@Override
public void processElement(ProcessContext c) throws Exception {
String dest = c.element();
logger.info("Saving to " + dest);
Iterable<GATKRead> reads = c.sideInput(iterableView);
OutputStream outputStream = BucketUtils.createFile(dest, c.getPipelineOptions());
try (SAMFileWriter writer =
new SAMFileWriterFactory().makeBAMWriter(header, false, outputStream)) {
for (GATKRead r : reads) {
final SAMRecord sr = r.convertToSAMRecord(header);
writer.addAlignment(sr);
}
}
}
/**
* Takes a few Reads and will write them to a BAM file. The Reads don't have to be sorted
* initially, the BAM file will be. All the reads must fit into a single worker's memory, so this
* won't go well if you have too many.
*
* @param pipeline the pipeline to add this operation to.
* @param reads the reads to write (they don't need to be sorted).
* @param header the header that corresponds to the reads.
* @param destPath the GCS or local path to write to (must start with "gs://" if writing to GCS).
* @param parquet whether to write out BAM or Parquet data (BDG AlignmentRecords); only applies
* when writing to Hadoop
*/
public static void writeToFile(
Pipeline pipeline,
PCollection<GATKRead> reads,
final SAMFileHeader header,
final String destPath,
final boolean parquet) {
if (BucketUtils.isHadoopUrl(destPath)
|| pipeline.getRunner().getClass().equals(SparkPipelineRunner.class)) {
writeToHadoop(pipeline, reads, header, destPath, parquet);
} else {
PCollectionView<Iterable<GATKRead>> iterableView = reads.apply(View.<GATKRead>asIterable());
PCollection<String> dummy = pipeline.apply("output file name", Create.<String>of(destPath));
dummy.apply(
ParDo.named("save to BAM file")
.withSideInputs(iterableView)
.of(new SaveToBAMFile(header, iterableView)));
}
}