def test_contigset_consolidate_int_names(self):
# build set to merge
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
inFas = os.path.join(outdir, 'infile.fasta')
outFas1 = os.path.join(outdir, 'tempfile1.fasta')
outFas2 = os.path.join(outdir, 'tempfile2.fasta')
# copy fasta reference to hide fai and ensure FastaReader is used
shutil.copyfile(
ReferenceSet(data.getXml(8)).toExternalFiles()[0], inFas)
rs1 = ContigSet(inFas)
double = 'B.cereus.1'
exp_double = rs1.get_contig(double)
# todo: modify the names first:
with FastaWriter(outFas1) as writer:
writer.writeRecord('5141', exp_double.sequence)
with FastaWriter(outFas2) as writer:
writer.writeRecord('5142', exp_double.sequence)
exp_double_seqs = [exp_double.sequence, exp_double.sequence]
exp_names = ['5141', '5142']
obs_file = ContigSet(outFas1, outFas2)
log.debug(obs_file.toExternalFiles())
obs_file.consolidate()
log.debug(obs_file.toExternalFiles())
# open obs and compare to exp
for name, seq in zip(exp_names, exp_double_seqs):
assert obs_file.get_contig(name).sequence[:] == seq
def test_contigset_consolidate_int_names(self):
#build set to merge
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
inFas = os.path.join(outdir, 'infile.fasta')
outFas1 = os.path.join(outdir, 'tempfile1.fasta')
outFas2 = os.path.join(outdir, 'tempfile2.fasta')
# copy fasta reference to hide fai and ensure FastaReader is used
backticks('cp {i} {o}'.format(
i=ReferenceSet(data.getXml(9)).toExternalFiles()[0],
o=inFas))
rs1 = ContigSet(inFas)
double = 'B.cereus.1'
exp_double = rs1.get_contig(double)
# todo: modify the names first:
with FastaWriter(outFas1) as writer:
writer.writeRecord('5141', exp_double.sequence)
with FastaWriter(outFas2) as writer:
writer.writeRecord('5142', exp_double.sequence)
exp_double_seqs = [exp_double.sequence, exp_double.sequence]
exp_names = ['5141', '5142']
obs_file = ContigSet(outFas1, outFas2)
log.debug(obs_file.toExternalFiles())
obs_file.consolidate()
log.debug(obs_file.toExternalFiles())
# open obs and compare to exp
for name, seq in zip(exp_names, exp_double_seqs):
self.assertEqual(obs_file.get_contig(name).sequence[:], seq)
def test_contigset_consolidate(self):
#build set to merge
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
inFas = os.path.join(outdir, 'infile.fasta')
outFas1 = os.path.join(outdir, 'tempfile1.fasta')
outFas2 = os.path.join(outdir, 'tempfile2.fasta')
# copy fasta reference to hide fai and ensure FastaReader is used
backticks('cp {i} {o}'.format(
i=ReferenceSet(data.getXml(9)).toExternalFiles()[0],
o=inFas))
rs1 = ContigSet(inFas)
singletons = ['A.baumannii.1', 'A.odontolyticus.1']
double = 'B.cereus.1'
reader = rs1.resourceReaders()[0]
exp_double = rs1.get_contig(double)
exp_singles = [rs1.get_contig(name) for name in singletons]
# todo: modify the names first:
with FastaWriter(outFas1) as writer:
writer.writeRecord(exp_singles[0])
writer.writeRecord(exp_double.name + '_10_20', exp_double.sequence)
with FastaWriter(outFas2) as writer:
writer.writeRecord(exp_double.name + '_0_10',
exp_double.sequence + 'ATCGATCGATCG')
writer.writeRecord(exp_singles[1])
exp_double_seq = ''.join([exp_double.sequence,
'ATCGATCGATCG',
exp_double.sequence])
exp_single_seqs = [rec.sequence for rec in exp_singles]
acc_file = ContigSet(outFas1, outFas2)
acc_file.induceIndices()
log.debug(acc_file.toExternalFiles())
self.assertEqual(len(acc_file), 4)
self.assertEqual(len(list(acc_file)), 4)
acc_file.consolidate()
log.debug(acc_file.toExternalFiles())
# open acc and compare to exp
for name, seq in zip(singletons, exp_single_seqs):
self.assertEqual(acc_file.get_contig(name).sequence[:], seq)
self.assertEqual(acc_file.get_contig(double).sequence[:],
exp_double_seq)
self.assertEqual(len(acc_file._openReaders), 1)
self.assertEqual(len(acc_file.index), 3)
self.assertEqual(len(acc_file._indexMap), 3)
self.assertEqual(len(acc_file), 3)
self.assertEqual(len(list(acc_file)), 3)
# test merge:
acc1 = ContigSet(outFas1)
acc2 = ContigSet(outFas2)
acc3 = acc1 + acc2
def test_contigset_consolidate(self):
#build set to merge
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
inFas = os.path.join(outdir, 'infile.fasta')
outFas1 = os.path.join(outdir, 'tempfile1.fasta')
