diff --git a/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/BamStats.scala b/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/BamStats.scala
index db9164bb5734a6e195fed27ba6695f71336efb32..26e14cc75d6811d82b17eb6f082dc05b49c8eee7 100644
--- a/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/BamStats.scala
+++ b/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/BamStats.scala
@@ -4,7 +4,7 @@ import java.io.File
import java.util.concurrent.TimeoutException
import htsjdk.samtools.reference.FastaSequenceFile
-import htsjdk.samtools.{SAMSequenceDictionary, SamReaderFactory}
+import htsjdk.samtools.{ SAMSequenceDictionary, SamReaderFactory }
import nl.lumc.sasc.biopet.utils.BamUtils.SamDictCheck
import nl.lumc.sasc.biopet.utils.ToolCommand
import nl.lumc.sasc.biopet.utils.intervals.{ BedRecord, BedRecordList }
@@ -13,6 +13,7 @@ import scala.collection.JavaConversions._
import scala.concurrent.ExecutionContext.Implicits.global
import scala.concurrent.duration._
import scala.concurrent.{ Await, Future }
+import scala.language.postfixOps
/**
* This tool will collect stats from a bamfile
@@ -76,14 +77,14 @@ object BamStats extends ToolCommand {
}
/**
- * This is the main running function of [[BamStats]]. This will start the thereads and collect and write the results.
- *
- * @param outputDir All output files will be placed here
- * @param bamFile Input bam file
- * @param referenceDict Dict for scattering
- * @param binSize stats binsize
- * @param threadBinSize Thread binsize
- */
+ * This is the main running function of [[BamStats]]. This will start the thereads and collect and write the results.
+ *
+ * @param outputDir All output files will be placed here
+ * @param bamFile Input bam file
+ * @param referenceDict Dict for scattering
+ * @param binSize stats binsize
+ * @param threadBinSize Thread binsize
+ */
def init(outputDir: File, bamFile: File, referenceDict: SAMSequenceDictionary, binSize: Int, threadBinSize: Int): Unit = {
val contigsFutures = BedRecordList.fromDict(referenceDict).allRecords.map { contig =>
Future { processContig(contig, bamFile, binSize, threadBinSize) }
@@ -105,28 +106,28 @@ object BamStats extends ToolCommand {
}
/**
- * This will start the subjobs for each contig and collect [[Stats]] on contig level
- *
- * @param region Region to check, mostly yhis is the complete contig
- * @param bamFile Input bam file
- * @param binSize stats binsize
- * @param threadBinSize Thread binsize
- * @return Output stats
- */
+ * This will start the subjobs for each contig and collect [[Stats]] on contig level
+ *
+ * @param region Region to check, mostly yhis is the complete contig
+ * @param bamFile Input bam file
+ * @param binSize stats binsize
+ * @param threadBinSize Thread binsize
+ * @return Output stats
+ */
def processContig(region: BedRecord, bamFile: File, binSize: Int, threadBinSize: Int): Stats = {
val scattersFutures = region
.scatter(binSize)
.grouped((region.length.toDouble / threadBinSize).ceil.toInt)
- .map( scatters => Future { processThread(scatters, bamFile) })
+ .map(scatters => Future { processThread(scatters, bamFile) })
waitOnFutures(scattersFutures.toList, Some(region.chr))
}
/**
- * This method will wait when all futures are complete and collect a single [[Stats]] instance
- * @param futures List of futures to monitor
- * @param msg Optional message for logging
- * @return Output stats
- */
+ * This method will wait when all futures are complete and collect a single [[Stats]] instance
+ * @param futures List of futures to monitor
+ * @param msg Optional message for logging
+ * @return Output stats
+ */
def waitOnFutures(futures: List[Future[Stats]], msg: Option[String] = None): Stats = {
msg.foreach(m => logger.info(s"Start monitoring jobs for '$m', ${futures.size} jobs"))
futures.foreach(_.onFailure { case t => throw new RuntimeException(t) })
