def test_read_reentrant_without_splitting(self):
with TempDir() as tempdir:
file_name = self._create_temp_vcf_file(
_SAMPLE_HEADER_LINES + _SAMPLE_TEXT_LINES, tempdir)
source = VcfSource(file_name)
source_test_utils.assert_reentrant_reads_succeed(
(source, None, None))
def test_dynamic_work_rebalancing(self):
with TempDir() as tempdir:
file_name = self._create_temp_vcf_file(_SAMPLE_HEADER_LINES +
_SAMPLE_TEXT_LINES, tempdir)
source = VcfSource(file_name)
splits = [split for split in source.split(desired_bundle_size=100000)]
assert len(splits) == 1
source_test_utils.assert_split_at_fraction_exhaustive(
splits[0].source, splits[0].start_position, splits[0].stop_position)
def test_read_reentrant_after_splitting(self):
with TempDir() as tempdir:
file_name = self._create_temp_vcf_file(_SAMPLE_HEADER_LINES +
_SAMPLE_TEXT_LINES, tempdir)
source = VcfSource(file_name)
splits = [split for split in source.split(desired_bundle_size=100000)]
assert len(splits) == 1
source_test_utils.assert_reentrant_reads_succeed(
(splits[0].source, splits[0].start_position, splits[0].stop_position))
def test_read_after_splitting(self):
file_name = get_full_file_path('valid-4.1-large.vcf')
source = VcfSource(file_name)
splits = [p for p in source.split(desired_bundle_size=500)]
self.assertGreater(len(splits), 1)
sources_info = ([(split.source, split.start_position,
split.stop_position) for split in splits])
self.assertGreater(len(sources_info), 1)
split_records = []
for source_info in sources_info:
split_records.extend(
source_test_utils.read_from_source(*source_info))
self.assertEqual(9882, len(split_records))
def _read_records(self, file_or_pattern, **kwargs):
return source_test_utils.read_from_source(
VcfSource(file_or_pattern, **kwargs))