def test_fastq_to_generator_invalid_files_all_variants(self):
# files that should be invalid for all variants, as well as custom
# phred offsets
for fp, error_type, error_msg_regex in self.invalid_files:
for variant in 'sanger', 'illumina1.3', 'illumina1.8':
with six.assertRaisesRegex(self, error_type, error_msg_regex):
list(_fastq_to_generator(fp, variant=variant))
for offset in 33, 64, 40, 77:
with six.assertRaisesRegex(self, error_type, error_msg_regex):
list(_fastq_to_generator(fp, phred_offset=offset))
def test_fastq_to_generator_invalid_files_illumina(self):
# files that should be invalid for illumina1.3 and illumina1.8 variants
fps = [get_data_path(fp) for fp in
['sanger_full_range_original_sanger.fastq',
'solexa_full_range_original_solexa.fastq']]
for fp in fps:
with self.assertRaisesRegex(ValueError, 'out of range \[0, 62\]'):
list(_fastq_to_generator(fp, variant='illumina1.3'))
with self.assertRaisesRegex(ValueError, 'out of range \[0, 62\]'):
list(_fastq_to_generator(fp, variant='illumina1.8'))
def test_fastq_to_generator_solexa(self):
# solexa support isn't implemented yet. should raise error even with
# valid solexa file
with self.assertRaises(NotImplementedError):
list(_fastq_to_generator(
get_data_path('solexa_full_range_original_solexa.fastq'),
variant='solexa'))
def test_fastq_to_generator_valid_files(self):
for valid_files, kwargs, components in self.valid_configurations:
for valid in valid_files:
for observed_kwargs in kwargs:
_drop_kwargs(observed_kwargs, 'seq_num')
constructor = observed_kwargs.get('constructor', Sequence)
# Can't use partials for this because the read
# function below can't operate on partials
expected_kwargs = {}
if hasattr(constructor, 'lowercase'):
expected_kwargs['lowercase'] = 'introns'
observed_kwargs['lowercase'] = 'introns'
expected = [constructor(c[2],
metadata={'id': c[0],
'description': c[1]},
positional_metadata={'quality': np.array(c[3],
dtype=np.uint8)},
**expected_kwargs)
for c in components]
observed = list(_fastq_to_generator(valid,
**observed_kwargs))
self.assertEqual(len(expected), len(observed))
for o, e in zip(observed, expected):
self.assertEqual(o, e)
def test_conversion(self):
for from_fp, to_fp, kwargs in self.conversions:
for from_kwargs, to_kwargs in kwargs:
read_gen = _fastq_to_generator(from_fp, **from_kwargs)
fh = io.StringIO()
# will issue warning when truncating quality scores
with warnings.catch_warnings(record=True):
warnings.simplefilter("ignore")
_generator_to_fastq(read_gen, fh, **to_kwargs)
obs = fh.getvalue()
fh.close()
with io.open(to_fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_fastq_to_generator_valid_files(self):
for valid_files, kwargs, components in self.valid_configurations:
for valid in valid_files:
for observed_kwargs in kwargs:
_drop_kwargs(observed_kwargs, 'seq_num')
constructor = observed_kwargs.get('constructor', Sequence)
expected_kwargs = {}
expected_kwargs['lowercase'] = 'introns'
observed_kwargs['lowercase'] = 'introns'
expected = [constructor(c[2],
metadata={'id': c[0],
'description': c[1]},
positional_metadata={'quality': np.array(c[3],
dtype=np.uint8)},
**expected_kwargs)
for c in components]
observed = list(_fastq_to_generator(valid,
**observed_kwargs))
self.assertEqual(len(expected), len(observed))
for o, e in zip(observed, expected):
self.assertEqual(o, e)
