def run_mem_estimator(self, ctx, params):
"""
This is a local function that estimates how much memory SPAdes or metaSPAdes needs
to assemble a paired end library.
Returns a float, representing the estimated memory use in GB.
:param params: instance of type "MemEstimatorParams" (reads_file -
path to a paired end reads file. If this is here alone, expect it
to be interleaved. reads_file2 - path to the pair of the first
file.) -> structure: parameter "reads_file" of String, parameter
"reads_file2" of String
:returns: instance of type "MemEstimatorOutput" (estimate - the
estimated amount of memory required to assemble the paired end
files, in GB.) -> structure: parameter "estimate" of Double
"""
# ctx is the context object
# return variables are: output
#BEGIN run_mem_estimator
runner = MemEstimatorRunner(params)
output = runner.run()
#END run_mem_estimator
# At some point might do deeper type checking...
if not isinstance(output, dict):
raise ValueError('Method run_mem_estimator return value ' +
'output is not type dict as required.')
# return the results
return [output]
def test_mem_estimator_ok_unit(self):
in_file = os.path.join('data', 'reads', 'interleaved.fastq')
params = {"reads_file": in_file}
runner = MemEstimatorRunner(params)
estimate = runner.run()
self.assertGreater(estimate["estimate"], 0)
self.assertGreater(estimate["size"], 0)
def test_mem_estimator_ok_pair(self):
params = {
"reads_file": os.path.join('data', 'reads', 'small.forward.fq'),
"reads_file2": os.path.join('data', 'reads', 'small.reverse.fq')
}
runner = MemEstimatorRunner(params)
estimate = runner.run()
self.assertGreater(estimate["estimate"], 0)
self.assertGreater(estimate["size"], 0)
def test_mem_estimator_pair_dups(self):
in_file = os.path.join('data', 'reads', 'interleaved.fastq')
params = {"reads_file": in_file, "reads_file2": in_file}
with self.assertRaises(ValueError) as e:
MemEstimatorRunner(params)
self.assertIn("If two files are present, they must be different.",
str(e.exception))
def test_bad_inputs(self):
impl = self.getImpl()
ctx = self.getContext()
with self.assertRaises(ValueError) as e:
MemEstimatorRunner({})
self.assertIn('Parameter "reads_file" must be present!',
str(e.exception))
with self.assertRaises(ValueError) as e:
impl.run_mem_estimator(ctx, {"reads_file": "not_real"})
self.assertIn(
"The file not_real does not seem to exist, or is a directory",
str(e.exception))
with self.assertRaises(ValueError) as e:
impl.run_mem_estimator(
ctx, {
"reads_file":
os.path.join('data', 'reads', 'interleaved.fastq'),
"reads_file2":
"not_real2"
})
self.assertIn(
"The file not_real2 does not seem to exist, or is a directory",
str(e.exception))
def test_mem_estimator_bad_file(self):
in_file = os.path.join('data', 'reads', 'bad_reads.txt')
params = {"reads_file": in_file}
with self.assertRaises(ValueError) as e:
MemEstimatorRunner(params).run()
self.assertIn("Count of unique 31-mers not found.", str(e.exception))
self.assertNotIn("31-mers processed", str(e.exception))
self.assertNotIn("Correct 31-mers", str(e.exception))
self.assertNotIn("Unique 31-mers", str(e.exception))