Updates (#22)

CHANGELOG.md

@@ -1,5 +1,8 @@
 # Changelog
 
+## 3.6.4
+No user-facing changes
+
 ## 3.6.3
 * Documentation for processing demultiplexed FASTQ files
 

build.sbt

@@ -2,34 +2,33 @@ val artifactId = "poolq"
 
 inThisBuild(
   List(
-    scalaVersion := "2.13.10",
+    scalaVersion := "2.13.11",
     semanticdbEnabled := true,
     semanticdbVersion := scalafixSemanticdb.revision,
-    scalafixDependencies += "com.github.liancheng" %% "organize-imports" % "0.6.0",
     versionScheme := Some("early-semver")
   )
 )
 
 lazy val versions = new {
   val acyclic = "0.2.1"
-  val betterFiles = "3.9.1"
+  val betterFiles = "3.9.2"
   val betterMonadicFor = "0.3.1"
-  val catsEffect3 = "3.4.5"
-  val cats = "2.9.0"
-  val commonsIo = "2.11.0"
+  val catsEffect3 = "3.5.1"
+  val cats = "2.10.0"
+  val commonsIo = "2.13.0"
   val commonsText = "1.10.0"
   val commonsMath3 = "3.6.1"
-  val fastutil = "8.5.11"
-  val fs2 = "3.5.0"
+  val fastutil = "8.5.12"
+  val fs2 = "3.8.0"
   val kantanCodecs = "0.5.3"
   val kantanCsv = "0.7.0"
   val log4s = "1.10.0"
   val logback = "1.2.11"
   val munit = "0.7.29"
   val munitCatsEffect3 = "1.0.7"
-  val samTools = "3.0.4"
+  val samTools = "3.0.5"
   val scalaCheck = "1.17.0"
-  val scalaTest = "3.2.15"
+  val scalaTest = "3.2.16"
   val scalaTestPlusScalaCheck = "3.2.2.0"
   val scopt = "4.1.0"
   val slf4j = "1.7.36"

project/build.properties

@@ -1 +1 @@
-sbt.version=1.8.2
+sbt.version=1.9.4

project/plugins.sbt

@@ -1,11 +1,11 @@
-addSbtPlugin("ch.epfl.scala" % "sbt-missinglink" % "0.3.3")
-addSbtPlugin("ch.epfl.scala" % "sbt-scalafix" % "0.10.4")
+addSbtPlugin("ch.epfl.scala" % "sbt-missinglink" % "0.3.6")
+addSbtPlugin("ch.epfl.scala" % "sbt-scalafix" % "0.11.0")
 addSbtPlugin("com.codecommit" % "sbt-github-packages" % "0.5.3")
 addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "1.2.0")
 addSbtPlugin("com.eed3si9n" % "sbt-buildinfo" % "0.11.0")
-addSbtPlugin("com.github.cb372" % "sbt-explicit-dependencies" % "0.2.16")
+addSbtPlugin("com.github.cb372" % "sbt-explicit-dependencies" % "0.3.1")
 addSbtPlugin("com.github.sbt" % "sbt-release" % "1.1.0")
-addSbtPlugin("de.heikoseeberger" % "sbt-header" % "5.9.0")
-addSbtPlugin("io.github.davidgregory084" % "sbt-tpolecat" % "0.4.1")
+addSbtPlugin("de.heikoseeberger" % "sbt-header" % "5.10.0")
+addSbtPlugin("org.typelevel" % "sbt-tpolecat" % "0.5.0")
 addSbtPlugin("org.scalameta" % "sbt-scalafmt" % "2.5.0")
-addSbtPlugin("org.scoverage" % "sbt-scoverage" % "1.9.3")
+addSbtPlugin("org.scoverage" % "sbt-scoverage" % "2.0.8")

src/main/scala/org/broadinstitute/gpp/poolq3/parser/BarcodeSet.scala

@@ -36,7 +36,12 @@ object BarcodeSet {
 
   def apply(file: Path): BarcodeSet =
     Using.resource(new FileInputStream(file.toFile)) { fin =>
-      val in = new BOMInputStream(fin, false, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE)
+      val in = BOMInputStream
+        .builder()
+        .setInputStream(fin)
+        .setByteOrderMarks(ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE)
+        .setInclude(false)
+        .get()
       val br = new BufferedReader(new InputStreamReader(in))
       skipHeader(br, BarcodeRe)
       br.lines()

