Examples with SAMRecordWritable org.seqdoop.hadoop_bam.SAMRecordWritable used on opensource projects

Example 1 with SAMRecordWritable

use of org.seqdoop.hadoop_bam.SAMRecordWritable in project gatk by broadinstitute.

the class ReadsSparkSource method getParallelReads.

/**
     * Loads Reads using Hadoop-BAM. For local files, bam must have the fully-qualified path,
     * i.e., file:///path/to/bam.bam.
     * @param readFileName file to load
     * @param referencePath Reference path or null if not available. Reference is required for CRAM files.
     * @param intervals intervals of reads to include. If <code>null</code> then all the reads (both mapped and unmapped) will be returned.
     * @param splitSize maximum bytes of bam file to read into a single partition, increasing this will result in fewer partitions. A value of zero means
     *                  use the default split size (determined by the Hadoop input format, typically the size of one HDFS block).
     * @return RDD of (SAMRecord-backed) GATKReads from the file.
     */
public JavaRDD<GATKRead> getParallelReads(final String readFileName, final String referencePath, final List<SimpleInterval> intervals, final long splitSize) {
    SAMFileHeader header = getHeader(readFileName, referencePath);
    // use the Hadoop configuration attached to the Spark context to maintain cumulative settings
    final Configuration conf = ctx.hadoopConfiguration();
    if (splitSize > 0) {
        conf.set("mapreduce.input.fileinputformat.split.maxsize", Long.toString(splitSize));
    }
    final JavaPairRDD<LongWritable, SAMRecordWritable> rdd2;
    setHadoopBAMConfigurationProperties(readFileName, referencePath);
    boolean isBam = IOUtils.isBamFileName(readFileName);
    if (isBam && intervals != null && !intervals.isEmpty()) {
        BAMInputFormat.setIntervals(conf, intervals);
    } else {
        conf.unset(BAMInputFormat.INTERVALS_PROPERTY);
    }
    rdd2 = ctx.newAPIHadoopFile(readFileName, AnySAMInputFormat.class, LongWritable.class, SAMRecordWritable.class, conf);
    JavaRDD<GATKRead> reads = rdd2.map(v1 -> {
        SAMRecord sam = v1._2().get();
        if (isBam || samRecordOverlaps(sam, intervals)) {
            return (GATKRead) SAMRecordToGATKReadAdapter.headerlessReadAdapter(sam);
        }
        return null;
    }).filter(v1 -> v1 != null);
    return putPairsInSamePartition(header, reads);
}