def _make_datasets(self):
NameConverter.load()
input_path = PathResolver.input_path()
files = [n.split('/')[-1] for n in glob.glob(input_path + '/*')]
files.sort()
groups = {}
for gid, els in itertools.groupby(files, self._extract_external_name):
groups[gid] = list(els)
for group, files in groups.iteritems():
if not group or len(files) < 3:
continue
file_group = {'reads_1': None, 'reads_2': None, 'contigs': None}
for f in files:
if re.match(DataManager.LEFT_READS_FNAME_REGEXP, f):
file_group['reads_1'] = f
elif re.match(DataManager.RIGHT_READS_FNAME_REGEXP, f):
file_group['reads_2'] = f
elif re.match(DataManager.CONTIGS_FNAME_REGEXP, f):
file_group['contigs'] = f
if not None in file_group.values():
ext_name = self._extract_external_name(file_group['contigs'])
dataset = Dataset(ext_name)
self.datasets.append(dataset)
return self.datasets
def _find_dataset_file(self, file_name, extensions):
path = PathResolver.input_path()
paths = [
glob.glob('%s/%s.%s' % (path, file_name, ext))
for ext in extensions
]
paths = sum(paths, [])
if len(paths) > 0:
return paths[0]
else:
return None