src/main/scala/org/broadinstitute/gpp/poolq3/parser/ReferenceData.scala

@@ -70,7 +70,12 @@ object ReferenceData {
 
   def apply(file: Path, quote: Char = '"'): ReferenceData = {
     Using.resource(new FileInputStream(file.toFile)) { fin =>
-      val in = new BOMInputStream(fin, false, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE)
+      val in = BOMInputStream
+        .builder()
+        .setInputStream(fin)
+        .setByteOrderMarks(ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE)
+        .setInclude(false)
+        .get()
       val br = new BufferedReader(new InputStreamReader(in))
       val delimiter = guessDelimiter(br)
       val config =

src/main/scala/org/broadinstitute/gpp/poolq3/process/ScoringConsumer.scala

@@ -159,9 +159,8 @@ final class ScoringConsumer(
     log.debug(s"Incrementing state for ($r, $c}).")
     umiReference match {
       case None =>
-        None
         // we're not in UMI mode, so just increment the state
-        state.known.increment(None, (r, c))
+        val _ = state.known.increment(None, (r, c))
       case Some(ref) =>
         // we're in UMI mode
         handleUmi(umi, ref, r, c)
@@ -182,7 +181,7 @@ final class ScoringConsumer(
           val _ = state.known.increment(Some(u), (r, c))
         } else {
           // we found an unknown UMI barcode, so track it somehow
-          state.known.increment(None, (r, c))
+          val _ = state.known.increment(None, (r, c))
           val _ = state.unknownUmi.increment(u)
         }
       case None =>

src/main/scala/org/broadinstitute/gpp/poolq3/reports/UnexpectedSequenceWriter.scala

@@ -105,7 +105,7 @@ object UnexpectedSequenceWriter {
           val colBc = fields(1)
 
           // can't avoid the double hash lookup here without a big hassle
-          r.put(rowBc, r.getOrElseUpdate(rowBc, 0) + 1)
+          val _ = r.put(rowBc, r.getOrElseUpdate(rowBc, 0) + 1)
           h.putIfAbsent(rowBc, new Object2IntOpenHashMap[String]())
           h.get(rowBc).addTo(colBc, 1)
         }
@@ -120,7 +120,7 @@ object UnexpectedSequenceWriter {
   ): Unit = {
     val drop = r.toSeq.sortBy { case (_, count) => -count }.drop(n)
     drop.foreach { case (bc, _) =>
-      r.remove(bc)
+      val _ = r.remove(bc)
       h.remove(bc)
     }
   }

src/test/scala/org/broadinstitute/gpp/poolq3/barcode/BarcodePolicyTest.scala

@@ -5,50 +5,53 @@
  */
 package org.broadinstitute.gpp.poolq3.barcode
 
-import org.scalatest.flatspec.AnyFlatSpec
-import org.scalatest.matchers.should.Matchers._
+import munit.FunSuite
 
-class BarcodePolicyTest extends AnyFlatSpec {
+class BarcodePolicyTest extends FunSuite {
 
-  "BarcodePolicy" should "choose a fixed barcode policy" in {
-    BarcodePolicy("FIXED@0", 8, false) should be(FixedOffsetPolicy(0, 8, false))
+  test("fixed barcode policy") {
+    assertEquals(BarcodePolicy("FIXED@0", 8, false), FixedOffsetPolicy(0, 8, false))
     // this is a deprecated option but needs to be supported for the time being
-    BarcodePolicy("FIXED:0", 8, false) should be(FixedOffsetPolicy(0, 8, false))
+    assertEquals(BarcodePolicy("FIXED:0", 8, false), FixedOffsetPolicy(0, 8, false))
   }
 
-  it should "choose a known prefix barcode policy" in {
-    BarcodePolicy("PREFIX:CACCG@7", 20, false) should be(IndexOfKnownPrefixPolicy("CACCG", 20, Some(7)))
-    BarcodePolicy("PREFIX:CACCG@7-9", 20, false) should be(IndexOfKnownPrefixPolicy("CACCG", 20, Some(7), Some(9)))
-    BarcodePolicy("PREFIX:CACCG@-9", 20, false) should be(IndexOfKnownPrefixPolicy("CACCG", 20, None, Some(9)))
+  test("known prefix barcode policy") {
+    assertEquals(BarcodePolicy("PREFIX:CACCG@7", 20, false), IndexOfKnownPrefixPolicy("CACCG", 20, Some(7)))
+    assertEquals(BarcodePolicy("PREFIX:CACCG@7-9", 20, false), IndexOfKnownPrefixPolicy("CACCG", 20, Some(7), Some(9)))
+    assertEquals(BarcodePolicy("PREFIX:CACCG@-9", 20, false), IndexOfKnownPrefixPolicy("CACCG", 20, None, Some(9)))
   }
 
