Refactor Vcf2ADAM and ADAM2Vcf into TransformGenotypes and TransformV…

…ariants.

README.md

@@ -72,12 +72,12 @@ ADAM ACTIONS
     countContigKmers : Counts the k-mers/q-mers from a read dataset.
  transformAlignments : Convert SAM/BAM to ADAM format and optionally perform read pre-processing transformations
    transformFeatures : Convert a file with sequence features into corresponding ADAM format and vice versa
+  transformGenotypes : Convert a file with genotypes into corresponding ADAM format and vice versa
+   transformVariants : Convert a file with variants into corresponding ADAM format and vice versa
          mergeShards : Merges the shards of a file
       reads2coverage : Calculate the coverage from a given ADAM file
 
 CONVERSION OPERATIONS
-            vcf2adam : Convert a VCF file to the corresponding ADAM format
-            adam2vcf : Convert an ADAM variant to the VCF ADAM format
           fasta2adam : Converts a text FASTA sequence file into an ADAMNucleotideContig Parquet file which represents assembled sequences.
           adam2fasta : Convert ADAM nucleotide contig fragments to FASTA files
           adam2fastq : Convert BAM to FASTQ files

adam-apis/src/test/java/org/bdgenomics/adam/apis/java/JavaADAMGenotypeConduit.java

@@ -34,7 +34,7 @@ public static GenotypeRDD conduit(final GenotypeRDD recordRdd,
         // make temp directory and save file
         Path tempDir = Files.createTempDirectory("javaAC");
         String fileName = tempDir.toString() + "/testRdd.genotype.adam";
-        recordRdd.save(fileName);
+        recordRdd.saveAsParquet(fileName);
 
         // create a new adam context and load the file
         JavaADAMContext jac = new JavaADAMContext(ac);

adam-apis/src/test/java/org/bdgenomics/adam/apis/java/JavaADAMVariantConduit.java

@@ -34,7 +34,7 @@ public static VariantRDD conduit(final VariantRDD recordRdd,
         // make temp directory and save file
         Path tempDir = Files.createTempDirectory("javaAC");
         String fileName = tempDir.toString() + "/testRdd.variant.adam";
-        recordRdd.save(fileName);
+        recordRdd.saveAsParquet(fileName);
 
         // create a new adam context and load the file
         JavaADAMContext jac = new JavaADAMContext(ac);

adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAMMain.scala

@@ -36,15 +36,15 @@ object ADAMMain {
           CountContigKmers,
           TransformAlignments,
           TransformFeatures,
+          TransformGenotypes,
+          TransformVariants,
           MergeShards,
           Reads2Coverage
         )
       ),
       CommandGroup(
         "CONVERSION OPERATIONS",
         List(
-          Vcf2ADAM,
-          ADAM2Vcf,
           Fasta2ADAM,
           ADAM2Fasta,
           ADAM2Fastq,

