def test_path_in_filename_is_invalid(self):
self.assertEqual(
[
"Path present in filename: /some/path/PAIR1_1.fastq.gz",
"Path present in filename: /some/path/PAIR1_2.fastq.gz",
],
validate_no_path_in_filename(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='/some/path/PAIR1_1.fastq.gz',
reverse_read='/some/path/PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_T_or_F_is_valid(self):
self.assertEqual([],
check_double_ended_column_is_T_or_F(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='T',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1'),
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='F',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_uniqueness_of_files_sample_and_library_ENA_download(self):
self.assertEqual([],
validate_uniqueness_of_reads(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1',
reverse_read='T',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1'),
RawRead(sample_accession=None,
forward_read='PAIR2',
reverse_read='F',
sample_name='SAMPLE2',
taxon_id="1280",
library_name='LIB2')
])))
def test_forward_read_not_unique(self):
self.assertEqual(["Forward read is not unique: PAIR1_1.fastq.gz"],
validate_uniqueness_of_reads(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1'),
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR2_2.fastq.gz',
sample_name='SAMPLE2',
taxon_id="1280",
library_name='LIB2')
])))
def test_reads_are_not_fastq(self):
self.assertEqual([
"Forward read file is not correctly formatted for RawRead(forward_read='PAIR1_1.gz', "
"reverse_read='PAIR1_2.gz', sample_name='SAMPLE1', sample_accession=None, "
"taxon_id='1280', library_name='LIB1')",
"Reverse read file is not correctly formatted for RawRead(forward_read='PAIR1_1.gz', "
"reverse_read='PAIR1_2.gz', sample_name='SAMPLE1', sample_accession=None, "
"taxon_id='1280', library_name='LIB1')"
],
validate_files_are_compressed(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.gz',
reverse_read='PAIR1_2.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_header_initialization_no_accession(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir,
'test_upload_no_pair_no_lib_no_accession.xls'))
expected = Spreadsheet.new_instance("MyStudy", [
self._raw_read('PAIR1_1.fastq.gz', None, 'SAMPLE1', 'LIB1', None),
self._raw_read('PAIR2_1.fastq.gz', None, 'SAMPLE2', 'LIB2', None)
],
contact="Some Name",
organisation="ENA",
supplier='ENA',
technology='Illumina',
size=123456.0,
accession=None,
limit='30/09/2020')
actual = loader.load_xls()
self.assertSpreadsheet(expected, actual)
def test_no_filename_only_run_accession(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir, 'test_run_accession.xls'))
expected = Spreadsheet.new_instance("MyStudy", [
self._raw_read('PAIR1', 'T', 'SAMPLE1', 'LIB1', 'ACCESSION1'),
self._raw_read('PAIR2', 'T', 'SAMPLE2', 'LIB2', 'ACCESSION2'),
self._raw_read('PAIR3', 'F', 'SAMPLE3', 'LIB3', 'ACCESSION3')
],
contact="Some Name",
organisation="ENA",
supplier='ENA',
technology='Illumina',
size=123456.0,
accession='accession',
limit='30/09/2020')
actual = loader.load_xls()
self.assertSpreadsheet(expected, actual)
def test_sample_and_library_names_as_integers(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir, 'test_sample_name_as_int.xls'))
expected = Spreadsheet.new_instance("AStudyName1", [
self._raw_read('ERR0000001_1.fastq.gz', 'ERR0000001_2.fastq.gz',
'101260', '1000000001', 'ERR0000001', '485'),
self._raw_read('ERR0000002_1.fastq.gz', 'ERR0000002_2.fastq.gz',
'101264', '2000000002', 'ERR0000002', '485')
],
contact="Me",
organisation="Org",
supplier='Supplier',
technology='Illumina',
size=1.90,
accession=None,
limit='01/01/2025')
actual = loader.load_xls()
self.assertSpreadsheet(expected, actual)
def test_cells_read_xlsx(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir, 'test_upload.xlsx'))
expected = Spreadsheet.new_instance("MyStudy", [
self._raw_read('PAIR1_1.fastq.gz', 'PAIR1_2.fastq.gz', 'SAMPLE1',
'LIB1', 'ACCESSION1'),
self._raw_read('PAIR2_1.fastq.gz', 'PAIR2_2.fastq.gz', 'SAMPLE2',
'LIB2', 'ACCESSION2')
],
contact="Some Name",
organisation="ENA",
supplier='ENA',
technology='Illumina',
size=123456.0,
accession='accession',
limit='30/09/2020')
actual = loader.load_xlsx()
self.assertSpreadsheet(expected, actual)
def test_valid_name_for_external_data_part_of_internal_study(self):
self.assertEqual(
[],
validate_external_data_part_of_internal_sequencing_study_name(
Spreadsheet.new_instance("345_external", [])))
def test_supplier_name_with_valid_char_should_pass_validation(self):
self.assertEqual([],
validate_no_abnormal_characters_in_supplier_name(
Spreadsheet.new_instance(
"name", supplier="This should work")))
def test_study_name_with_valid_char_should_pass_validation(self):
self.assertEqual([],
validate_study_name(
Spreadsheet.new_instance("ValidName12345__")))