-  it should "let the user specify a shorter length with a fixed policy" in {
-    BarcodePolicy("FIXED@0:6", 6, true) should be(FixedOffsetPolicy(0, 6, true))
+  test("specify a shorter length with a fixed policy") {
+    assertEquals(BarcodePolicy("FIXED@0:6", 6, true), FixedOffsetPolicy(0, 6, true))
     // this is a deprecated option but needs to be supported for the time being
-    BarcodePolicy("FIXED:0:6", 6, true) should be(FixedOffsetPolicy(0, 6, true))
+    assertEquals(BarcodePolicy("FIXED:0:6", 6, true), FixedOffsetPolicy(0, 6, true))
   }
 
-  it should "let the user specify a shorter length with a known prefix policy" in {
-    BarcodePolicy("PREFIX:CACCG@7:19", 19, false) should be(IndexOfKnownPrefixPolicy("CACCG", 19, Some(7)))
+  test("specify a shorter length with a known prefix policy") {
+    assertEquals(BarcodePolicy("PREFIX:CACCG@7:19", 19, false), IndexOfKnownPrefixPolicy("CACCG", 19, Some(7)))
   }
 
-  it should "let the user specify a keymask policy" in {
-    BarcodePolicy("KEYMASK:caccgNNNNttNNNNaa@3", 8, false) should be(
+  test("keymask policy") {
+    assertEquals(
+      BarcodePolicy("KEYMASK:caccgNNNNttNNNNaa@3", 8, false),
       GeneralTemplatePolicy(KeyMask("caccgNNNNttNNNNaa"), Some(3), None)
     )
-    BarcodePolicy("TEMPLATE:caccgNNNNttNNNNaa@3", 8, false) should be(
+    assertEquals(
+      BarcodePolicy("TEMPLATE:caccgNNNNttNNNNaa@3", 8, false),
       GeneralTemplatePolicy(KeyMask("caccgNNNNttNNNNaa"), Some(3), None)
     )
   }
 
-  it should "recognize a split barcode situation" in {
-    BarcodePolicy("TEMPLATE:caccgNNNNNnnnnnntatgcNNNNaa@3", 9, false) should be(
+  test("split barcode situation") {
+    assertEquals(
+      BarcodePolicy("TEMPLATE:caccgNNNNNnnnnnntatgcNNNNaa@3", 9, false),
       SplitBarcodePolicy("CACCG", 5, 6, "TATGC", 4, Some(3), None)
     )
   }
 
-  it should "let the user specify just a 3' limit" in {
-    BarcodePolicy("TEMPLATE:NNNNNNNNNNNNNNNNNNNNNNN@-1", 23, false) should be(
+  test("specify just a 3' limit") {
+    assertEquals(
+      BarcodePolicy("TEMPLATE:NNNNNNNNNNNNNNNNNNNNNNN@-1", 23, false),
       GeneralTemplatePolicy(KeyMask("NNNNNNNNNNNNNNNNNNNNNNN"), None, Some(1))
     )
   }

src/test/scala/org/broadinstitute/gpp/poolq3/barcode/KeyMaskTest.scala

@@ -12,13 +12,13 @@ class KeyMaskTest extends AnyFlatSpec {
 
   "KeyMask.apply" should "construct the correct key mask from a pattern" in {
     val km0 = KeyMask("NNNNNNNNNNNNNNNNN")
-    km0 should be(KeyMask.fromString(17, "1-17"))
+    val _ = km0 should be(KeyMask.fromString(17, "1-17"))
     val km1 = KeyMask("NNNNNNNNNNNNNNNNNnNN")
-    km1 should be(KeyMask.fromString(20, "1-17,19-20"))
+    val _ = km1 should be(KeyMask.fromString(20, "1-17,19-20"))
     val km2 = KeyMask("nNNNNNNNNNNNNNNNNNnNNn")
-    km2 should be(KeyMask.fromString(22, "2-18,20-21"))
+    val _ = km2 should be(KeyMask.fromString(22, "2-18,20-21"))
     val km3 = KeyMask("nnnNNNNNNNNNNNNNNNNNnNNnN")
-    km3 should be(KeyMask.fromString(25, "4-20,22-23,25"))
+    val _ = km3 should be(KeyMask.fromString(25, "4-20,22-23,25"))
     val km4 = KeyMask("nnnnNNNNNNNNNNNNNNNNNNNNnnnnnn")
     km4 should be(KeyMask.fromString(30, "5-24"))
   }
@@ -30,14 +30,14 @@ class KeyMaskTest extends AnyFlatSpec {
     val km5 = KeyMask(
       "caccgNNNNNNNNNNNNNNNNNNNNnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnNNNNNNNNNNNNNNNNNNNNN"
     )
-    km5.contextLength should be(240)
-    km5.keyLengthInBases should be(41)
+    val _ = km5.contextLength should be(240)
+    val _ = km5.keyLengthInBases should be(41)
     km5.keyRanges should be(Seq(KeyRange(5, 24), KeyRange(219, 239)))
   }
 