outFas2 = os.path.join(outdir, 'tempfile2.fasta')
# copy fasta reference to hide fai and ensure FastaReader is used
backticks('cp {i} {o}'.format(i=ReferenceSet(
data.getXml(9)).toExternalFiles()[0],
o=inFas))
rs1 = ContigSet(inFas)
singletons = ['A.baumannii.1', 'A.odontolyticus.1']
double = 'B.cereus.1'
reader = rs1.resourceReaders()[0]
exp_double = rs1.get_contig(double)
exp_singles = [rs1.get_contig(name) for name in singletons]
# todo: modify the names first:
with FastaWriter(outFas1) as writer:
writer.writeRecord(exp_singles[0])
writer.writeRecord(exp_double.name + '_10_20', exp_double.sequence)
with FastaWriter(outFas2) as writer:
writer.writeRecord(exp_double.name + '_0_10',
exp_double.sequence + 'ATCGATCGATCG')
writer.writeRecord(exp_singles[1])
exp_double_seq = ''.join(
[exp_double.sequence, 'ATCGATCGATCG', exp_double.sequence])
exp_single_seqs = [rec.sequence for rec in exp_singles]
acc_file = ContigSet(outFas1, outFas2)
acc_file.induceIndices()
log.debug(acc_file.toExternalFiles())
self.assertEqual(len(acc_file), 4)
self.assertEqual(len(list(acc_file)), 4)
acc_file.consolidate()
log.debug(acc_file.toExternalFiles())
# open acc and compare to exp
for name, seq in zip(singletons, exp_single_seqs):
self.assertEqual(acc_file.get_contig(name).sequence[:], seq)
self.assertEqual(
acc_file.get_contig(double).sequence[:], exp_double_seq)
self.assertEqual(len(acc_file._openReaders), 1)
self.assertEqual(len(acc_file.index), 3)
self.assertEqual(len(acc_file._indexMap), 3)
self.assertEqual(len(acc_file), 3)
self.assertEqual(len(list(acc_file)), 3)
# test merge:
acc1 = ContigSet(outFas1)
acc2 = ContigSet(outFas2)
acc3 = acc1 + acc2
def __gather_contigset(resource_file_extension,
input_files,
output_file,
new_resource_file=None,
skip_empty=True):
"""
:param input_files: List of file paths
:param output_file: File Path
:param new_resource_file: the path of the file to which the other contig
files are consolidated
:param skip_empty: Ignore empty files (doesn't do much yet)
:return: Output file
:rtype: str
"""
if skip_empty:
_input_files = []
for file_name in input_files:
cs = ContigSet(file_name)
if len(cs.toExternalFiles()) > 0:
_input_files.append(file_name)
input_files = _input_files
tbr = ContigSet(*input_files)
if not new_resource_file:
if output_file.endswith('xml'):
new_resource_file = output_file[:-3] + resource_file_extension
tbr.consolidate(new_resource_file)
tbr.newUuid()
sanitize_dataset_tags(tbr)
tbr.write(output_file)
return output_file
def __gather_contigset(resource_file_extension, input_files, output_file,
new_resource_file=None,
skip_empty=True):
"""
:param input_files: List of file paths
:param output_file: File Path
:param new_resource_file: the path of the file to which the other contig
files are consolidated
:param skip_empty: Ignore empty files (doesn't do much yet)
:return: Output file
:rtype: str
"""
if skip_empty:
_input_files = []
for file_name in input_files:
cs = ContigSet(file_name)
if len(cs.toExternalFiles()) > 0:
_input_files.append(file_name)
input_files = _input_files
tbr = ContigSet(*input_files)
if not new_resource_file:
if output_file.endswith('xml'):
new_resource_file = output_file[:-3] + resource_file_extension
tbr.consolidate(new_resource_file)
tbr.newUuid()
tbr.write(output_file)
return output_file
def _get_fasta_path(file_name):
if file_name.endswith(".contigset.xml"):
ds = ContigSet(file_name)
fasta_files = ds.toExternalFiles()
assert len(fasta_files) == 1
return fasta_files[0]
return file_name
def _get_fasta_path(file_name):
if file_name.endswith(".contigset.xml"):
ds = ContigSet(file_name)
fasta_files = ds.toExternalFiles()
assert len(fasta_files) == 1
return fasta_files[0]
return file_name
def __gather_contigset(input_files, output_file, new_resource_file):
"""Copied from pbcoretools.chunking.gather:__gather_contigset()
"""
skip_empty = True
if skip_empty:
_input_files = []
for file_name in input_files:
cs = ContigSet(file_name)
if len(cs.toExternalFiles()) > 0:
_input_files.append(file_name)
input_files = _input_files
tbr = ContigSet(*input_files)
tbr.consolidate(new_resource_file)
tbr.newUuid()
tbr.write(output_file, relPaths=True)
return output_file
