Support validation stringency in out formatters.

bigdatagenomics · Apr 19, 2018 · 4ea7617 · 4ea7617
1 parent 2b4a3d2
commit 4ea7617
Show file tree

Hide file tree

Showing 6 changed files with 21 additions and 11 deletions.
diff --git a/cli/src/main/scala/org/bdgenomics/cannoli/cli/BcftoolsNorm.scala b/cli/src/main/scala/org/bdgenomics/cannoli/cli/BcftoolsNorm.scala
@@ -66,10 +66,12 @@ class BcftoolsNormFnArgs extends Args4jBase {
  * for use in cannoli-shell or notebooks.
  *
  * @param args Bcftools norm function arguments.
+ * @param stringency Validation stringency. Defaults to ValidationStringency.LENIENT.
  * @param sc Spark context.
  */
 class BcftoolsNormFn(
     val args: BcftoolsNormFnArgs,
+    val stringency: ValidationStringency = ValidationStringency.LENIENT,
     sc: SparkContext) extends CannoliFn[VariantContextRDD, VariantContextRDD](sc) with Logging {
 
   override def apply(variantContexts: VariantContextRDD): VariantContextRDD = {
@@ -96,7 +98,7 @@ class BcftoolsNormFn(
       variantContexts, builder.build(), builder.getFiles())
 
     implicit val tFormatter = VCFInFormatter
-    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration)
+    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration, stringency)
 
     variantContexts.pipe[VariantContext, VariantContextProduct, VariantContextRDD, VCFInFormatter](
       cmd = builder.build(),
@@ -149,7 +151,7 @@ class BcftoolsNorm(protected val args: BcftoolsNormArgs) extends BDGSparkCommand
 
   def run(sc: SparkContext) {
     val variantContexts = sc.loadVcf(args.inputPath, stringency = stringency)
-    val pipedVariantContexts = new BcftoolsNormFn(args, sc).apply(variantContexts)
+    val pipedVariantContexts = new BcftoolsNormFn(args, stringency, sc).apply(variantContexts)
     pipedVariantContexts.saveAsVcf(args, stringency)
   }
 }
diff --git a/cli/src/main/scala/org/bdgenomics/cannoli/cli/Freebayes.scala b/cli/src/main/scala/org/bdgenomics/cannoli/cli/Freebayes.scala
@@ -72,10 +72,12 @@ class FreebayesFnArgs extends Args4jBase {
  * for use in cannoli-shell or notebooks.
  *
  * @param args Freebayes function arguments.
+ * @param stringency Validation stringency. Defaults to ValidationStringency.LENIENT.
  * @param sc Spark context.
  */
 class FreebayesFn(
     val args: FreebayesFnArgs,
+    val stringency: ValidationStringency = ValidationStringency.LENIENT,
     sc: SparkContext) extends CannoliFn[AlignmentRecordRDD, VariantContextRDD](sc) with Logging {
 
   override def apply(alignments: AlignmentRecordRDD): VariantContextRDD = {
@@ -110,7 +112,7 @@ class FreebayesFn(
     val accumulator: CollectionAccumulator[VCFHeaderLine] = sc.collectionAccumulator("headerLines")
 
     implicit val tFormatter = BAMInFormatter
-    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration, Some(accumulator))
+    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration, stringency, Some(accumulator))
 
     val variantContexts = alignments.pipe[VariantContext, VariantContextProduct, VariantContextRDD, BAMInFormatter](
       cmd = builder.build(),
@@ -166,7 +168,7 @@ class Freebayes(protected val args: FreebayesArgs) extends BDGSparkCommand[Freeb
 
   def run(sc: SparkContext) {
     val alignments = sc.loadAlignments(args.inputPath, stringency = stringency)
-    val variantContexts = new FreebayesFn(args, sc).apply(alignments)
+    val variantContexts = new FreebayesFn(args, stringency, sc).apply(alignments)
 
     if (isVcfExt(args.outputPath)) {
       variantContexts.saveAsVcf(

diff --git a/cli/src/main/scala/org/bdgenomics/cannoli/cli/SamtoolsMpileup.scala b/cli/src/main/scala/org/bdgenomics/cannoli/cli/SamtoolsMpileup.scala
@@ -64,10 +64,12 @@ class SamtoolsMpileupFnArgs extends Args4jBase {
  * for use in cannoli-shell or notebooks.
  *
  * @param args Samtools mpileup function arguments.
+ * @param stringency Validation stringency. Defaults to ValidationStringency.LENIENT.
  * @param sc Spark context.
  */
 class SamtoolsMpileupFn(
     val args: SamtoolsMpileupFnArgs,
+    val stringency: ValidationStringency = ValidationStringency.LENIENT,
     sc: SparkContext) extends CannoliFn[AlignmentRecordRDD, VariantContextRDD](sc) with Logging {
 
   override def apply(alignments: AlignmentRecordRDD): VariantContextRDD = {
@@ -97,7 +99,7 @@ class SamtoolsMpileupFn(
       alignments, builder.build(), builder.getFiles())
 
