def run(description):
parser = argparse.ArgumentParser(
description='Renames sequences in a file, calling them 1,2,3... etc',
usage='fastaq enumerate_names [options] <infile> <outfile>')
parser.add_argument('--start_index',
type=int,
help='Starting number [%(default)s]',
default=1)
parser.add_argument(
'--rename_file',
help='If used, will write a file of old name to new name')
parser.add_argument(
'--keep_suffix',
action='store_true',
help='Use this to keep a /1 or /2 suffix at the end of each name')
parser.add_argument('--suffix',
help='Add the given string to the end of every name',
default=None)
parser.add_argument('infile', help='Name of fasta/q file to be read')
parser.add_argument('outfile', help='Name of output fasta/q file')
options = parser.parse_args()
tasks.enumerate_names(options.infile,
options.outfile,
start_index=options.start_index,
keep_illumina_suffix=options.keep_suffix,
rename_file=options.rename_file,
suffix=options.suffix)
def test_enumerate_names(self):
'''Test enomereate_names works with all options'''
outfile = 'tmp.enumerate_seqs.fa'
rename_out = outfile + '.rename'
tasks.enumerate_names(
os.path.join(data_dir, 'sequences_test_enumerate_names.fa'),
outfile)
self.assertTrue(
filecmp.cmp(
os.path.join(data_dir,
'sequences_test_enumerate_names.fa.out.start.1'),
outfile))
tasks.enumerate_names(os.path.join(
data_dir, 'sequences_test_enumerate_names.fa'),
outfile,
rename_file=rename_out)
self.assertTrue(
filecmp.cmp(
os.path.join(data_dir,
'sequences_test_enumerate_names.fa.out.start.1'),
outfile))
self.assertTrue(
filecmp.cmp(
os.path.join(
data_dir,
'sequences_test_enumerate_names.fa.out.start.1.rename_file'
), rename_out))
tasks.enumerate_names(os.path.join(
data_dir, 'sequences_test_enumerate_names.fa'),
outfile,
start_index=2)
self.assertTrue(
filecmp.cmp(
os.path.join(data_dir,
'sequences_test_enumerate_names.fa.out.start.2'),
outfile))
tasks.enumerate_names(os.path.join(
data_dir, 'sequences_test_enumerate_names.fa'),
outfile,
keep_illumina_suffix=True)
self.assertTrue(
filecmp.cmp(
os.path.join(
data_dir,
'sequences_test_enumerate_names.fa.out.keep_suffix'),
outfile))
tasks.enumerate_names(os.path.join(
data_dir, 'sequences_test_enumerate_names.fa'),
outfile,
suffix='.SUFFIX')
self.assertTrue(
filecmp.cmp(os.path.join(
data_dir, 'sequences_test_enumerate_names.fa.out.add_suffix'),
outfile,
shallow=False))
os.unlink(outfile)
os.unlink(rename_out)
def run(description):
parser = argparse.ArgumentParser(
description = 'Renames sequences in a file, calling them 1,2,3... etc',
usage = 'fastaq enumerate_names [options] <infile> <outfile>')
parser.add_argument('--start_index', type=int, help='Starting number [%(default)s]', default=1)
parser.add_argument('--rename_file', help='If used, will write a file of old name to new name')
parser.add_argument('--keep_suffix', action='store_true', help='Use this to keep a /1 or /2 suffix at the end of each name')
parser.add_argument('--suffix', help='Add the given string to the end of every name', default=None)
parser.add_argument('infile', help='Name of fasta/q file to be read')
parser.add_argument('outfile', help='Name of output fasta/q file')
options = parser.parse_args()
tasks.enumerate_names(options.infile,
options.outfile,
start_index=options.start_index,
keep_illumina_suffix=options.keep_suffix,
rename_file=options.rename_file,
suffix=options.suffix)
def test_enumerate_names(self):
'''Test enomereate_names works with all options'''
outfile = 'tmp.enumerate_seqs.fa'
rename_out = outfile + '.rename'
tasks.enumerate_names(os.path.join(data_dir, 'sequences_test_enumerate_names.fa'), outfile)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_enumerate_names.fa.out.start.1'), outfile))
tasks.enumerate_names(os.path.join(data_dir, 'sequences_test_enumerate_names.fa'), outfile, rename_file=rename_out)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_enumerate_names.fa.out.start.1'), outfile))
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_enumerate_names.fa.out.start.1.rename_file'), rename_out))
tasks.enumerate_names(os.path.join(data_dir, 'sequences_test_enumerate_names.fa'), outfile, start_index=2)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_enumerate_names.fa.out.start.2'), outfile))
tasks.enumerate_names(os.path.join(data_dir, 'sequences_test_enumerate_names.fa'), outfile, keep_illumina_suffix=True)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_enumerate_names.fa.out.keep_suffix'), outfile))
tasks.enumerate_names(os.path.join(data_dir, 'sequences_test_enumerate_names.fa'), outfile, suffix='.SUFFIX')
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_enumerate_names.fa.out.add_suffix'), outfile, shallow=False))
os.unlink(outfile)
os.unlink(rename_out)
