added java friendly version of filterByOverlappingRegions

bigdatagenomics · Jan 30, 2018 · e3540ac · e3540ac
1 parent 95e7109
commit e3540ac
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 2 deletions.
diff --git a/adam-cli/src/main/scala/org/bdgenomics/adam/cli/TransformAlignments.scala b/adam-cli/src/main/scala/org/bdgenomics/adam/cli/TransformAlignments.scala
@@ -17,7 +17,6 @@
  */
 package org.bdgenomics.adam.cli
 
-import scala.collection.JavaConverters._
 import htsjdk.samtools.ValidationStringency
 import java.time.Instant
 import org.apache.parquet.filter2.dsl.Dsl._
@@ -488,7 +487,7 @@ class TransformAlignments(protected val args: TransformAlignmentsArgs) extends B
 
  if (args.regionPredicate != null) {
  val loci = ReferenceRegion.fromString(args.regionPredicate)
- loadedReads.filterByOverlappingRegions(loci.asJava)
+ loadedReads.filterByOverlappingRegions(loci)
  } else {
  loadedReads
  }

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/GenomicRDD.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/GenomicRDD.scala
@@ -725,6 +725,25 @@ trait GenomicRDD[T, U <: GenomicRDD[T, U]] extends Logging {
  * @return Returns a new GenomicRDD containing only data that overlaps the
  * querys region.
  */
+ def filterByOverlappingRegions(querys: Iterable[ReferenceRegion]): U = {
+ replaceRdd(rdd.filter(elem => {
+
+ val regions = getReferenceRegions(elem)
+
+ querys.exists(query => {
+ regions.exists(_.overlaps(query))
+ })
+ }), optPartitionMap)
+ }
+
+ /**
+ * Runs a filter that selects data in the underlying RDD that overlaps
+ * several genomic regions. Java friendly version.
+ *
+ * @param querys The regions to query for.
+ * @return Returns a new GenomicRDD containing only data that overlaps the
+ * querys region.
+ */
  def filterByOverlappingRegions(querys: java.lang.Iterable[ReferenceRegion]): U = {
  replaceRdd(rdd.filter(elem => {