocessed reads.
    */
-  def preprocessReadsForRealignment(reads: Iterable[RichAlignmentRecord],
-                                    reference: String,
-                                    region: ReferenceRegion): Iterable[RichAlignmentRecord] = {
+  def preprocessReadsForRealignment(
+    reads: Iterable[RichAlignmentRecord],
+    reference: String,
+    region: ReferenceRegion): Iterable[RichAlignmentRecord] = {
     reads
   }
 
@@ -67,8 +68,8 @@ class ConsensusGeneratorFromKnowns(file: String, @transient sc: SparkContext) ex
     val table = indelTable.value
 
     // get region
-    val start = reads.map(_.record.getStart.toLong).reduce(_ min _)
-    val end = reads.map(_.getEnd.toLong).reduce(_ max _)
+    val start = reads.map(_.record.getStart).min
+    val end = reads.map(_.getEnd).max
     val refId = reads.head.record.getContig.getContigName
 
     val region = ReferenceRegion(refId, start, end + 1)

adam-core/src/main/scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromReads.scala

@@ -44,9 +44,10 @@ class ConsensusGeneratorFromReads extends ConsensusGenerator {
    * @param reads Reads to process.
    * @return Reads with indels normalized if they contain a single indel.
    */
-  def preprocessReadsForRealignment(reads: Iterable[RichAlignmentRecord],
-                                    reference: String,
-                                    region: ReferenceRegion): Iterable[RichAlignmentRecord] = {
+  def preprocessReadsForRealignment(
+    reads: Iterable[RichAlignmentRecord],
+    reference: String,
+    region: ReferenceRegion): Iterable[RichAlignmentRecord] = {
     reads.map(r => {
       // if there are two alignment blocks (sequence matches) then there is a single indel in the read
       if (r.samtoolsCigar.numAlignmentBlocks == 2) {
@@ -74,10 +75,14 @@ class ConsensusGeneratorFromReads extends ConsensusGenerator {
       .flatMap(r => {
         // try to generate a consensus alignment - if a consensus exists, add it to our
         // list of consensuses to test
-        Consensus.generateAlternateConsensus(r.getSequence,
-          ReferencePosition(r.getContig.getContigName,
-            r.getStart),
-          r.samtoolsCigar)
+        Consensus.generateAlternateConsensus(
+          r.getSequence,
+          ReferencePosition(
+            r.getContig.getContigName,
+            r.getStart
+          ),
+          r.samtoolsCigar
+        )
       })
       .toSeq
       .distinct

adam-core/src/main/scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromSmithWaterman.scala

@@ -25,10 +25,11 @@ import org.bdgenomics.adam.rich.RichCigar._
 import org.bdgenomics.adam.util.MdTag
 import org.bdgenomics.formats.avro.AlignmentRecord
 
-class ConsensusGeneratorFromSmithWaterman(wMatch: Double,
-                                          wMismatch: Double,
-                                          wInsert: Double,
-                                          wDelete: Double) extends ConsensusGeneratorFromReads {
+class ConsensusGeneratorFromSmithWaterman(
+    wMatch: Double,
+    wMismatch: Double,
+    wInsert: Double,
+    wDelete: Double) extends ConsensusGeneratorFromReads {
 
   /**
    * Attempts realignment of all reads using Smith-Waterman. Accepts all realignments that have one
@@ -37,25 +38,30 @@ class ConsensusGeneratorFromSmithWaterman(wMatch: Double,
    * @param reads Reads to process.
    * @return Reads with indels normalized if they contain a single indel.
    */
-  override def preprocessReadsForRealignment(reads: Iterable[RichAlignmentRecord],
-                                             reference: String,
-                                             region: ReferenceRegion): Iterable[RichAlignmentRecord] = {
+  override def preprocessReadsForRealignment(
+    reads: Iterable[RichAlignmentRecord],
+    reference: String,
+    region: ReferenceRegion): Iterable[RichAlignmentRecord] = {
     val rds: Iterable[RichAlignmentRecord] = reads.map(r => {
 
-      val sw = new SmithWatermanConstantGapScoring(r.record.getSequence.toString,
+      val sw = new SmithWatermanConstantGapScoring(
+        r.record.getSequence,
         reference,
         wMatch,
         wMismatch,
         wInsert,
-        wDelete)
+        wDelete
+      )
       println("for " + r.record.getReadName + " sw to " + sw.xStart + " with " + sw.cigarX)
 
       // if we realign with fewer than three alignment blocks, then take the new alignment
       if (sw.cigarX.numAlignmentBlocks <= 2) {
-        val mdTag = MdTag(r.record.getSequence.toString,
+        val mdTag = MdTag(
+          r.record.getSequence,
           reference.drop(sw.xStart),
           sw.cigarX,
-          region.start)
+          region.start
+        )
 
         val newRead: RichAlignmentRecord = AlignmentRecord.newBuilder(r)
           .setStart(sw.xStart + region.start)

adam-core/src/main/scala/org/bdgenomics/adam/algorithms/smithwaterman/SmithWaterman.scala

@@ -130,11 +130,12 @@ abstract class SmithWaterman(xSequence: String, ySequence: String) extends Seria
    *
    * @see buildScoringMatrix
    */
-  @tailrec private[smithwaterman] final def move(matrix: Array[Array[Char]],
-                                                 i: Int,
-                                                 j: Int,
-                                                 cX: String,
-                                                 cY: String): (String, String, Int, Int) = {
+  @tailrec private[smithwaterman] final def move(
+    matrix: Array[Array[Char]],
+    i: Int,
+    j: Int,
+    cX: String,
+    cY: String): (String, String, Int, Int) = {
     if (matrix(i)(j) == 'T') {
       // return if told to terminate
       (cigarFromRNNCigar(cX), cigarFromRNNCigar(cY), i, j)
@@ -160,8 +161,9 @@ abstract class SmithWaterman(xSequence: String, ySequence: String) extends Seria
    * @param moveMatrix Move matrix to track back on.
    * @return Tuple of Cigar for X, Y.
    */
-  private[smithwaterman] def trackback(scoreMatrix: Array[Array[Double]],
-                                       moveMatrix: Array[Array[Char]]): (Cigar, Cigar, Int, Int) = {
+  private[smithwaterman] def trackback(
+    scoreMatrix: Array[Array[Double]],
+    moveMatrix: Array[Array[Char]]): (Cigar, Cigar, Int, Int) = {
     assert(scoreMatrix.length == xSequence.length + 1)
     assert(scoreMatrix.forall(_.length == ySequence.length + 1))
     assert(moveMatrix.length == xSequence.length + 1)