def test_read_variants_large_mode(self):
pipeline = test_pipeline.TestPipeline()
all_patterns = [testdata_util.get_full_file_path('valid-4.0.vcf')]
variants = pipeline_common.read_variants(pipeline, all_patterns,
PipelineModes.LARGE, False)
assert_that(variants, asserts.count_equals_to(5))
pipeline.run()
def _read_variants(
all_patterns, # type: List[str]
pipeline, # type: beam.Pipeline
known_args, # type: argparse.Namespace
pipeline_mode, # type: int
pre_infer_headers=False, # type: bool
keep_raw_sample_names=False, # type: bool
use_1_based_coordinate=True # type: bool
):
# type: (...) -> pvalue.PCollection
"""Helper method for returning a PCollection of Variants from VCFs."""
representative_header_lines = None
if known_args.representative_header_file:
representative_header_lines = vcf_header_parser.get_metadata_header_lines(
known_args.representative_header_file)
return pipeline_common.read_variants(
pipeline,
all_patterns,
pipeline_mode,
known_args.allow_malformed_records,
representative_header_lines,
pre_infer_headers=pre_infer_headers,
sample_name_encoding=(
SampleNameEncoding.NONE if keep_raw_sample_names else
SampleNameEncoding[known_args.sample_name_encoding]),
use_1_based_coordinate=use_1_based_coordinate)
def test_read_variants_use_1_based_coordinate(self):
pipeline = test_pipeline.TestPipeline()
all_patterns = [testdata_util.get_full_file_path('valid-4.0.vcf')]
variants = pipeline_common.read_variants(pipeline,
all_patterns,
PipelineModes.SMALL,
False,
use_1_based_coordinate=True)
assert_that(variants, asserts.count_equals_to(5))
pipeline.run()
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 = pipeline_common.parse_args(
argv, _COMMAND_LINE_OPTIONS)
options = pipeline_options.PipelineOptions(pipeline_args)
all_patterns = known_args.all_patterns
pipeline_mode = pipeline_common.get_pipeline_mode(all_patterns)
with beam.Pipeline(options=options) as p:
headers = pipeline_common.read_headers(p, pipeline_mode, all_patterns)
merged_headers = pipeline_common.get_merged_headers(headers)
merged_definitions = (
headers
|
'MergeDefinitions' >> merge_header_definitions.MergeDefinitions())
if known_args.report_all_conflicts:
variants = pipeline_common.read_variants(
p,
all_patterns,
pipeline_mode,
allow_malformed_records=True,
pre_infer_headers=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:
pipeline_common.write_headers(merged_headers,
known_args.resolved_headers_path)
def _read_variants(all_patterns, # type: List[str]
pipeline, # type: beam.Pipeline
known_args, # type: argparse.Namespace
pipeline_mode # type: int
):
# type: (...) -> pvalue.PCollection
"""Helper method for returning a PCollection of Variants from VCFs."""
representative_header_lines = None
if known_args.representative_header_file:
representative_header_lines = vcf_header_parser.get_metadata_header_lines(
known_args.representative_header_file)
return pipeline_common.read_variants(
pipeline,
all_patterns,
pipeline_mode,
known_args.allow_malformed_records,
representative_header_lines,
vcfio.VcfParserType[known_args.vcf_parser])
