def run(description):
parser = argparse.ArgumentParser(
description = 'Splits a multi sequence file into separate files. Does not split sequences. Puts up to max_bases into each split file. The exception is that any sequence longer than max_bases is put into its own file.',
usage = 'fastaq split_by_base_count [options] <infile> <outprefix> <max_bases>')
parser.add_argument('infile', help='Name of input file to be split')
parser.add_argument('outprefix', help='Name of output file')
parser.add_argument('max_bases', type=int, help='Max bases in each output split file', metavar='max_bases')
parser.add_argument('--max_seqs', type=int, help='Max number of sequences in each output split file [no limit]', metavar='INT')
options = parser.parse_args()
tasks.split_by_base_count(options.infile, options.outprefix, options.max_bases, options.max_seqs)
def test_split_by_base_count(self):
'''Check that fasta/q files get split by base count correctly'''
infile = os.path.join(data_dir, 'sequences_test_split_test.fa')
outprefix = 'tmp.sequences_test_split_test.fa.test'
length2files = {2: ['1','2','3','4'],
3: ['1','2','3'],
4: ['1', '2', '3'],
6: ['1', '2']}
for l in length2files:
tasks.split_by_base_count(infile, outprefix, l)
for x in range(len(length2files[l])):
file_index = str(length2files[l][x])
fname = outprefix + '.' + file_index
self.assertTrue(filecmp.cmp(fname, infile + '.' + str(l) + '.' + file_index))
os.unlink(fname)
# check that limiting the number of files works
tasks.split_by_base_count(infile, outprefix, 6, 2)
for i in range(1,4):
test_file = outprefix + '.' + str(i)
self.assertTrue(filecmp.cmp(test_file, os.path.join(data_dir, 'sequences_test_split_test.fa.6.limit2.') + str(i)))
os.unlink(test_file)
# check big sequence not broken
tasks.split_by_base_count(os.path.join(data_dir, 'sequences_test_split_test.long.fa'), outprefix, 2)
self.assertTrue(filecmp.cmp(outprefix + '.1', os.path.join(data_dir, 'sequences_test_split_test.long.fa.2.1')))
self.assertTrue(filecmp.cmp(outprefix + '.2', os.path.join(data_dir, 'sequences_test_split_test.long.fa.2.2')))
os.unlink(outprefix + '.1')
os.unlink(outprefix + '.2')
def test_split_by_base_count(self):
'''Check that fasta/q files get split by base count correctly'''
infile = os.path.join(data_dir, 'sequences_test_split_test.fa')
outprefix = 'tmp.sequences_test_split_test.fa.test'
length2files = {2: ['1','2','3','4'],
3: ['1','2','3'],
4: ['1', '2', '3'],
6: ['1', '2']}
for l in length2files:
tasks.split_by_base_count(infile, outprefix, l)
for x in range(len(length2files[l])):
file_index = str(length2files[l][x])
fname = outprefix + '.' + file_index
self.assertTrue(filecmp.cmp(fname, infile + '.' + str(l) + '.' + file_index))
os.unlink(fname)
# check that limiting the number of files works
tasks.split_by_base_count(infile, outprefix, 6, 2)
for i in range(1,4):
test_file = outprefix + '.' + str(i)
self.assertTrue(filecmp.cmp(test_file, os.path.join(data_dir, 'sequences_test_split_test.fa.6.limit2.') + str(i)))
os.unlink(test_file)
# check big sequence not broken
tasks.split_by_base_count(os.path.join(data_dir, 'sequences_test_split_test.long.fa'), outprefix, 2)
self.assertTrue(filecmp.cmp(outprefix + '.1', os.path.join(data_dir, 'sequences_test_split_test.long.fa.2.1')))
self.assertTrue(filecmp.cmp(outprefix + '.2', os.path.join(data_dir, 'sequences_test_split_test.long.fa.2.2')))
os.unlink(outprefix + '.1')
os.unlink(outprefix + '.2')
