org.broadinstitute.hellbender.tools.spark.pipelines.CountReadsSpark Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of gatk Show documentation
Development on GATK 4
The newest version!
package org.broadinstitute.hellbender.tools.spark.pipelines;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.broadinstitute.barclay.argparser.Argument;
import org.broadinstitute.barclay.argparser.CommandLineProgramProperties;
import org.broadinstitute.barclay.help.DocumentedFeature;
import org.broadinstitute.hellbender.cmdline.StandardArgumentDefinitions;
import org.broadinstitute.hellbender.cmdline.programgroups.CoverageAnalysisProgramGroup;
import org.broadinstitute.hellbender.engine.filters.ReadFilter;
import org.broadinstitute.hellbender.engine.filters.ReadFilterLibrary;
import org.broadinstitute.hellbender.engine.spark.GATKSparkTool;
import org.broadinstitute.hellbender.utils.gcs.BucketUtils;
import org.broadinstitute.hellbender.utils.read.GATKRead;

import java.io.PrintStream;
import java.util.Collections;
import java.util.List;

/**
 * Calculate the overall number of reads in a SAM/BAM file
 *
 * Input
 * 
 *     A single BAM file
 * 
 *
 * Output
 * 
 *     A text file containing number of reads
 * 
 *
 * Example
 *
 * Output number of reads to file
 *  *   gatk CountReadsSpark \
 *     -I input_reads.bam \
 *     -O read_count.txt
 * 
 *
 * Print read count
 *  *   gatk CountReadsSpark \
 *     -I input_reads.bam
 * 
 */
@DocumentedFeature
@CommandLineProgramProperties(
        summary = "Counts reads in the input SAM/BAM",
        oneLineSummary = "Counts reads in the input SAM/BAM",
        programGroup = CoverageAnalysisProgramGroup.class
)
public final class CountReadsSpark extends GATKSparkTool {

    private static final long serialVersionUID = 1L;

    @Override
    public boolean requiresReads() { return true; }

    @Argument(
            doc = "uri for the output file: a local file path",
            shortName = StandardArgumentDefinitions.OUTPUT_SHORT_NAME,
            fullName = StandardArgumentDefinitions.OUTPUT_LONG_NAME,
            optional = true
    )
    public String out;

    @Override
    public List getDefaultReadFilters() {
        return Collections.singletonList(ReadFilterLibrary.ALLOW_ALL_READS);
    }

    @Override
    protected void runTool(final JavaSparkContext ctx) {
        final JavaRDD reads = getReads();

        final long count = reads.count();
        System.out.println(count);

        if(out != null) {
            try (final PrintStream ps = new PrintStream(BucketUtils.createFile(out))) {
                ps.print(count);
            }
        }
    }
}