adam-cli/src/main/scala/org/bdgenomics/adam/cli/TransformGenotypes.scala

@@ -0,0 +1,132 @@
+/**
+ * Licensed to Big Data Genomics (BDG) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The BDG licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.bdgenomics.adam.cli
+
+import htsjdk.samtools.ValidationStringency
+import org.apache.spark.SparkContext
+import org.bdgenomics.adam.rdd.ADAMContext._
+import org.bdgenomics.adam.rdd.{ ADAMSaveAnyArgs, GenomicRDD }
+import org.bdgenomics.utils.cli._
+import org.kohsuke.args4j.{ Argument, Option ⇒ Args4jOption }
+
+object TransformGenotypes extends BDGCommandCompanion {
+  val commandName = "transformGenotypes"
+  val commandDescription = "Convert a file with genotypes into corresponding ADAM format and vice versa"
+
+  def apply(cmdLine: Array[String]) = {
+    new TransformGenotypes(Args4j[TransformGenotypesArgs](cmdLine))
+  }
+}
+
+class TransformGenotypesArgs extends Args4jBase with ADAMSaveAnyArgs with ParquetArgs {
+  @Argument(required = true, metaVar = "INPUT", usage = "The genotypes file to convert (e.g., .vcf, .vcf.gz, .vcf.bgzf, .vcf.bgz). If extension is not detected, Parquet is assumed.", index = 0)
+  var inputPath: String = null
+
+  @Argument(required = true, metaVar = "OUTPUT", usage = "Location to write ADAM genotypes data. If extension is not detected, Parquet is assumed.", index = 1)
+  var outputPath: String = null
+
+  @Args4jOption(required = false, name = "-coalesce", usage = "Number of partitions written to the ADAM output directory.")
+  var coalesce: Int = -1
+
+  @Args4jOption(required = false, name = "-force_shuffle_coalesce", usage = "Even if the repartitioned RDD has fewer partitions, force a shuffle.")
+  var forceShuffle: Boolean = false
+
+  @Args4jOption(required = false, name = "-sort_on_save", usage = "Sort VCF output by contig index.")
+  var sort: Boolean = false
+
+  @Args4jOption(required = false, name = "-sort_lexicographically_on_save", usage = "Sort VCF output by lexicographic order. Conflicts with -sort_on_save.")
+  var sortLexicographically: Boolean = false
+
+  @Args4jOption(required = false, name = "-single", usage = "Save as a single VCF file.")
+  var asSingleFile: Boolean = false
+
+  @Args4jOption(required = false, name = "-defer_merging", usage = "Defers merging single file output.")
+  var deferMerging: Boolean = false
+
+  @Args4jOption(required = false, name = "-disable_fast_concat", usage = "Disables the parallel file concatenation engine.")
+  var disableFastConcat: Boolean = false
+
+  @Args4jOption(required = false, name = "-stringency", usage = "Stringency level for various checks; can be SILENT, LENIENT, or STRICT. Defaults to STRICT.")
+  var stringency: String = "STRICT"
+
+  // must be defined due to ADAMSaveAnyArgs, but unused here
+  var sortFastqOutput: Boolean = false
+}
+
+/**
+ * Convert a file with genotypes into corresponding ADAM format and vice versa.
+ */
+class TransformGenotypes(val args: TransformGenotypesArgs)
+    extends BDGSparkCommand[TransformGenotypesArgs] {
+  val companion = TransformGenotypes
+  val stringency = ValidationStringency.valueOf(args.stringency)
+
+  /**
+   * Coalesce the specified GenomicRDD if requested.
+   *
+   * @param rdd GenomicRDD to coalesce.
+   * @return The specified GenomicRDD coalesced if requested.
+   */
+  private def maybeCoalesce[U <: GenomicRDD[_, U]](rdd: U): U = {
+    if (args.coalesce != -1) {
+      log.info("Coalescing the number of partitions to '%d'".format(args.coalesce))
+      if (args.coalesce > rdd.rdd.partitions.length || args.forceShuffle) {
+        rdd.transform(_.coalesce(args.coalesce, shuffle = true))
+      } else {
+        rdd.transform(_.coalesce(args.coalesce, shuffle = false))
+      }
+    } else {
+      rdd
+    }
+  }
+
+  /**
+   * Sort the specified GenomicRDD if requested.
+   *
+   * @param rdd GenomicRDD to sort.
+   * @return The specified GenomicRDD sorted if requested.
+   */
+  private def maybeSort[U <: GenomicRDD[_, U]](rdd: U): U = {
+    if (args.sort) {
+      log.info("Sorting before saving")
+      rdd.sort()
+    } else if (args.sortLexicographically) {
+      log.info("Sorting lexicographically before saving")
+      rdd.sortLexicographically()
+    } else {
+      rdd
+    }
+  }
+
+  def run(sc: SparkContext) {
+    require(!(args.sort && args.sortLexicographically),
+      "Cannot set both -sort_on_save and -sort_lexicographically_on_save.")
+
+    val genotypes = sc.loadGenotypes(
+      args.inputPath,
+      optPredicate = None,
+      optProjection = None,
+      stringency = stringency)
+
+    if (args.outputPath.endsWith(".vcf")) {
+      maybeSort(maybeCoalesce(genotypes.toVariantContextRDD)).saveAsVcf(args)
+    } else {
+      maybeSort(maybeCoalesce(genotypes)).saveAsParquet(args)
+    }
+  }
+}