def test_convert_variant_to_bigquery_row_omit_empty_calls(self):
variant, row, header_num_dict = self._get_sample_variant_with_empty_calls()
header_fields = vcf_header_util.make_header(header_num_dict)
proc_var = processed_variant.ProcessedVariantFactory(
header_fields).create_processed_variant(variant)
pipeline = TestPipeline(blocking=True)
bigquery_rows = (
pipeline
| Create([proc_var])
| 'ConvertToRow' >> beam.ParDo(ConvertVariantToRow(
self._row_generator, omit_empty_sample_calls=True)))
assert_that(bigquery_rows, equal_to([row]))
pipeline.run()
def test_convert_variant_to_bigquery_row_allow_incompatible_recoreds(self):
variant, row, header_num_dict = (
self._get_sample_variant_with_incompatible_records())
header_fields = vcf_header_util.make_header(header_num_dict)
proc_var = processed_variant.ProcessedVariantFactory(
header_fields).create_processed_variant(variant)
pipeline = TestPipeline(blocking=True)
bigquery_rows = (
pipeline
| Create([proc_var])
| 'ConvertToRow' >> beam.ParDo(
ConvertVariantToRow(self._row_generator,
allow_incompatible_records=True)))
assert_that(bigquery_rows, equal_to([row]))
pipeline.run()
self._row_generator = bigquery_row_generator.VariantCallRowGenerator(
self._schema_descriptor, self._conflict_resolver)
def test_convert_variant_with_sample_name_to_bigquery_row(self):
self._row_generator = bigquery_row_generator.VariantCallRowGenerator(
self._schema_descriptor,
self._conflict_resolver,
include_call_name=True)
variant, row, header_num_dict = self._get_sample_variant_with_sample_name(
)
header_fields = vcf_header_util.make_header(header_num_dict)
proc_var = processed_variant.ProcessedVariantFactory(
header_fields).create_processed_variant(variant)
pipeline = TestPipeline(blocking=True)
bigquery_rows = (
pipeline
| Create([proc_var])
| 'ConvertToRow' >> beam.ParDo(
ConvertVariantToRow(self._row_generator,
omit_empty_sample_calls=True)))
assert_that(bigquery_rows, equal_to([row]))
pipeline.run()
def test_convert_variant_to_bigquery_row(self):
variant_1, row_1, header_num_dict_1 = self._get_sample_variant_1()
variant_2, row_2, header_num_dict_2 = self._get_sample_variant_2()
variant_3, row_3, header_num_dict_3 = self._get_sample_variant_3()
header_num_dict = header_num_dict_1.copy()
header_num_dict.update(header_num_dict_2)
header_num_dict.update(header_num_dict_3)
header_fields = vcf_header_util.make_header(header_num_dict)
proc_var_1 = processed_variant.ProcessedVariantFactory(
header_fields).create_processed_variant(variant_1)
proc_var_2 = processed_variant.ProcessedVariantFactory(
header_fields).create_processed_variant(variant_2)
proc_var_3 = processed_variant.ProcessedVariantFactory(
header_fields).create_processed_variant(variant_3)
pipeline = TestPipeline(blocking=True)
bigquery_rows = (pipeline
| Create([proc_var_1, proc_var_2, proc_var_3])
| 'ConvertToRow' >> beam.ParDo(
ConvertVariantToRow(self._row_generator)))
assert_that(bigquery_rows, equal_to([row_1, row_2, row_3]))
pipeline.run()