@@ -148,12 +149,12 @@ object BamStats extends ToolCommand {
}
/**
- * This method will process 1 thread bin
- *
- * @param scatters bins to check
- * @param bamFile Input bamfile
- * @return Output stats
- */
+ * This method will process 1 thread bin
+ *
+ * @param scatters bins to check
+ * @param bamFile Input bamfile
+ * @return Output stats
+ */
def processThread(scatters: List[BedRecord], bamFile: File): Stats = {
val totalStats = Stats()
val sortedScatters = scatters.sortBy(_.start)
@@ -201,10 +202,10 @@ object BamStats extends ToolCommand {
}
/**
- * This method will only count the unmapped fragments
- * @param bamFile Input bamfile
- * @return Output stats
- */
+ * This method will only count the unmapped fragments
+ * @param bamFile Input bamfile
+ * @return Output stats
+ */
def processUnmappedReads(bamFile: File): Stats = {
val stats = Stats()
val samReader = SamReaderFactory.makeDefault().open(bamFile)
diff --git a/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Histogram.scala b/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Histogram.scala
index 67f9bd6cfb7ef0aa3249f33e83977878e8692923..154257842adca51d1da47d988ee2adc29db149d5 100644
--- a/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Histogram.scala
+++ b/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Histogram.scala
@@ -34,6 +34,13 @@ class Counts[T](_counts: Map[T, Long] = Map[T, Long]())(implicit ord: Ordering[T
counts.keys.toList.sorted.foreach(x => writer.println(s"$x\t${counts(x)}"))
writer.close()
}
+
+ override def equals(other: Any): Boolean = {
+ other match {
+ case c: Counts[T] => this.counts == c.counts
+ case _ => false
+ }
+ }
}
class Histogram[T](_counts: Map[T, Long] = Map[T, Long]())(implicit ord: Numeric[T]) extends Counts[T](_counts) {
diff --git a/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Stats.scala b/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Stats.scala
index bf446e2dd6ba0e1a1ea36b8d5c99f39aa1e7a963..cdc8a3f65c6a90ab0e98c2d65d64519d86479d7f 100644
--- a/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Stats.scala
+++ b/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/bamstats/Stats.scala
@@ -3,18 +3,16 @@ package nl.lumc.sasc.biopet.tools.bamstats
/**
* Created by pjvanthof on 05/07/16.
*/
-case class Stats() {
-
- var totalReads = 0L
- var unmapped = 0L
- var secondary = 0L
- val mappingQualityHistogram = new Histogram[Int]()
- val insertSizeHistogram = new Histogram[Int]()
- val clippingHistogram = new Histogram[Int]()
- val leftClippingHistogram = new Histogram[Int]()
- val rightClippingHistogram = new Histogram[Int]()
- val _5_ClippingHistogram = new Histogram[Int]()
- val _3_ClippingHistogram = new Histogram[Int]()
+case class Stats(var totalReads: Long = 0L,
+ var unmapped: Long = 0L,
+ var secondary: Long = 0L,
+ mappingQualityHistogram: Histogram[Int] = new Histogram[Int](),
+ insertSizeHistogram: Histogram[Int] = new Histogram[Int](),
+ clippingHistogram: Histogram[Int] = new Histogram[Int](),
+ leftClippingHistogram: Histogram[Int] = new Histogram[Int](),
+ rightClippingHistogram: Histogram[Int] = new Histogram[Int](),
+ _5_ClippingHistogram: Histogram[Int] = new Histogram[Int](),
+ _3_ClippingHistogram: Histogram[Int] = new Histogram[Int]()) {
/** This will add an other [[Stats]] inside `this` */
def +=(other: Stats): Stats = {
diff --git a/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/CountsTest.scala b/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/CountsTest.scala
index 286abc24573fc6d448445e9241b7a87ae9cd59bf..af79d371ca2a53c97d525b723e745c77a0dd26b9 100644
--- a/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/CountsTest.scala
+++ b/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/CountsTest.scala
@@ -9,12 +9,12 @@ import org.testng.annotations.Test
import scala.io.Source
/**
- * Created by pjvan_thof on 19-7-16.
- */
+ * Created by pjvan_thof on 19-7-16.