     implicit val tFormatter = BAMInFormatter
-    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration)
+    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration, stringency)
 
     alignments.pipe[VariantContext, VariantContextProduct, VariantContextRDD, BAMInFormatter](
       cmd = builder.build(),
@@ -150,7 +152,7 @@ class SamtoolsMpileup(protected val args: SamtoolsMpileupArgs) extends BDGSparkC
 
   def run(sc: SparkContext) {
     val alignments = sc.loadAlignments(args.inputPath, stringency = stringency)
-    val variantContexts = new SamtoolsMpileupFn(args, sc).apply(alignments)
+    val variantContexts = new SamtoolsMpileupFn(args, stringency, sc).apply(alignments)
 
     if (isVcfExt(args.outputPath)) {
       variantContexts.saveAsVcf(

diff --git a/cli/src/main/scala/org/bdgenomics/cannoli/cli/SnpEff.scala b/cli/src/main/scala/org/bdgenomics/cannoli/cli/SnpEff.scala
@@ -62,10 +62,12 @@ class SnpEffFnArgs extends Args4jBase {
  * for use in cannoli-shell or notebooks.
  *
  * @param args SnpEff function arguments.
+ * @param stringency Validation stringency. Defaults to ValidationStringency.LENIENT.
  * @param sc Spark context.
  */
 class SnpEffFn(
     val args: SnpEffFnArgs,
+    val stringency: ValidationStringency = ValidationStringency.LENIENT,
     sc: SparkContext) extends CannoliFn[VariantContextRDD, VariantContextRDD](sc) with Logging {
 
   override def apply(variantContexts: VariantContextRDD): VariantContextRDD = {
@@ -85,7 +87,7 @@ class SnpEffFn(
       variantContexts, builder.build(), builder.getFiles())
 
     implicit val tFormatter = VCFInFormatter
-    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration)
+    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration, stringency)
 
     variantContexts.pipe[VariantContext, VariantContextProduct, VariantContextRDD, VCFInFormatter](
       cmd = builder.build(),
@@ -138,7 +140,7 @@ class SnpEff(protected val args: SnpEffArgs) extends BDGSparkCommand[SnpEffArgs]
 
   def run(sc: SparkContext) {
     val variantContexts = sc.loadVcf(args.inputPath, stringency = stringency)
-    val pipedVariantContexts = new SnpEffFn(args, sc).apply(variantContexts)
+    val pipedVariantContexts = new SnpEffFn(args, stringency, sc).apply(variantContexts)
     pipedVariantContexts.saveAsVcf(args, stringency)
   }
 }
diff --git a/cli/src/main/scala/org/bdgenomics/cannoli/cli/VtNormalize.scala b/cli/src/main/scala/org/bdgenomics/cannoli/cli/VtNormalize.scala
@@ -69,10 +69,12 @@ class VtNormalizeFnArgs extends Args4jBase {
  * for use in cannoli-shell or notebooks.
  *
  * @param args Vt normalize function arguments.
+ * @param stringency Validation stringency. Defaults to ValidationStringency.LENIENT.
  * @param sc Spark context.
  */
 class VtNormalizeFn(
     val args: VtNormalizeFnArgs,
+    val stringency: ValidationStringency = ValidationStringency.LENIENT,
     sc: SparkContext) extends CannoliFn[VariantContextRDD, VariantContextRDD](sc) with Logging {
 
   override def apply(variantContexts: VariantContextRDD): VariantContextRDD = {
@@ -99,7 +101,7 @@ class VtNormalizeFn(
       variantContexts, builder.build(), builder.getFiles())
 
     implicit val tFormatter = VCFInFormatter
-    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration)
+    implicit val uFormatter = new VCFOutFormatter(sc.hadoopConfiguration, stringency)
 
     variantContexts.pipe[VariantContext, VariantContextProduct, VariantContextRDD, VCFInFormatter](
       cmd = builder.build(),
@@ -152,7 +154,7 @@ class VtNormalize(protected val args: VtNormalizeArgs) extends BDGSparkCommand[V
 
   def run(sc: SparkContext) {
     val variantContexts = sc.loadVcf(args.inputPath, stringency = stringency)
-    val pipedVariantContexts = new VtNormalizeFn(args, sc).apply(variantContexts)
+    val pipedVariantContexts = new VtNormalizeFn(args, stringency, sc).apply(variantContexts)
     pipedVariantContexts.saveAsVcf(args, stringency)
   }
 }
diff --git a/pom.xml b/pom.xml
@@ -17,7 +17,7 @@
   <inceptionYear>2017</inceptionYear>
 
   <properties>
-    <adam.version>0.24.0</adam.version>
+    <adam.version>0.25.0-SNAPSHOT</adam.version>
     <scala.version>2.11.12</scala.version>
     <scala.version.prefix>2.11</scala.version.prefix>
     <spark.version>2.2.1</spark.version>