def process(self):
# Reduce inputs to only first element
if hasattr(self.input_dir, '__iter__'):
self.input_dir = self.input_dir[0]
self.input_dir = os.path.join(self.input_dir, "Data/Intensities/BaseCalls/")
if type(self.sample_sheet) == list:
if len(self.sample_sheet) > 1:
raise Exception('Too many sample sheet files: %s' % ','.join(self.sample_sheet))
else:
self.sample_sheet = self.sample_sheet[0]
ss = SampleSheet(self.sample_sheet)
mask_length, double_idx = ss.get_mask_length()
if double_idx:
self.use_base_mask = "y*,I{0},I{0},Y*".format(mask_length)
else:
self.use_base_mask = "y*,I{0},Y*".format(mask_length)
self.use_base_mask = str(self.use_base_mask)
super(CasavaDemux, self).process()
prj_dir = os.path.join(self.output_dir, 'Project_' + self.meta['pipeline']['project_name'])
self.output_files = utils.find(prj_dir, "*.fastq.gz")
#set the metadata
self.meta['job']['sample_id'] = []
sample_ids = ss.get_sample_ids()
for output_file in self.output_files:
for sample_id in sample_ids:
if os.path.basename(output_file).startswith("%s_" % sample_id):
self.meta['job']['sample_id'].append(sample_id)
break
def process(self):
self.output_files = ut.find(self.input_dirs, self.pattern,
self.regex_match)
def process(self):
self.output_files = ut.find(self.input_dirs, self.pattern, self.regex_match)
