Several package moves, as part of the org.bdgenomics.adam.util clea…

…nup: * Moved `NormalizationUtils` to `org.bdgenomics.adam.algorithms.consensus`, and made it package private to `consensus`. * Moved `MdTag` to `org.bdgenomics.adam.models`. * Moved `QualityScore` to `org.bdgenomics.adam.models` and made it package private to `consensus`.
bigdatagenomics · Nov 6, 2016 · f148b07 · f148b07
1 parent 694dbe2
commit f148b07
Show file tree

Hide file tree

Showing 16 changed files with 44 additions and 34 deletions.
diff --git a/...src/main/scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromReads.scala b/...src/main/scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromReads.scala
@@ -18,13 +18,11 @@
 package org.bdgenomics.adam.algorithms.consensus
 
 import org.apache.spark.rdd.RDD
-import org.bdgenomics.adam.models.{ ReferencePosition, ReferenceRegion }
+import org.bdgenomics.adam.models.{ MdTag, ReferencePosition, ReferenceRegion }
 import org.bdgenomics.adam.rdd.read.realignment.IndelRealignmentTarget
 import org.bdgenomics.adam.rich.RichAlignmentRecord._
 import org.bdgenomics.adam.rich.RichCigar._
 import org.bdgenomics.adam.rich.RichAlignmentRecord
-import org.bdgenomics.adam.util.NormalizationUtils._
-import org.bdgenomics.adam.util.MdTag
 import org.bdgenomics.formats.avro.AlignmentRecord
 
 /**
@@ -59,7 +57,7 @@ private[adam] class ConsensusGeneratorFromReads extends ConsensusGenerator {
       // if there are two alignment blocks (sequence matches) then there is a single indel in the read
       if (r.samtoolsCigar.numAlignmentBlocks == 2) {
         // left align this indel and update the mdtag
-        val cigar = leftAlignIndel(r)
+        val cigar = NormalizationUtils.leftAlignIndel(r)
         val mdTag = MdTag.moveAlignment(r, cigar)
 
         val newRead: RichAlignmentRecord = AlignmentRecord.newBuilder(r)

diff --git a/.../scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromSmithWaterman.scala b/.../scala/org/bdgenomics/adam/algorithms/consensus/ConsensusGeneratorFromSmithWaterman.scala
@@ -18,11 +18,10 @@
 package org.bdgenomics.adam.algorithms.consensus
 
 import org.bdgenomics.adam.algorithms.smithwaterman.SmithWatermanConstantGapScoring
-import org.bdgenomics.adam.models.ReferenceRegion
+import org.bdgenomics.adam.models.{ MdTag, ReferenceRegion }
 import org.bdgenomics.adam.rich.RichAlignmentRecord._
 import org.bdgenomics.adam.rich.RichCigar._
 import org.bdgenomics.adam.rich.RichAlignmentRecord
-import org.bdgenomics.adam.util.MdTag
 import org.bdgenomics.formats.avro.AlignmentRecord
 
 /**

diff --git a/...nomics/adam/util/NormalizationUtils.scala → ...rithms/consensus/NormalizationUtils.scala b/...nomics/adam/util/NormalizationUtils.scala → ...rithms/consensus/NormalizationUtils.scala
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.bdgenomics.adam.util
+package org.bdgenomics.adam.algorithms.consensus
 
 import htsjdk.samtools.{ Cigar, CigarOperator }
 import org.bdgenomics.adam.rich.RichAlignmentRecord
@@ -27,7 +27,7 @@ import scala.collection.JavaConversions._
 /**
  * Utility for left normalizing INDELs in alignments.
  */
-private[adam] object NormalizationUtils {
+private[consensus] object NormalizationUtils {
 
