gistfile1.scala

package edu.berkeley.cs.amplab.adam.cli

import java.io.File;

import edu.berkeley.cs.amplab.adam.models.ADAMVariantContext
import edu.berkeley.cs.amplab.adam.rdd.AdamContext._
import edu.berkeley.cs.amplab.adam.rdd.variation.ADAMVariationContext._
import edu.berkeley.cs.amplab.adam.util.ParquetLogger
import java.util.logging.Level
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.{Logging, SparkContext}
import org.apache.spark.rdd.RDD
import org.kohsuke.args4j.Argument
import edu.berkeley.cs.amplab.adam.converters.VariantContextConverter
import fi.tkk.ics.hadoop.bam.{VariantContextWritable, VCFInputFormat}
import org.apache.hadoop.io.LongWritable
import parquet.hadoop.util.ContextUtil
import org.broadinstitute.variant.variantcontext.VariantContext
import edu.berkeley.cs.amplab.adam.avro._

object TesterJob extends AdamCommandCompanion {

  val commandName = "TesterJob"
  val commandDescription = "Play with corresponding ADAM format"

  def apply(cmdLine: Array[String]) = {
    new TesterJob(Args4j[TesterJobArgs](cmdLine))
  }
}

class TesterJobArgs extends Args4jBase with ParquetArgs with SparkArgs {
  @Argument(required = true, metaVar = "VCF", usage = "The VCF file to convert", index = 0)
  var vcfFile: String = _
  @Argument(required = true, metaVar = "ADAM", usage = "Location to write ADAM Variant data", index = 1)
  var outputPath: String = null
}

class TesterJob(val args: TesterJobArgs) extends AdamSparkCommand[TesterJobArgs] with Logging {
  val companion = TesterJob

  def run(sc: SparkContext, job: Job) {
    log.info("Reading ADAMVCF file from %s".format(args.vcfFile))

    val variants : RDD[ADAMGenotype] = sc.adamLoad(args.vcfFile)
    println(variants.count())
    println(variants.filter(x => x.varIsFiltered != null && x.varIsFiltered == true).count())

  }
}