def run(description):
parser = argparse.ArgumentParser(
description=description,
usage='fastaq to_fasta [options] <infile> <outfile>')
parser.add_argument(
'infile',
help=
'Name of input file. Can be any of FASTA, FASTQ, GFF3, EMBL, GBK, Phylip'
)
parser.add_argument('outfile', help='Name of output file')
parser.add_argument(
'-l',
'--line_length',
type=int,
help=
'Number of bases on each sequence line of output file. Set to zero for no linebreaks in sequences [%(default)s]',
default=60)
parser.add_argument(
'-s',
'--strip_after_whitespace',
action='store_true',
help='Remove everything after first whitespace in every sequence name')
parser.add_argument(
'-u',
'--check_unique',
action='store_true',
help='Die if any of the output sequence names are not unique')
options = parser.parse_args()
tasks.to_fasta(options.infile,
options.outfile,
line_length=options.line_length,
strip_after_first_whitespace=options.strip_after_whitespace,
check_unique=options.check_unique)
def test_to_fasta_strip_after_whitespace_unique(self):
'''Test strip_after_whitespace with unique names'''
tmpfile = 'tmp.strip_after_whitespace.fa'
infile = os.path.join(data_dir, 'sequences_test.to_fasta.strip_after_whitespace_unique.in.fa')
expected = os.path.join(data_dir, 'sequences_test.to_fasta.strip_after_whitespace_unique.out.fa')
tasks.to_fasta(infile, tmpfile, strip_after_first_whitespace=True, check_unique=True)
self.assertTrue(filecmp.cmp(tmpfile, expected, shallow=False))
os.unlink(tmpfile)
def test_to_fasta_strip_after_whitespace_unique(self):
'''Test strip_after_whitespace with unique names'''
tmpfile = 'tmp.strip_after_whitespace.fa'
infile = os.path.join(data_dir, 'sequences_test.to_fasta.strip_after_whitespace_unique.in.fa')
expected = os.path.join(data_dir, 'sequences_test.to_fasta.strip_after_whitespace_unique.out.fa')
tasks.to_fasta(infile, tmpfile, strip_after_first_whitespace=True, check_unique=True)
self.assertTrue(filecmp.cmp(tmpfile, expected, shallow=False))
os.unlink(tmpfile)
def run(description):
parser = argparse.ArgumentParser(
description = description,
usage = 'fastaq to_fasta [options] <infile> <outfile>')
parser.add_argument('infile', help='Name of input file. Can be any of FASTA, FASTQ, GFF3, EMBL, GBK, Phylip')
parser.add_argument('outfile', help='Name of output file')
parser.add_argument('-l', '--line_length', type=int, help='Number of bases on each sequence line of output file. Set to zero for no linebreaks in sequences [%(default)s]', default=60)
parser.add_argument('-s', '--strip_after_whitespace', action='store_true', help='Remove everything after first whitespace in every sequence name')
options = parser.parse_args()
tasks.to_fasta(
options.infile,
options.outfile,
line_length=options.line_length,
strip_after_first_whitespace=options.strip_after_whitespace
)
def test_to_fasta(self):
'''Test to_fasta'''
tmpfile = 'tmp.to_fasta'
infiles = [
'sequences_test_good_file.fq',
'sequences_test_gffv3.gff',
'sequences_test_gffv3.no_FASTA_line.gff',
'sequences_test.embl',
'sequences_test.gbk',
'sequences_test_phylip.interleaved',
'sequences_test_phylip.interleaved2',
'sequences_test_phylip.sequential'
]
infiles = [os.path.join(data_dir, x) for x in infiles]
expected_outfiles = [x + '.to_fasta' for x in infiles]
for i in range(len(infiles)):
tasks.to_fasta(infiles[i], tmpfile)
self.assertTrue(filecmp.cmp(expected_outfiles[i], tmpfile))
tasks.to_fasta(os.path.join(data_dir, 'sequences_test.fa'), tmpfile, line_length=3)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test.line_length3.fa'), tmpfile))
tasks.to_fasta(os.path.join(data_dir, 'sequences_test_strip_after_whitespace.fa'), tmpfile, strip_after_first_whitespace=True)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_strip_after_whitespace.fa.to_fasta'), tmpfile))
os.unlink(tmpfile)
def test_to_fasta(self):
'''Test to_fasta'''
tmpfile = 'tmp.to_fasta'
infiles = [
'sequences_test_good_file.fq',
'sequences_test_gffv3.gff',
'sequences_test_gffv3.no_FASTA_line.gff',
'sequences_test.embl',
'sequences_test.gbk',
'sequences_test_phylip.interleaved',
'sequences_test_phylip.interleaved2',
'sequences_test_phylip.sequential'
]
infiles = [os.path.join(data_dir, x) for x in infiles]
expected_outfiles = [x + '.to_fasta' for x in infiles]
for i in range(len(infiles)):
tasks.to_fasta(infiles[i], tmpfile)
self.assertTrue(filecmp.cmp(expected_outfiles[i], tmpfile))
tasks.to_fasta(os.path.join(data_dir, 'sequences_test.fa'), tmpfile, line_length=3)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test.line_length3.fa'), tmpfile))
tasks.to_fasta(os.path.join(data_dir, 'sequences_test_strip_after_whitespace.fa'), tmpfile, strip_after_first_whitespace=True)
self.assertTrue(filecmp.cmp(os.path.join(data_dir, 'sequences_test_strip_after_whitespace.fa.to_fasta'), tmpfile))
os.unlink(tmpfile)
