Add asSingleFile, disableFastConcat to adam2fasta/q.

bigdatagenomics · Feb 13, 2018 · 1d7179b · 1d7179b
1 parent 638fd2e
commit 1d7179b
Show file tree

Hide file tree

Showing 2 changed files with 26 additions and 16 deletions.
diff --git a/adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAM2Fasta.scala b/adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAM2Fasta.scala
@@ -21,18 +21,22 @@ import org.apache.spark.SparkContext
 import org.bdgenomics.adam.rdd.ADAMContext._
 import org.bdgenomics.utils.cli._
 import org.bdgenomics.utils.misc.Logging
-import org.kohsuke.args4j.{ Argument, Option => Args4JOption }
+import org.kohsuke.args4j.{ Argument, Option => Args4jOption }
 
 class ADAM2FastaArgs extends Args4jBase {
   @Argument(required = true, metaVar = "ADAM", usage = "The Parquet file to convert", index = 0)
   var inputPath: String = null
   @Argument(required = true, metaVar = "FASTA", usage = "Location to write the FASTA to", index = 1)
   var outputPath: String = null
-  @Args4JOption(required = false, name = "-coalesce", usage = "Choose the number of partitions to coalesce down to.")
+  @Args4jOption(required = false, name = "-single", usage = "Saves FASTA as single file")
+  var asSingleFile: Boolean = false
+  @Args4jOption(required = false, name = "-defer_merging", usage = "Defers merging single file output")
+  var disableFastConcat: Boolean = false
+  @Args4jOption(required = false, name = "-coalesce", usage = "Choose the number of partitions to coalesce down to.")
   var coalesce: Int = -1
-  @Args4JOption(required = false, name = "-force_shuffle_coalesce", usage = "Force shuffle while partitioning, default false.")
+  @Args4jOption(required = false, name = "-force_shuffle_coalesce", usage = "Force shuffle while partitioning, default false.")
   var forceShuffle: Boolean = false
-  @Args4JOption(required = false, name = "-line_width", usage = "Hard wrap FASTA formatted sequence at line width, default 60")
+  @Args4jOption(required = false, name = "-line_width", usage = "Hard wrap FASTA formatted sequence at line width, default 60")
   var lineWidth: Int = 60
 }
 
@@ -64,6 +68,11 @@ class ADAM2Fasta(val args: ADAM2FastaArgs) extends BDGSparkCommand[ADAM2FastaArg
     } else {
       contigs
     }
-    cc.saveAsFasta(args.outputPath, args.lineWidth)
+    cc.saveAsFasta(
+      args.outputPath,
+      args.lineWidth,
+      asSingleFile = args.asSingleFile,
+      disableFastConcat = args.disableFastConcat
+    )
   }
 }
diff --git a/adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAM2Fastq.scala b/adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAM2Fastq.scala
@@ -23,7 +23,7 @@ import org.apache.spark.storage.StorageLevel
 import org.bdgenomics.adam.projections.{ AlignmentRecordField, Projection }
 import org.bdgenomics.adam.rdd.ADAMContext._
 import org.bdgenomics.utils.cli._
-import org.kohsuke.args4j.{ Argument, Option => Args4JOption }
+import org.kohsuke.args4j.{ Argument, Option => Args4jOption }
 
 class ADAM2FastqArgs extends Args4jBase {
   @Argument(required = true, metaVar = "INPUT", usage = "The read file to convert", index = 0)
@@ -32,20 +32,19 @@ class ADAM2FastqArgs extends Args4jBase {
   var outputPath: String = null
   @Argument(required = false, metaVar = "SECOND_OUTPUT", usage = "When writing FASTQ data, all second-in-pair reads will go here, if this argument is provided", index = 2)
   var outputPath2: String = null
-
-  @Args4JOption(required = false, name = "-validation", usage = "SAM tools validation level; when STRICT, checks that all reads are paired.")
+  @Args4jOption(required = false, name = "-single", usage = "Saves OUTPUT and SECOND_OUTPUT as single files")
+  var asSingleFile: Boolean = false
+  @Args4jOption(required = false, name = "-disable_fast_concat", usage = "Disables the parallel file concatenation engine.")
+  var disableFastConcat: Boolean = false
+  @Args4jOption(required = false, name = "-validation", usage = "SAM tools validation level; when STRICT, checks that all reads are paired.")
   var validationStringency = ValidationStringency.LENIENT
-
-  @Args4JOption(required = false, name = "-repartition", usage = "Set the number of partitions to map data to")
+  @Args4jOption(required = false, name = "-repartition", usage = "Set the number of partitions to map data to")
   var repartition: Int = -1
-
-  @Args4JOption(required = false, name = "-persist_level", usage = "Persist() intermediate RDDs")
+  @Args4jOption(required = false, name = "-persist_level", usage = "Persist() intermediate RDDs")
   var persistLevel: String = null
-
-  @Args4JOption(required = false, name = "-no_projection", usage = "Disable projection on records. No great reason to do this, but useful for testing / comparison.")
+  @Args4jOption(required = false, name = "-no_projection", usage = "Disable projection on records. No great reason to do this, but useful for testing / comparison.")
   var disableProjection: Boolean = false
-
-  @Args4JOption(required = false, name = "-output_oq", usage = "Output the original sequencing quality scores")
+  @Args4jOption(required = false, name = "-output_oq", usage = "Output the original sequencing quality scores")
   var outputOriginalBaseQualities = false
 }
 
@@ -86,6 +85,8 @@ class ADAM2Fastq(val args: ADAM2FastqArgs) extends BDGSparkCommand[ADAM2FastqArg
     reads.saveAsFastq(
       args.outputPath,
       Option(args.outputPath2),
+      asSingleFile = args.asSingleFile,
+      disableFastConcat = args.disableFastConcat,
       outputOriginalBaseQualities = args.outputOriginalBaseQualities,
       validationStringency = args.validationStringency,
       persistLevel = Option(args.persistLevel).map(StorageLevel.fromString(_))