Added more run data

biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala

@@ -88,7 +88,8 @@ trait BiopetQScript extends Configurable with GatkLogging { qscript: QScript =>
       case q: MultiSampleQScript if q.onlySamples.nonEmpty && !q.samples.forall(x => q.onlySamples.contains(x._1)) =>
         logger.info("Write report is skipped because sample flag is used")
       case _ => reportClass.foreach { report =>
-        add(report)
+        //add(report)
+        //FIXEME: Disabled this till implementation of SummaryDb is done
       }
     }
 
@@ -108,6 +109,8 @@ trait BiopetQScript extends Configurable with GatkLogging { qscript: QScript =>
       if (count % 500 == 0) logger.info(s"Preprocessing done for ${count} jobs out of ${functions.length} total")
     }
 
+    logger.info(s"Preprocessing done for  ${functions.length} jobs")
+
     val logDir = new File(outputDir, ".log" + File.separator + qSettings.runName.toLowerCase)
 
     if (outputDir.getParentFile.canWrite || (outputDir.exists && outputDir.canWrite))

biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/summary/SummaryQScript.scala

@@ -14,14 +14,14 @@
  */
 package nl.lumc.sasc.biopet.core.summary
 
-import java.io.{ File, PrintWriter }
+import java.io.{File, PrintWriter}
+import java.sql.Date
 
 import nl.lumc.sasc.biopet.core._
-import nl.lumc.sasc.biopet.core.extensions.{ CheckChecksum, Md5sum }
+import nl.lumc.sasc.biopet.core.extensions.{CheckChecksum, Md5sum}
 import nl.lumc.sasc.biopet.utils.summary.db.SummaryDb
 import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.queue.engine.JobRunInfo
-import org.broadinstitute.gatk.queue.function.QFunction
+import nl.lumc.sasc.biopet.LastCommitHash
 
 import scala.collection.mutable
 import scala.concurrent.Await
@@ -124,7 +124,8 @@ trait SummaryQScript extends BiopetQScript { qscript: QScript =>
       case q: BiopetQScript => q.outputDir
       case _                => throw new IllegalStateException("Root should be a BiopetQscript")
     }
-    val id = Await.result(db.createRun(summaryName, dir.getAbsolutePath), Duration.Inf)
+    val id = Await.result(db.createRun(summaryName, dir.getAbsolutePath, nl.lumc.sasc.biopet.Version,
+      LastCommitHash, new Date(System.currentTimeMillis())), Duration.Inf)
     runIdFile.getParentFile.mkdir()
     val writer = new PrintWriter(runIdFile)
     writer.println(id)

biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/summary/WriteSummary.scala

@@ -253,8 +253,8 @@ class WriteSummary(val parent: SummaryQScript) extends InProcessFunction with Co
     }).foldRight(pipelineMap)((a, b) => ConfigUtils.mergeMaps(a._1, b, a._2))
 
     val combinedMap = //(for (qscript <- qscript.summaryQScripts) yield {
-    //  ConfigUtils.fileToConfigMap(qscript.summaryFile)
-   // }).foldRight(jobsMap)((a, b) => ConfigUtils.mergeMaps(a, b)) ++
+      //  ConfigUtils.fileToConfigMap(qscript.summaryFile)
+      // }).foldRight(jobsMap)((a, b) => ConfigUtils.mergeMaps(a, b)) ++
       jobsMap ++ Map("meta" -> Map(
         "last_commit_hash" -> LastCommitHash,
         "pipeline_version" -> nl.lumc.sasc.biopet.Version,

biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/SummaryToSqlite.scala

-package nl.lumc.sasc.biopet.tools
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.utils.summary.db.SummaryDb
-import nl.lumc.sasc.biopet.utils.{ ConfigUtils, ToolCommand }
-import slick.driver.H2Driver.api._
-
-import scala.concurrent.Await
-import scala.concurrent.duration.Duration
-
-/**
- * Created by pjvanthof on 26/01/2017.
- */
-object SummaryToSqlite extends ToolCommand {
-
-  case class Args(inputJson: File = null,
-                  outputSqlite: File = null,
-                  force: Boolean = false) extends AbstractArgs
-
-  class OptParser extends AbstractOptParser {
-    opt[File]('I', "inputJson") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
-      c.copy(inputJson = x)
-    } text "Input json file"
-    opt[File]('o', "outputHdf5") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
-      c.copy(outputSqlite = x)
-    } text "Output hdf5 file"
-    opt[Unit]('f', "force") action { (x, c) =>
-      c.copy(force = true)
-    } text "If database already exist it will be moved"
-  }
-
-  def main(args: Array[String]): Unit = {
-    val argsParser = new OptParser
-    val cmdArgs = argsParser.parse(args, Args()) getOrElse (throw new IllegalArgumentException)
-    logger.info("Start")
-
-    val jsonMap = ConfigUtils.fileToConfigMap(cmdArgs.inputJson)
-
-    if (cmdArgs.outputSqlite.exists()) {
-      if (cmdArgs.force) {
-        logger.warn("Deleting old database")
-        cmdArgs.outputSqlite.delete()
-      } else throw new IllegalArgumentException(s"Db already exist: ${cmdArgs.outputSqlite}")
-    }
-
-    val db = Database.forURL(s"jdbc:sqlite:${cmdArgs.outputSqlite.getAbsolutePath}", driver = "org.sqlite.JDBC")
-
-    val summary = new SummaryDb(db)
-    summary.createTables
-    val runId = Await.result(summary.createRun("runName", "kdfhla"), Duration.Inf)
-
-    val runs = Await.result(summary.getRuns(), Duration.Inf)
-
-    List("1", "2", "3", "4").foreach(x => Await.result(summary.createSample(x, runId, Some("""{"father": "blabla"}""")), Duration.Inf))
-
-    println(Await.result(summary.getSamples(), Duration.Inf))
-
-    println(Await.result(summary.getSampleTags(1), Duration.Inf))
-
-    Await.result(summary.createLibrary("lib1", runId, 1), Duration.Inf)
-
-    println(Await.result(summary.getLibraries(), Duration.Inf))
-
-    val pipelineId = Await.result(summary.forceCreatePipeline("pipelineName", runId), Duration.Inf)
-
-    println(Await.result(summary.getPipelines(), Duration.Inf))
-
-    Await.result(summary.createStat(runId, pipelineId, None, None, None, """{"bla": "bla"}"""), Duration.Inf)
-
-    println(Await.result(summary.getStats(runId = Some(runId), pipelineId = Some(pipelineId), sampleId = Option(None)), Duration.Inf))
-
-    println(Await.result(summary.getStat(0, 0), Duration.Inf))
-
-    db.close()
-
-    logger.info("Done")
-  }
-
-}

biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/summary/db/Schema.scala

 package nl.lumc.sasc.biopet.utils.summary.db
 
+import java.sql.Date
+
 import slick.driver.H2Driver.api._
 
 /**
@@ -7,13 +9,17 @@ import slick.driver.H2Driver.api._
  */
 object Schema {
 
-  case class Run(id: Int, name: String, outputDir: String)
+  case class Run(id: Int, name: String, outputDir: String, version: String, commitHash: String,
+                 creationDate: Date)
   class Runs(tag: Tag) extends Table[Run](tag, "Runs") {
     def id = column[Int]("id", O.PrimaryKey)
     def runName = column[String]("runName")
     def outputDir = column[String]("outputDir")
+    def version = column[String]("version")
+    def commitHash = column[String]("commitHash")
+    def creationDate = column[Date]("creationDate")
 
-    def * = (id, runName, outputDir) <> (Run.tupled, Run.unapply)
+    def * = (id, runName, outputDir, version, commitHash, creationDate) <> (Run.tupled, Run.unapply)
   }
   val runs = TableQuery[Runs]
 

biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/summary/db/SummaryDb.scala

@@ -6,9 +6,9 @@ import slick.driver.H2Driver.api._
 
 import scala.concurrent.ExecutionContext.Implicits.global
 import scala.concurrent.duration.Duration
-import scala.concurrent.{ Await, Future }
-
-import java.io.{ Closeable, File }
+import scala.concurrent.{Await, Future}
+import java.io.{Closeable, File}
+import java.sql.Date
 
 /**
  * This class interface wityh a summary database
@@ -34,9 +34,10 @@ class SummaryDb(db: Database) extends Closeable {
   }
 
   /** This method will create a new run and return the runId */
-  def createRun(runName: String, outputDir: String): Future[Int] = {
+  def createRun(runName: String, outputDir: String, version: String, commitHash: String,
+                creationDate: Date): Future[Int] = {
     val id = Await.result(db.run(runs.size.result), Duration.Inf)
-    db.run(runs.forceInsert(Run(id, runName, outputDir))).map(_ => id)
+    db.run(runs.forceInsert(Run(id, runName, outputDir, version, commitHash, creationDate))).map(_ => id)
   }
 
   /** This will return all runs that match the critiria given */