   /**
    * Given a cigar, returns the cigar with the position of the cigar shifted left.
@@ -115,7 +115,7 @@ private[adam] object NormalizationUtils {
    * @param preceeding Bases of sequence to left of variant.
    * @return The number of bases to shift an indel for it to be left normalized.
    */
-  private[util] def numberOfPositionsToShiftIndel(variant: String, preceeding: String): Int = {
+  private[consensus] def numberOfPositionsToShiftIndel(variant: String, preceeding: String): Int = {
 
     // tail recursive function to determine shift
     @tailrec def numberOfPositionsToShiftIndelAccumulate(variant: String, preceeding: String, accumulator: Int): Int = {
@@ -142,7 +142,7 @@ private[adam] object NormalizationUtils {
    * @param shifts Number of bases to shift element.
    * @return Cigar that has been shifted as far left as possible.
    */
-  @tailrec private[util] def shiftIndel(cigar: Cigar, position: Int, shifts: Int): Cigar = {
+  @tailrec private[consensus] def shiftIndel(cigar: Cigar, position: Int, shifts: Int): Cigar = {
     // generate new cigar with indel shifted by one
     val newCigar = new Cigar(cigar.getCigarElements).moveLeft(position)
 

diff --git a/...cala/org/bdgenomics/adam/util/MdTag.scala → ...la/org/bdgenomics/adam/models/MdTag.scala b/...cala/org/bdgenomics/adam/util/MdTag.scala → ...la/org/bdgenomics/adam/models/MdTag.scala
@@ -15,10 +15,9 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.bdgenomics.adam.util
+package org.bdgenomics.adam.models
 
 import htsjdk.samtools.{ Cigar, CigarOperator }
-import org.bdgenomics.adam.models.ReferencePosition
 import org.bdgenomics.adam.rich.RichAlignmentRecord._
 import org.bdgenomics.adam.rich.RichAlignmentRecord
 import scala.collection.JavaConversions._

diff --git a/...g/bdgenomics/adam/util/QualityScore.scala → ...bdgenomics/adam/models/QualityScore.scala b/...g/bdgenomics/adam/util/QualityScore.scala → ...bdgenomics/adam/models/QualityScore.scala
@@ -15,14 +15,16 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.bdgenomics.adam.util
+package org.bdgenomics.adam.models
+
+import org.bdgenomics.adam.util.PhredUtils
 
 /**
  * Model describing a single Quality score.
  *
  * @param phred The phred score.
  */
-case class QualityScore(phred: Int) extends Ordered[QualityScore] with Serializable {
+private[adam] case class QualityScore(phred: Int) extends Ordered[QualityScore] with Serializable {
 
   // Valid range of phred + 33 is described by the regex "[!-~]".
   require(phred + 33 >= '!'.toInt && phred + 33 <= '~'.toInt, "Phred %s out of range".format(phred))
@@ -58,7 +60,7 @@ case class QualityScore(phred: Int) extends Ordered[QualityScore] with Serializa
 /**
  * Companion object for building quality score objects.
  */
-object QualityScore {
+private[adam] object QualityScore {
 
   /**
    * The lowest quality score.

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/MDTagging.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/MDTagging.scala
@@ -19,13 +19,13 @@ package org.bdgenomics.adam.rdd.read
 
 import org.bdgenomics.adam.rdd.ADAMContext._
 import htsjdk.samtools.{ TextCigarCodec, ValidationStringency }
-import org.bdgenomics.utils.misc.Logging
 // NOTE(ryan): this is necessary for Spark <= 1.2.1.
 import org.apache.spark.SparkContext._
 import org.apache.spark.rdd.RDD
-import org.bdgenomics.adam.models.ReferenceRegion
-import org.bdgenomics.adam.util.{ ReferenceFile, MdTag }
+import org.bdgenomics.adam.models.{ MdTag, ReferenceRegion }
+import org.bdgenomics.adam.util.ReferenceFile
 import org.bdgenomics.formats.avro.AlignmentRecord
+import org.bdgenomics.utils.misc.Logging
 
