def test_get_projects(self):
"""Test that getting the projects from a flowcell works
"""
# Assert that an empty file returns an empty list
fh, ssheet = tempfile.mkstemp(dir=self.rootdir, suffix=".csv")
os.close(fh)
self.assertListEqual([],sq.get_projects(ssheet),
"The list of projects for an empty file is not empty")
# Generate artificial samplesheet data
data = td.generate_samplesheet_data()
projects = {}
for d in data:
projects[d[-1]] = 1
# Write the data to a samplesheet
td._write_samplesheet(data,ssheet)
# Assert that the list of projects returned is the same that we generated
self.assertListEqual(sorted(projects.keys()),sorted(sq.get_projects(ssheet)),
"The list of projects does not match the original list")
# Assert that the list of projects returned is filtered as specified
self.assertListEqual([projects.keys()[-1]],sq.get_projects(ssheet,projects.keys()[-1]),
"The filtered list of projects does not match the expected")
def test_get_project_names(self):
"""Get the projects from a samplesheet
"""
# Assert that an empty file returns an empty list
fh, ssheet = tempfile.mkstemp(dir=self.rootdir, suffix=".csv")
os.close(fh)
self.assertListEqual([],HiSeqRun.get_project_names(ssheet),
"The list of projects for an empty file is not empty")
# Generate artificial samplesheet data
data = td.generate_samplesheet_data()
projects = {}
for d in data:
projects[d[-1]] = 1
# Write the data to a samplesheet
td._write_samplesheet(data,ssheet)
# Assert that the list of projects returned is the same that we generated
self.assertListEqual(sorted(projects.keys()),sorted(HiSeqRun.get_project_names(ssheet)),
"The list of projects does not match the original list")
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_fastq_utils_")
# Generate some test fastq_files
indexes = {td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): []}
args = {'instrument': td.generate_instrument(),
'run_number': random.randint(101,9999),
'fcid': td.generate_fc_barcode(),
'lane': 1,
'pair': True}
fd, f1 = tempfile.mkstemp(suffix="_R1.fastq.gz", dir=self.rootdir)
os.close(fd)
f2 = f1.replace("_R1","_R2")
f1h = fu.FastQWriter(f1)
f2h = fu.FastQWriter(f2)
for n in range(1000):
args['index'] = random.choice(indexes.keys())
record = td.generate_fastq_record(**args)
indexes[args['index']].append(record[0])
f1h.write(record[0:4])
f2h.write(record[4:])
f1h.close()
f2h.close()
# Create a samplesheet to use for demultiplexing using all but the last index
samplesheet = f1.replace("_R1.fastq.gz",".csv")
sdata = []
for n, index in enumerate(indexes.keys()[0:-1]):
sdata.append([args['fcid'],
str(args['lane']),
"Sample_{}".format(str(n)),
"unknown",
index,
"DemuxTest",
"0",
"",
"",
"DemuxTestProject"])
# Add an entry that will not match
s = copy.copy(sdata[-1])
s[1] = str(args['lane']+1)
sdata.append(s)
self.samplesheet = td._write_samplesheet(sdata,samplesheet)
self.indexes = indexes
self.fastq_1 = f1
self.fastq_2 = f2
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_fastq_utils_")
# Generate some test fastq_files
indexes = {
td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): []
}
args = {
'instrument': td.generate_instrument(),
'run_number': random.randint(101, 9999),
'fcid': td.generate_fc_barcode(),
'lane': 1,
'pair': True
}
fd, f1 = tempfile.mkstemp(suffix="_R1.fastq.gz", dir=self.rootdir)
os.close(fd)
f2 = f1.replace("_R1", "_R2")
f1h = fu.FastQWriter(f1)
f2h = fu.FastQWriter(f2)
for n in range(1000):
args['index'] = random.choice(indexes.keys())
record = td.generate_fastq_record(**args)
indexes[args['index']].append(record[0])
f1h.write(record[0:4])
f2h.write(record[4:])
f1h.close()
f2h.close()
# Create a samplesheet to use for demultiplexing using all but the last index
samplesheet = f1.replace("_R1.fastq.gz", ".csv")
sdata = []
for n, index in enumerate(indexes.keys()[0:-1]):
sdata.append([
args['fcid'],
str(args['lane']), "Sample_{}".format(str(n)), "unknown",
index, "DemuxTest", "0", "", "", "DemuxTestProject"
])
# Add an entry that will not match
s = copy.copy(sdata[-1])
s[1] = str(args['lane'] + 1)
sdata.append(s)
self.samplesheet = td._write_samplesheet(sdata, samplesheet)
self.indexes = indexes
self.fastq_1 = f1
self.fastq_2 = f2
def test_get_project_samples(self):
"""Test that getting the project samples from a samplesheet behaves as expected
"""
# Generate artificial samplesheet data
data = td.generate_samplesheet_data()
fh, ssheet = tempfile.mkstemp(dir=self.rootdir, suffix=".csv")
os.close(fh)
td._write_samplesheet(data,ssheet)
# Assert that getting samples for a non-existing project returns an empty list
self.assertListEqual([],sq.get_project_samples(ssheet,td.generate_project()),
"Getting samples for a non-existing project returned unexpected output")
# Iterate over the projects and assert that the returned samples are correct
samples = {}
for row in data:
if row[9] not in samples:
samples[row[9]] = []
samples[row[9]].append(row[2])
for proj, sample in samples.items():
self.assertListEqual(sorted(sample),sorted(sq.get_project_samples(ssheet,proj)),
"The returned list of samples did not match the original")