   "KeyMask.fromString" should "compute the correct key mask from a list of key ranges in either syntax" in {
     val km1 = KeyMask.fromString(23, "4-20,22-23")
-    km1 should be(KeyMask(23, Seq(KeyRange(3, 19), KeyRange(21, 22))))
+    val _ = km1 should be(KeyMask(23, Seq(KeyRange(3, 19), KeyRange(21, 22))))
     val km2 = KeyMask.fromString(23, "4..20,22..23")
     km2 should be(KeyMask(23, Seq(KeyRange(3, 19), KeyRange(21, 22))))
   }
@@ -59,7 +59,7 @@ class KeyMaskTest extends AnyFlatSpec {
   }
 
   it should "merge adjacent ranges" in {
-    KeyMask.mergeAdjacent(Seq(KeyRange(1, 9), KeyRange(10, 12), KeyRange(14, 17))) should be(
+    val _ = KeyMask.mergeAdjacent(Seq(KeyRange(1, 9), KeyRange(10, 12), KeyRange(14, 17))) should be(
       Seq(KeyRange(1, 12), KeyRange(14, 17))
     )
     KeyMask.fromString(10, "1,2..4,5,6-8,9") should be(KeyMask.fromString(10, "1-9"))

src/test/scala/org/broadinstitute/gpp/poolq3/barcode/KeyMaskTest2.scala

@@ -5,23 +5,22 @@
  */
 package org.broadinstitute.gpp.poolq3.barcode
 
-import org.scalatest.flatspec.AnyFlatSpec
-import org.scalatest.matchers.should.Matchers._
+import munit.FunSuite
 
 /** This class provides additional tests for the KeyMask that are not found in the FISHR codebase from which KeyMask and
   * its primary test class were lifted. We will try not to modify the copied test classes to make subsequent updates
   * from FISHR easier. Instead, new PoolQ-specific tests will live here.
   */
-class KeyMaskTest2 extends AnyFlatSpec {
+class KeyMaskTest2 extends FunSuite {
 
-  "KeyMask.apply" should "construct the correct key mask from a pattern" in {
+  test("construct the correct key mask from a pattern") {
     //                 0        1         2
     //                 12345678901234567890123456789
     val km0 = KeyMask("caccgNNNNNnnnnnnnnnttacaNNNNN")
 
     // parsing should work how we expect
-    km0.keyRanges should be(Seq(KeyRange(5, 9), KeyRange(24, 28)))
-    km0.keyLengthInBases should be(10)
+    assertEquals(km0.keyRanges, Seq(KeyRange(5, 9), KeyRange(24, 28)))
+    assertEquals(km0.keyLengthInBases, 10)
   }
 
 }

src/test/scala/org/broadinstitute/gpp/poolq3/barcode/KeyRangeTest.scala

@@ -14,32 +14,32 @@ import org.scalatest.matchers.should.Matchers._
 class KeyRangeTest extends AnyFlatSpec {
 
   "KeyRange" should "enforce well-formedness" in {
-    noException should be thrownBy KeyRange(3, 4)
-    noException should be thrownBy KeyRange(3, 3)
-    an[IllegalArgumentException] should be thrownBy KeyRange(3, 2)
+    val _ = noException should be thrownBy KeyRange(3, 4)
+    val _ = noException should be thrownBy KeyRange(3, 3)
+    val _ = an[IllegalArgumentException] should be thrownBy KeyRange(3, 2)
     an[IllegalArgumentException] should be thrownBy KeyRange(-2, 2)
   }
 
   it should "have working compare()" in {
     val ord = implicitly[Ordering[KeyRange]]
-    ord.compare(KeyRange(2, 5), KeyRange(2, 5)) should be(0)
-    KeyRange(2, 5) should be <= KeyRange(2, 5)
-    KeyRange(2, 5) should be >= KeyRange(2, 5)
+    val _ = ord.compare(KeyRange(2, 5), KeyRange(2, 5)) should be(0)
+    val _ = KeyRange(2, 5) should be <= KeyRange(2, 5)
+    val _ = KeyRange(2, 5) should be >= KeyRange(2, 5)
 
