def test_extra_field():
samplesheet = samplesheet_csv_to_samplegroup(
FILESDIR / Path("extra_fields.csv"))
assert samplesheet[0].additional_properties["extra_field1"] == "xf1"
assert samplesheet[0].additional_properties["extra_field2"] == "xf2"
assert samplesheet[1].additional_properties["extra_field1"] == "xfI"
assert samplesheet[1].additional_properties["extra_field2"] is None
def test_samplesheet_to_old_style_json():
output = samplesheet_to_json(COMPLETE_CSV,
old_style_json=True,
file_presence_check=False)
correct_output = output_conversions.samplegroup_to_biowdl_old_json(
input_conversions.samplesheet_csv_to_samplegroup(COMPLETE_CSV))
assert output == correct_output
def test_main(correct_md5sum_samplesheet, capsys):
sys.argv = [
"biowdl-input-converter", "--check-file-md5sums",
str(correct_md5sum_samplesheet)
]
biowdl_input_converter.main()
stdout = capsys.readouterr().out
correct_output = output_conversions.samplegroup_to_biowdl_new_json(
input_conversions.samplesheet_csv_to_samplegroup(
correct_md5sum_samplesheet)) + '\n'
assert stdout == correct_output
def test_main_output_file(correct_md5sum_samplesheet):
output_file = Path(tempfile.mkstemp()[1])
sys.argv = [
"biowdl-input-converter", "--check-file-md5sums", "-o",
str(output_file),
str(correct_md5sum_samplesheet)
]
biowdl_input_converter.main()
output_contents = output_file.read_text()
correct_output = output_conversions.samplegroup_to_biowdl_new_json(
input_conversions.samplesheet_csv_to_samplegroup(
correct_md5sum_samplesheet)) + '\n'
assert output_contents == correct_output
os.remove(str(output_file))
def test_no_optional_fields():
samplesheet = samplesheet_csv_to_samplegroup(
FILESDIR / Path("no_optional_fields.csv"))
assert samplesheet[0].id == "s1"
assert samplesheet[0].libraries[0].id == "lib1"
assert samplesheet[0].libraries[0].readgroups[0].id == "rg1"
assert samplesheet[0].libraries[0].readgroups[0].R1 == "r1.fq"
assert samplesheet[0].libraries[0].readgroups[0].R1_md5 is None
assert samplesheet[0].libraries[0].readgroups[0].R2 is None
assert samplesheet[0].libraries[0].readgroups[0].R2_md5 is None
assert samplesheet[0].libraries[0].readgroups[0].additional_properties == {} # noqa: E501
assert samplesheet[1].id == "s2"
assert samplesheet[1].libraries[0].id == "lib1"
assert samplesheet[1].libraries[0].readgroups[0].id == "rg1"
assert samplesheet[1].libraries[0].readgroups[0].R1 == "r1.fq"
assert samplesheet[1].libraries[0].readgroups[0].R1_md5 is None
assert samplesheet[1].libraries[0].readgroups[0].R2 is None
assert samplesheet[1].libraries[0].readgroups[0].R2_md5 is None
assert samplesheet[1].libraries[0].readgroups[0].additional_properties == {} # noqa: E501
def test_conflicting_properties():
with pytest.raises(ValueError) as error:
samplesheet_csv_to_samplegroup(
FILESDIR / Path("conflicting_properties.csv")
)
error.match("Conflicting fields in column 'extra_field1' for sample 's1'")
def test_mixed_empty_and_filled_additional_properties():
samplesheet = samplesheet_csv_to_samplegroup(
FILESDIR / Path("mixed_empty_filled_addprops.csv"))
assert len(samplesheet.samples) == 1
assert samplesheet[0].additional_properties["extra_field2"] == "xf2"
def test_main_missing_field():
with pytest.raises(KeyError) as e:
samplesheet_csv_to_samplegroup(
FILESDIR / Path("missing_field.csv"))
assert e.match("sample")
def test_main_tab_without_readgroup():
with (FILESDIR / Path("without_readgroup.yml")).open() as f:
result = f.read()
samplegroup = samplesheet_csv_to_samplegroup(
FILESDIR / Path("without_readgroup.tsv"))
assert samplegroup_to_biowdl_old_yaml(samplegroup) == result
def test_main_semicolon_without_md5():
with (FILESDIR / Path("without_md5.yml")).open() as f:
result = f.read()
samplegroup = samplesheet_csv_to_samplegroup(
FILESDIR / Path("without_md5.csv"))
assert samplegroup_to_biowdl_old_yaml(samplegroup) == result
def test_main_comma_complete():
with (FILESDIR / Path("complete.yml")).open() as f:
result = f.read()
samplegroup = samplesheet_csv_to_samplegroup(
FILESDIR / Path("complete.csv"))
assert samplegroup_to_biowdl_old_yaml(samplegroup) == result
def test_duplicate_readgroup():
with pytest.raises(ValueError) as error:
samplesheet_csv_to_samplegroup(
FILESDIR / Path("duplicate_readgroup.csv"))
assert error.match("Duplicate readgroup id s2-lib1-rg1")
def test_samplesheet_to_json_no_checks():
output = samplesheet_to_json(COMPLETE_CSV, file_presence_check=False)
correct_output = output_conversions.samplegroup_to_biowdl_new_json(
input_conversions.samplesheet_csv_to_samplegroup(COMPLETE_CSV))
assert output == correct_output
