def test_insert_preprocessed_data(self):
study = Study(1)
params = PreprocessedIlluminaParams(1)
prep_template = PrepTemplate(1)
prep_out_dir = mkdtemp()
self.dirs_to_remove.append(prep_out_dir)
path_builder = partial(join, prep_out_dir)
db_path_builder = partial(join, join(self.db_dir, "preprocessed_data"))
file_suffixes = [
'seqs.fna', 'seqs.fastq', 'seqs.demux', 'split_library_log.txt'
]
db_files = []
for f_suff in file_suffixes:
fp = path_builder(f_suff)
with open(fp, 'w') as f:
f.write("\n")
self.files_to_remove.append(fp)
db_files.append(db_path_builder("3_%s" % f_suff))
self.files_to_remove.extend(db_files)
_insert_preprocessed_data(study, params, prep_template, prep_out_dir)
# Check that the files have been copied
for fp in db_files:
self.assertTrue(exists(fp))
# Check that a new preprocessed data has been created
self.assertTrue(
self.conn_handler.execute_fetchone(
"SELECT EXISTS(SELECT * FROM qiita.preprocessed_data WHERE "
"preprocessed_data_id=%s)", (3, ))[0])
def test_get_preprocess_fastq_cmd(self):
raw_data = RawData(1)
params = PreprocessedIlluminaParams(1)
prep_template = PrepTemplate(1)
obs_cmd, obs_output_dir = _get_preprocess_fastq_cmd(
raw_data, prep_template, params)
get_raw_path = partial(join, self.db_dir, 'raw_data')
seqs_fp = get_raw_path('1_s_G1_L001_sequences.fastq.gz')
bc_fp = get_raw_path('1_s_G1_L001_sequences_barcodes.fastq.gz')
exp_cmd_1 = ("split_libraries_fastq.py --store_demultiplexed_fastq -i "
"{} -b {} "
"-m ".format(seqs_fp, bc_fp))
exp_cmd_2 = ("-o {0} --barcode_type golay_12 --max_bad_run_length 3 "
"--max_barcode_errors 1.5 "
"--min_per_read_length_fraction 0.75 "
"--phred_quality_threshold 3 "
"--sequence_max_n 0".format(obs_output_dir))
# We are splitting the command into two parts because there is no way
# that we can know the filepath of the mapping file. We thus split the
# command on the mapping file path and we check that the two parts
# of the commands is correct
obs_cmd_1 = obs_cmd[:len(exp_cmd_1)]
obs_cmd_2 = obs_cmd[len(exp_cmd_1):].split(" ", 1)[1]
self.assertEqual(obs_cmd_1, exp_cmd_1)
self.assertEqual(obs_cmd_2, exp_cmd_2)
def test_to_str(self):
params = PreprocessedIlluminaParams(1)
obs = params.to_str()
exp = ("--barcode_type golay_12 --max_bad_run_length 3 "
"--max_barcode_errors 1.5 --min_per_read_length_fraction 0.75 "
"--phred_quality_threshold 3 --sequence_max_n 0")
self.assertEqual(obs, exp)
def test_values(self):
obs = PreprocessedIlluminaParams(1).values
exp = {'max_barcode_errors': 1.5, 'sequence_max_n': 0,
'max_bad_run_length': 3, 'rev_comp': False,
'phred_quality_threshold': 3, 'rev_comp_barcode': False,
'rev_comp_mapping_barcodes': False,
'min_per_read_length_fraction': 0.75,
'barcode_type': 'golay_12'}
self.assertEqual(obs, exp)
def test_name(self):
obs = PreprocessedIlluminaParams(1).name
self.assertEqual(obs, "Defaults")
def test_iter(self):
obs = list(PreprocessedIlluminaParams.iter())
exp = [PreprocessedIlluminaParams(1)]
for o, e in zip(obs, exp):
self.assertEqual(o.id, e.id)