-    KeyRange(2, 5) should be < KeyRange(3, 4)
-    KeyRange(2, 5) should be < KeyRange(2, 6)
-    KeyRange(2, 5) should be > KeyRange(2, 4)
+    val _ = KeyRange(2, 5) should be < KeyRange(3, 4)
+    val _ = KeyRange(2, 5) should be < KeyRange(2, 6)
+    val _ = KeyRange(2, 5) should be > KeyRange(2, 4)
     KeyRange(2, 5) should be > KeyRange(1, 32)
   }
 
   it should "be creatable from a string" in {
-    KeyRange("1-1") should be(KeyRange(0, 0))
-    KeyRange("1..1") should be(KeyRange(0, 0))
-    KeyRange("1") should be(KeyRange(0, 0))
-    KeyRange("1-6") should be(KeyRange(0, 5))
-    KeyRange("1..6") should be(KeyRange(0, 5))
-    an[IllegalArgumentException] should be thrownBy KeyRange("0-5")
-    an[IllegalArgumentException] should be thrownBy KeyRange("-1-5")
+    val _ = KeyRange("1-1") should be(KeyRange(0, 0))
+    val _ = KeyRange("1..1") should be(KeyRange(0, 0))
+    val _ = KeyRange("1") should be(KeyRange(0, 0))
+    val _ = KeyRange("1-6") should be(KeyRange(0, 5))
+    val _ = KeyRange("1..6") should be(KeyRange(0, 5))
+    val _ = an[IllegalArgumentException] should be thrownBy KeyRange("0-5")
+    val _ = an[IllegalArgumentException] should be thrownBy KeyRange("-1-5")
     an[IllegalArgumentException] should be thrownBy KeyRange("6-5")
   }
 

src/test/scala/org/broadinstitute/gpp/poolq3/barcode/TemplatePolicyTest.scala

@@ -113,8 +113,12 @@ class TemplatePolicyTest extends AnyFlatSpec {
     val keymask = KeyMask(pattern)
     val kmp = new GeneralTemplatePolicy(keymask, Some(0))
 
-    kmp.find(Read("", read1)) should be(Some(FoundBarcode("TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT".toCharArray, 5)))
-    kmp.find(Read("", read2)) should be(Some(FoundBarcode("NTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT".toCharArray, 5)))
+    val _ = kmp.find(Read("", read1)) should be(
+      Some(FoundBarcode("TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT".toCharArray, 5))
+    )
+    val _ = kmp.find(Read("", read2)) should be(
+      Some(FoundBarcode("NTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT".toCharArray, 5))
+    )
     kmp.find(Read("", read3)) should be(None)
   }
 
@@ -131,8 +135,8 @@ class TemplatePolicyTest extends AnyFlatSpec {
       (variable: String, r1: String, ns: String, r2: String, rest: String) =>
         val read = Read("id", variable + fixed + prefix1 + r1 + ns + prefix2 + r2 + rest)
         // warm up phase
-        nanoTimed(100)(_ => kmp.find(read))
-        nanoTimed(100)(_ => kpp.find(read))
+        val _ = nanoTimed(100)(_ => kmp.find(read))
+        val _ = nanoTimed(100)(_ => kpp.find(read))
 
         // go!
         val (ret1, t1) = nanoTimed(10000)(_ => kmp.find(read))

src/test/scala/org/broadinstitute/gpp/poolq3/hist/OpenHashMapHistogramTest.scala

@@ -13,17 +13,17 @@ class OpenHashMapHistogramTest extends FunSuite with ScalaCheckSuite {
   test("OpenHashMapHistogram should track frequencies") {
     val h = new OpenHashMapHistogram[String]
 
-    h.increment("AAAA")
-    h.increment("AAAA")
-    h.increment("AAAA")
-    h.increment("AAAA")
+    val _ = h.increment("AAAA")
+    val _ = h.increment("AAAA")
+    val _ = h.increment("AAAA")
+    val _ = h.increment("AAAA")
 
     assertEquals(h.count("AAAA"), 4)
     assertEquals(h.count("CCCC"), 0)
   }
 
   property("OpenHashMapHistogram should track frequencies for arbitrary data") {
-    forAll { data: List[Int] =>
+    forAll { (data: List[Int]) =>
       val expectedCounts: Map[Int, Int] = data.groupBy(identity).view.mapValues(_.length).toMap
 
       val hist = new OpenHashMapHistogram[Int]