 case class MDTagging(
     reads: RDD[AlignmentRecord],

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/realignment/RealignIndels.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/realignment/RealignIndels.scala
@@ -23,10 +23,9 @@ import org.apache.spark.rdd.MetricsContext._
 import org.apache.spark.rdd.RDD
 import org.bdgenomics.adam.algorithms.consensus.{ Consensus, ConsensusGenerator, ConsensusGeneratorFromReads }
 import org.bdgenomics.adam.models.ReferenceRegion._
-import org.bdgenomics.adam.models.{ ReferencePosition, ReferenceRegion }
+import org.bdgenomics.adam.models.{ MdTag, ReferencePosition, ReferenceRegion }
 import org.bdgenomics.adam.rich.RichAlignmentRecord
 import org.bdgenomics.adam.rich.RichAlignmentRecord._
-import org.bdgenomics.adam.util.MdTag
 import org.bdgenomics.adam.instrumentation.Timers._
 import org.bdgenomics.formats.avro.AlignmentRecord
 import scala.annotation.tailrec

diff --git a/.../src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/BaseQualityRecalibration.scala b/.../src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/BaseQualityRecalibration.scala
@@ -23,10 +23,9 @@ import org.apache.spark.SparkContext._
 import org.bdgenomics.utils.misc.Logging
 import org.apache.spark.broadcast.Broadcast
 import org.apache.spark.rdd.RDD
-import org.bdgenomics.adam.models.SnpTable
+import org.bdgenomics.adam.models.{ QualityScore, SnpTable }
 import org.bdgenomics.adam.rich.DecadentRead
 import org.bdgenomics.adam.rich.DecadentRead._
-import org.bdgenomics.adam.util.QualityScore
 import org.bdgenomics.formats.avro.AlignmentRecord
 
 /**

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/Covariate.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/Covariate.scala
@@ -17,8 +17,8 @@
  */
 package org.bdgenomics.adam.rdd.read.recalibration
 
+import org.bdgenomics.adam.models.QualityScore
 import org.bdgenomics.adam.rich.DecadentRead
-import org.bdgenomics.adam.util.QualityScore
 
 /**
  * A Covariate represents a predictor, also known as a "feature" or

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/ObservationTable.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/ObservationTable.scala
@@ -18,7 +18,7 @@
 package org.bdgenomics.adam.rdd.read.recalibration
 
 import org.bdgenomics.adam.instrumentation.Timers._
-import org.bdgenomics.adam.util.QualityScore
+import org.bdgenomics.adam.models.QualityScore
 import scala.collection.mutable
 
 /**

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/Recalibrator.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/read/recalibration/Recalibrator.scala
@@ -17,10 +17,10 @@
  */
 package org.bdgenomics.adam.rdd.read.recalibration
 
+import org.bdgenomics.adam.models.QualityScore
 import org.bdgenomics.adam.rich.DecadentRead.Residue
 import org.bdgenomics.adam.rich.RichAlignmentRecord._
 import org.bdgenomics.adam.rich.DecadentRead
-import org.bdgenomics.adam.util.QualityScore
 import org.bdgenomics.formats.avro.AlignmentRecord
 import org.bdgenomics.adam.instrumentation.Timers._
 import scala.math.{ exp, log }

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rich/DecadentRead.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rich/DecadentRead.scala
@@ -20,10 +20,14 @@ package org.bdgenomics.adam.rich
 import htsjdk.samtools.ValidationStringency
 import org.bdgenomics.utils.misc.Logging
 import org.apache.spark.rdd.RDD
-import org.bdgenomics.adam.models.ReferencePosition
+import org.bdgenomics.adam.models.{
+  MdTag,
+  ReferencePosition,
+  ReferenceRegion,
+  QualityScore
+}
 import org.bdgenomics.adam.rdd.ADAMContext._
 import org.bdgenomics.adam.rich.RichAlignmentRecord._
-import org.bdgenomics.adam.util.{ MdTag, QualityScore }
 import org.bdgenomics.formats.avro.AlignmentRecord
 
