def _merge_headers(known_args, pipeline_args, pipeline_mode):
# type: (argparse.Namespace, List[str], int) -> None
"""Merges VCF headers using beam based on pipeline_mode."""
if known_args.representative_header_file:
return
options = pipeline_options.PipelineOptions(pipeline_args)
# Always run pipeline locally if data is small.
if (pipeline_mode == vcf_to_bq_common.PipelineModes.SMALL
and not known_args.infer_headers):
options.view_as(
pipeline_options.StandardOptions).runner = 'DirectRunner'
google_cloud_options = options.view_as(pipeline_options.GoogleCloudOptions)
# Add a time suffix to ensure the job names and the merged headers files are
# unique in case multiple pipelines are run at the same time.
merge_headers_job_name = '-'.join([
_MERGE_HEADERS_JOB_NAME,
datetime.datetime.now().strftime('%Y%m%d-%H%M%S')
])
if google_cloud_options.job_name:
google_cloud_options.job_name += '-' + merge_headers_job_name
else:
google_cloud_options.job_name = merge_headers_job_name
temp_directory = google_cloud_options.temp_location or tempfile.mkdtemp()
temp_merged_headers_file_name = '-'.join(
[google_cloud_options.job_name, _MERGE_HEADERS_FILE_NAME])
temp_merged_headers_file_path = filesystems.FileSystems.join(
temp_directory, temp_merged_headers_file_name)
with beam.Pipeline(options=options) as p:
headers = vcf_to_bq_common.read_headers(p, pipeline_mode, known_args)
merged_header = vcf_to_bq_common.get_merged_headers(
headers, known_args.split_alternate_allele_info_fields,
known_args.allow_incompatible_records)
if known_args.infer_headers or known_args.infer_annotation_types:
merged_header = _add_inferred_headers(p, known_args, merged_header)
vcf_to_bq_common.write_headers(merged_header,
temp_merged_headers_file_path)
known_args.representative_header_file = temp_merged_headers_file_path
def run(argv=None):
# type: (List[str]) -> (str, str)
"""Runs preprocess pipeline."""
logging.info('Command: %s', ' '.join(argv or sys.argv))
known_args, pipeline_args = vcf_to_bq_common.parse_args(
argv, _COMMAND_LINE_OPTIONS)
options = pipeline_options.PipelineOptions(pipeline_args)
pipeline_mode = vcf_to_bq_common.get_pipeline_mode(
known_args.input_pattern)
with beam.Pipeline(options=options) as p:
headers = vcf_to_bq_common.read_headers(p, pipeline_mode, known_args)
merged_headers = vcf_to_bq_common.get_merged_headers(headers)
merged_definitions = (
headers
|
'MergeDefinitions' >> merge_header_definitions.MergeDefinitions())
if known_args.report_all_conflicts:
variants = p | 'ReadFromVcf' >> vcfio.ReadFromVcf(
known_args.input_pattern, allow_malformed_records=True)
malformed_records = variants | filter_variants.ExtractMalformedVariants(
)
inferred_headers, merged_headers = (_get_inferred_headers(
variants, merged_headers))
_ = (merged_definitions
| 'GenerateConflictsReport' >> beam.ParDo(
preprocess_reporter.generate_report,
known_args.report_path,
beam.pvalue.AsSingleton(merged_headers),
beam.pvalue.AsSingleton(inferred_headers),
beam.pvalue.AsIter(malformed_records)))
else:
_ = (merged_definitions
| 'GenerateConflictsReport' >> beam.ParDo(
preprocess_reporter.generate_report,
known_args.report_path,
beam.pvalue.AsSingleton(merged_headers)))
if known_args.resolved_headers_path:
vcf_to_bq_common.write_headers(merged_headers,
known_args.resolved_headers_path)
