Fix up merge conflicts, add forward reference to VariantAnnotation, etc.

bigdatagenomics · Dec 29, 2016 · 9e38f17 · 9e38f17
1 parent 8ed8266
commit 9e38f17
Show file tree

Hide file tree

Showing 10 changed files with 176 additions and 220 deletions.
diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/converters/VariantContextConverter.scala b/adam-core/src/main/scala/org/bdgenomics/adam/converters/VariantContextConverter.scala
diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/ADAMContext.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/ADAMContext.scala
@@ -927,11 +927,8 @@ class ADAMContext(@transient val sc: SparkContext) extends Serializable with Log
     // load vcf metadata
     val (sd, samples, headers) = loadVcfMetadata(filePath)
 
-    val vcc = new VariantContextConverter()
-    val variantContextConvFn = vcc.makeHtsjdkVariantContextConverter(headers)
-    val genotypeConvFn = vcc.makeHtsjdkGenotypeConverter(headers)
-
-    VariantContextRDD(records.flatMap(p => vcc.convert(p._2.get, variantContextConvFn, genotypeConvFn)),
+    val vcc = new VariantContextConverter(headers)
+    VariantContextRDD(records.flatMap(p => vcc.convert(p._2.get, stringency)),
       sd,
       samples,
       cleanAndMixInSupportedLines(headers, stringency))
@@ -971,11 +968,8 @@ class ADAMContext(@transient val sc: SparkContext) extends Serializable with Log
     // load vcf metadata
     val (sd, samples, headers) = loadVcfMetadata(filePath)
 
-    val vcc = new VariantContextConverter()
-    val variantContextConvFn = vcc.makeHtsjdkVariantContextConverter(headers)
-    val genotypeConvFn = vcc.makeHtsjdkGenotypeConverter(headers)
-
-    VariantContextRDD(records.flatMap(p => vcc.convert(p._2.get, variantContextConvFn, genotypeConvFn)),
+    val vcc = new VariantContextConverter(headers)
+    VariantContextRDD(records.flatMap(p => vcc.convert(p._2.get, stringency)),
       sd,
       samples,
       cleanAndMixInSupportedLines(headers, stringency))

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/variant/VCFInFormatter.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/variant/VCFInFormatter.scala
@@ -17,6 +17,7 @@
  */
 package org.bdgenomics.adam.rdd.variant
 
+import htsjdk.samtools.ValidationStringency
 import htsjdk.variant.variantcontext.writer.{
   Options,
   VariantContextWriterBuilder
@@ -58,9 +59,7 @@ private[variant] case class VCFInFormatter private (
   protected val companion = VCFInFormatter
 
   // make a converter
-  val converter = new VariantContextConverter()
-  val variantContextConvFn = converter.makeBdgVariantContextConverter(headerLines)
-  val genotypeConvFn = converter.makeBdgGenotypeConverter(headerLines)
+  val converter = new VariantContextConverter(headerLines)
 
   /**
    * Writes variant contexts to an output stream in VCF format.
@@ -83,7 +82,7 @@ private[variant] case class VCFInFormatter private (
 
     // write the records
     iter.foreach(r => {
-      val optVc = converter.convert(r, variantContextConvFn, genotypeConvFn)
+      val optVc = converter.convert(r, ValidationStringency.LENIENT)
       optVc.foreach(vc => {
         writer.add(vc)
       })

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/variant/VCFOutFormatter.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/variant/VCFOutFormatter.scala
@@ -17,6 +17,7 @@
  */
 package org.bdgenomics.adam.rdd.variant
 
+import htsjdk.samtools.ValidationStringency
 import htsjdk.variant.vcf.{
   VCFCodec,
   VCFHeaderLine
@@ -46,9 +47,7 @@ case class VCFOutFormatter(headerLines: Seq[VCFHeaderLine]) extends OutFormatter
   def read(is: InputStream): Iterator[VariantContext] = {
 
     // make converter and empty dicts
-    val converter = new VariantContextConverter
-    val variantContextConvFn = converter.makeHtsjdkVariantContextConverter(headerLines)
-    val genotypeConvFn = converter.makeHtsjdkGenotypeConverter(headerLines)
+    val converter = new VariantContextConverter(headerLines)
 
     // make line reader iterator
     val lri = new AsciiLineReaderIterator(new AsciiLineReader(is))
@@ -65,7 +64,7 @@ case class VCFOutFormatter(headerLines: Seq[VCFHeaderLine]) extends OutFormatter
         iter.close()
         records.toIterator
       } else {
-        val nextRecords = records ++ converter.convert(codec.decode(iter.next), variantContextConvFn, genotypeConvFn)
+        val nextRecords = records ++ converter.convert(codec.decode(iter.next), ValidationStringency.LENIENT)
         convertIterator(iter, nextRecords)
       }
     }

diff --git a/adam-core/src/main/scala/org/bdgenomics/adam/rdd/variant/VariantContextRDD.scala b/adam-core/src/main/scala/org/bdgenomics/adam/rdd/variant/VariantContextRDD.scala
@@ -113,11 +113,9 @@ case class VariantContextRDD(rdd: RDD[VariantContext],
     val sampleIds = samples.map(_.getSampleId)
 
     // convert the variants to htsjdk VCs
-    val converter = new VariantContextConverter()
-    val variantContextConvFn = converter.makeBdgVariantContextConverter(headerLines)
-    val genotypeConvFn = converter.makeBdgGenotypeConverter(headerLines)
+    val converter = new VariantContextConverter(headerLines)
     val writableVCs: RDD[(LongWritable, VariantContextWritable)] = rdd.flatMap(vc => {
-      converter.convert(vc, variantContextConvFn, genotypeConvFn, stringency = stringency)
+      converter.convert(vc, stringency)
         .map(htsjdkVc => {
           val vcw = new VariantContextWritable
           vcw.set(htsjdkVc)