Merge pull request #17 from ryan-williams/ug

spark-util upgrade

.travis.yml

@@ -4,21 +4,21 @@ jdk:
   - oraclejdk8
 
 scala:
-  - 2.11.8
+  - 2.11.12
 
 env:
   - vars="-Dhadoop.version=2.6.0 -Dspark.version=2.1.0 -Dcoveralls.disable=1"
   - vars=""
 
-script: sbt $vars ++$TRAVIS_SCALA_VERSION clean coverage test
+script: sbt $vars ++$TRAVIS_SCALA_VERSION clean coverageTest
 
 cache:
   directories:
   - \$HOME/.ivy2/cache
   - \$HOME/.sbt/boot/
   - \$HOME/.zinc
 
-after_success: sbt $vars ++$TRAVIS_SCALA_VERSION travis-report
+after_success: bash <(curl -s https://codecov.io/bash)
 
 before_cache:
   # Tricks to avoid unnecessary cache updates

build.sbt

@@ -1,39 +1,30 @@
-organization := "org.hammerlab.adam"
+subgroup("adam", "core")
+github.repo("adam")
+v"0.23.4"
 
-name := "core"
-
-version := "0.23.2"
-
-addSparkDeps
+spark
 publishTestJar
-enableScalariform
-
-testDeps += ("org.mockito" ^ "mockito-core") ^ "2.6.4"
 
-testUtilsVersion := "1.3.0"
-sparkTestsVersion := "2.1.1"
-
-deps ++= Seq(
-  bdg_formats,
-  bdg_utils_cli ^ "0.3.0",
-  bdg_utils_intervalrdd,
-  bdg_utils_io,
-  bdg_utils_metrics,
-  bdg_utils_misc,
-  commons_io,
-  hadoop_bam ^ "7.9.0",
+dep(
+  bdg.formats,
+  hammerlab("bdg-utils", "cli") % "0.3.0",
+  bdg.utils.intervalrdd,
+  bdg.utils.io,
+  bdg.utils.metrics,
+  bdg.utils.misc +testtest,
+  commons.io,
+  seqdoop_hadoop_bam % "7.9.0",
+  genomics.loci % "2.2.0",
+  genomics.reference % "1.5.0" - htsjdk +testtest,
   htsjdk,
-  loci ^ "2.0.1",
   log4j,
   parquet_avro,
-  paths ^ "1.2.0",
-  spark_util ^ "1.2.1",
+  paths % "1.5.0",
+  spark_util % "3.0.0",
   "it.unimi.dsi" ^ "fastutil" ^ "6.6.5",
   "org.apache.avro" ^ "avro" ^ "1.8.1",
   "org.apache.httpcomponents" ^ "httpclient" ^ "4.5.2",
   ("org.apache.parquet" ^ "parquet-scala_2.10" ^ "1.8.1") - scala_lang
 )
 
-compileAndTestDeps += (reference % "1.4.0" - htsjdk)
-
-testTestDeps += bdg_utils_misc
+testDeps += "org.mockito" ^ "mockito-core" ^ "2.6.4"

project/build.properties

@@ -1 +1 @@
-sbt.version=0.13.13
+sbt.version=1.1.5

project/plugins.sbt

@@ -1 +1 @@
-addSbtPlugin("org.hammerlab" % "sbt-parent" % "3.0.0")
+addSbtPlugin("org.hammerlab.sbt" % "base" % "4.6.2")

src/main/scala/org/bdgenomics/adam/rdd/ADAMContext.scala

@@ -55,7 +55,7 @@ import org.bdgenomics.adam.util.{ ReferenceContigMap, ReferenceFile, TwoBitFile
 import org.bdgenomics.formats.avro._
 import org.bdgenomics.utils.instrumentation.Metrics
 import org.bdgenomics.utils.misc.{ HadoopUtil, Logging }
-import org.hammerlab.genomics.loci.parsing.{ LociRange, LociRanges, ParsedLoci }
+import org.hammerlab.genomics.loci.parsing.{ Range, LociRanges, ParsedLoci }
 import org.hammerlab.genomics.loci.set.LociSet
 import org.hammerlab.genomics.reference.ContigName.Factory
 import org.hammerlab.genomics.reference.Locus
@@ -731,7 +731,7 @@ class ADAMContext(val sc: SparkContext)(implicit factory: Factory)
       LociRanges(
         viewRegions.map(
           region =>
-            LociRange(region.referenceName, Locus(region.start), Locus(region.end))
+            Range(region.referenceName, Locus(region.start), Locus(region.end))
         )
       )
     )

src/main/scala/org/bdgenomics/adam/rdd/read/AlignmentRecordRDD.scala

@@ -825,7 +825,7 @@ case class AlignmentRecordRDD(
       case SILENT ⇒
     }
 
-    val pairedRecords: RDD[AlignmentRecord] = readsByID.filter(_._2.size == 2).map(_._2).flatMap(x => x)
+    val pairedRecords: RDD[AlignmentRecord] = readsByID.filter(_._2.size == 2).values.flatMap(x => x)
     maybePersist(pairedRecords)
     val numPairedRecords = pairedRecords.count()