+ */
class CountsTest extends TestNGSuite with Matchers {
@Test
- def testValues: Unit = {
- val data: Map[String, Long] = Map("1" -> 1, "2" -> 2, "3" -> 3)
+ def testValues(): Unit = {
+ val data: Map[String, Long] = Map("1" -> 1, "2" -> 2, "3" -> 3)
val c1 = new Counts[String](data)
c1.countsMap shouldBe data
c1.get("1") shouldBe Some(1)
@@ -37,14 +37,36 @@ class CountsTest extends TestNGSuite with Matchers {
}
@Test
- def testEmpty: Unit = {
+ def testEmpty(): Unit = {
val c1 = new Counts[Int]()
c1.countsMap.isEmpty shouldBe true
}
@Test
- def testTsv: Unit = {
- val data: Map[Int, Long] = Map(1 -> 1, 2 -> 2, 3 -> 3)
+ def testEqual(): Unit = {
+ val c1 = new Counts[Int]()
+ val c2 = new Counts[Int]()
+
+ c1 should not be "be a string"
+
+ c1 shouldBe c1
+ c2 shouldBe c2
+ c1 shouldBe c2
+
+ c1.add(1)
+ c1 shouldBe c1
+ c2 shouldBe c2
+ c1 should not be c2
+
+ c2.add(1)
+ c1 shouldBe c1
+ c2 shouldBe c2
+ c1 shouldBe c2
+ }
+
+ @Test
+ def testTsv(): Unit = {
+ val data: Map[Int, Long] = Map(1 -> 1, 2 -> 2, 3 -> 3)
val c1 = new Counts[Int](data)
val tsvFile = File.createTempFile("counts.", ".tsv")
diff --git a/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/HistogramTest.scala b/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/HistogramTest.scala
index 9944821b5db4e4f0a6137f9e7029975a3a2b0767..798cd0c563a2df65979665061b1b4bf02eedaa63 100644
--- a/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/HistogramTest.scala
+++ b/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/HistogramTest.scala
@@ -9,12 +9,12 @@ import org.testng.annotations.Test
import scala.io.Source
/**
- * Created by pjvan_thof on 19-7-16.
- */
+ * Created by pjvan_thof on 19-7-16.
+ */
class HistogramTest extends TestNGSuite with Matchers {
@Test
def testValues: Unit = {
- val data: Map[Int, Long] = Map(1 -> 1, 2 -> 2, 3 -> 3)
+ val data: Map[Int, Long] = Map(1 -> 1, 2 -> 2, 3 -> 3)
val c1 = new Histogram[Int](data)
c1.countsMap shouldBe data
c1.get(1) shouldBe Some(1)
@@ -44,7 +44,7 @@ class HistogramTest extends TestNGSuite with Matchers {
@Test
def testTsv: Unit = {
- val data: Map[Int, Long] = Map(1 -> 1, 2 -> 2, 3 -> 3)
+ val data: Map[Int, Long] = Map(1 -> 1, 2 -> 2, 3 -> 3)
val c1 = new Histogram[Int](data)
val tsvFile = File.createTempFile("counts.", ".tsv")
diff --git a/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/StatsTest.scala b/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/StatsTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..50194795ab3c81003364897257d0ffda4b6c4d8d
--- /dev/null
+++ b/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/bamstats/StatsTest.scala
@@ -0,0 +1,62 @@
+package nl.lumc.sasc.biopet.tools.bamstats
+
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+
+/**
+ * Created by pjvan_thof on 19-7-16.
+ */
+class StatsTest extends TestNGSuite with Matchers {
+ @Test
+ def testEqual(): Unit = {
+ val s1 = new Stats()
+ val s2 = new Stats()
+
+ s1 shouldBe s2
+
+ s1.totalReads += 1
+ s1 should not be s2
+
+ s2.totalReads += 1
+ s1 shouldBe s2
+
+ s1.mappingQualityHistogram.add(1)
+ s1 should not be s2
+
+ s2.mappingQualityHistogram.add(1)
+ s1 shouldBe s2
+ }
+
+ @Test
+ def testEmpty(): Unit = {
+ val stats = new Stats()
+
+ stats.totalReads shouldBe 0
+ stats.unmapped shouldBe 0
+ stats.secondary shouldBe 0
+
+ stats.clippingHistogram.countsMap shouldBe empty
+ stats.insertSizeHistogram.countsMap shouldBe empty
+ stats.mappingQualityHistogram.countsMap shouldBe empty
+ stats.leftClippingHistogram.countsMap shouldBe empty
+ stats.rightClippingHistogram.countsMap shouldBe empty
+ stats._5_ClippingHistogram.countsMap shouldBe empty
+ stats._3_ClippingHistogram.countsMap shouldBe empty
+ }
+
+ @Test
+ def testPlus: Unit = {
+ val s1 = new Stats()
+ val s2 = new Stats()
+
+ s2.totalReads += 1
+ s2._3_ClippingHistogram.add(1)
+
+ s1.totalReads shouldBe 0
+ s1._3_ClippingHistogram.get(1) shouldBe None
+ s1 += s2
+ s1.totalReads shouldBe 1
+ s1._3_ClippingHistogram.get(1) shouldBe Some(1)
+ }
+}