 @deprecated("Use RichAlignmentRecord wherever possible in new development.", since = "0.18.0")

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rich/RichAlignmentRecord.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rich/RichAlignmentRecord.scala
@@ -17,10 +17,20 @@
  */
 package org.bdgenomics.adam.rich
 
-import htsjdk.samtools.{ Cigar, CigarElement, CigarOperator, TextCigarCodec }
+import htsjdk.samtools.{
+  Cigar,
+  CigarElement,
+  CigarOperator,
+  TextCigarCodec
+}
 import java.util.regex.Pattern
-import org.bdgenomics.adam.models.{ Attribute, ReferencePosition, ReferenceRegion }
-import org.bdgenomics.adam.util._
+import org.bdgenomics.adam.models.{
+  Attribute,
+  MdTag,
+  ReferencePosition,
+  ReferenceRegion
+}
+import org.bdgenomics.adam.util.AttributeUtils
 import org.bdgenomics.formats.avro.{ AlignmentRecord, Strand }
 import scala.collection.JavaConversions._
 import scala.collection.immutable.NumericRange

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/serialization/ADAMKryoRegistrator.scala b/adam-core/src/main/scala/org/bdgenomics/adam/serialization/ADAMKryoRegistrator.scala
@@ -125,8 +125,10 @@ class ADAMKryoRegistrator extends KryoRegistrator {
 
     // org.bdgenomics.adam.models
     kryo.register(classOf[org.bdgenomics.adam.models.Coverage])
+    kryo.register(classOf[org.bdgenomics.adam.models.MdTag])
     kryo.register(classOf[org.bdgenomics.adam.models.MultiContigNonoverlappingRegions])
     kryo.register(classOf[org.bdgenomics.adam.models.NonoverlappingRegions])
+    kryo.register(classOf[org.bdgenomics.adam.models.QualityScore])
     kryo.register(classOf[org.bdgenomics.adam.models.RecordGroup])
     kryo.register(classOf[org.bdgenomics.adam.models.RecordGroupDictionary])
     kryo.register(classOf[org.bdgenomics.adam.models.ReferencePosition],
@@ -172,8 +174,6 @@ class ADAMKryoRegistrator extends KryoRegistrator {
     kryo.register(classOf[org.bdgenomics.adam.rich.RichVariant])
 
     // org.bdgenomics.adam.util
-    kryo.register(classOf[org.bdgenomics.adam.util.MdTag])
-    kryo.register(classOf[org.bdgenomics.adam.util.QualityScore])
     kryo.register(classOf[org.bdgenomics.adam.util.ReferenceContigMap])
     kryo.register(classOf[org.bdgenomics.adam.util.TwoBitFile],
       new org.bdgenomics.adam.util.TwoBitFileSerializer)

diff --git a/...s/adam/util/NormalizationUtilsSuite.scala → ...s/consensus/NormalizationUtilsSuite.scala b/...s/adam/util/NormalizationUtilsSuite.scala → ...s/consensus/NormalizationUtilsSuite.scala
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.bdgenomics.adam.util
+package org.bdgenomics.adam.algorithms.consensus
 
 import htsjdk.samtools.TextCigarCodec
 import org.bdgenomics.adam.rich.RichAlignmentRecord._

diff --git a/...org/bdgenomics/adam/util/MdTagSuite.scala → ...g/bdgenomics/adam/models/MdTagSuite.scala b/...org/bdgenomics/adam/util/MdTagSuite.scala → ...g/bdgenomics/adam/models/MdTagSuite.scala
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.bdgenomics.adam.util
+package org.bdgenomics.adam.models
 
 import htsjdk.samtools.TextCigarCodec
 import org.bdgenomics.adam.rich.RichAlignmentRecord._