def testSpacesMustBePreserved(self):
"""
If there are spaces in the query title or subject titles, the spaces
must be preserved.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORD_WITH_SPACES)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
acc94 = list(reader.records())
self.assertEqual('ACC 94', acc94[0]['query'])
self.assertEqual('IN SV', acc94[0]['alignments'][0]['title'])
def testSaveAsJSON(self):
"""
A DiamondTabularFormatReader must be able to save itself as JSON.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
fp = StringIO()
reader.saveAsJSON(fp)
self.maxDiff = None
self.assertEqual(DIAMOND_RECORDS_DUMPED, fp.getvalue())
def testSpacesMustBePreserved(self):
"""
If there are spaces in the query title or subject titles, the spaces
must be preserved.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORD_WITH_SPACES_IN_TITLES)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
acc94 = list(reader.records())
self.assertEqual('ACC 94', acc94[0]['query'])
self.assertEqual('IN SV', acc94[0]['alignments'][0]['title'])
def testDiamondInput(self):
"""
Test conversion of a chunk of DIAMOND output.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
acc94, akav, bhav = list(reader.records())
self.assertEqual(5, len(acc94['alignments']))
self.assertEqual(2, len(akav['alignments']))
self.assertEqual(2, len(bhav['alignments']))
def testSaveAsJSON(self):
"""
A DiamondTabularFormatReader must be able to save itself as JSON.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
fp = StringIO()
reader.saveAsJSON(fp)
self.maxDiff = None
self.assertEqual(DIAMOND_RECORDS_DUMPED, fp.getvalue())
def testDiamondInput(self):
"""
Test conversion of a chunk of DIAMOND output.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
acc94, akav, bhav = list(reader.records())
self.assertEqual(5, len(acc94['alignments']))
self.assertEqual(2, len(akav['alignments']))
self.assertEqual(2, len(bhav['alignments']))
def testSaveAsJSONBzip2(self):
"""
A DiamondTabularFormatReader must be able to save itself as bzip2'd
JSON.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
data = BytesIO()
fp = bz2file.BZ2File(data, 'w')
reader.saveAsJSON(fp, writeBytes=True)
fp.close()
self.assertEqual(compress(DIAMOND_RECORDS_DUMPED.encode('UTF-8')),
data.getvalue())
def testDiamondInputWithoutNidentOrPositives(self):
"""
Test conversion of a chunk of DIAMOND output that does not contain the
nident or positives fields.
"""
mockOpener = mockOpen(
read_data=DIAMOND_RECORDS_WITHOUT_NIDENT_AND_POSITIVE)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
acc94, akav, bhav = list(reader.records())
for record in acc94, akav, bhav:
for alignment in record['alignments']:
for hsp in alignment['hsps']:
self.assertIs(None, hsp['identicalCount'])
def testDiamondInputWithoutNidentOrPositives(self):
"""
Test conversion of a chunk of DIAMOND output that does not contain the
nident or positives fields.
"""
mockOpener = mockOpen(
read_data=DIAMOND_RECORDS_WITHOUT_NIDENT_AND_POSITIVE)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
acc94, akav, bhav = list(reader.records())
for record in acc94, akav, bhav:
for alignment in record['alignments']:
for hsp in alignment['hsps']:
self.assertIs(None, hsp['identicalCount'])
def testSaveAsJSONBzip2(self):
"""
A DiamondTabularFormatReader must be able to save itself as bzip2'd
JSON.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
data = BytesIO()
fp = bz2file.BZ2File(data, 'w')
reader.saveAsJSON(fp, writeBytes=True)
fp.close()
self.assertEqual(
compress(DIAMOND_RECORDS_DUMPED.encode('UTF-8')),
data.getvalue())
def testDiamondParams(self):
"""
When a DIAMOND file has been read, its parameters must be present
in the reader instance.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
list(reader.records())
self.assertEqual('DIAMOND', reader.application)
self.assertEqual(
{
'application': 'DIAMOND',
'reference': (
'Buchfink et al., Fast and Sensitive Protein '
'Alignment using DIAMOND, Nature Methods, 12, '
'59-60 (2015)'),
'task': 'blastx',
'version': 'v0.8.23',
},
reader.params)
def testDiamondParams(self):
"""
When a DIAMOND file has been read, its parameters must be present
in the reader instance.
"""
mockOpener = mockOpen(read_data=DIAMOND_RECORDS)
with patch.object(builtins, 'open', mockOpener):
reader = DiamondTabularFormatReader('file.txt')
list(reader.records())
self.assertEqual('DIAMOND', reader.application)
self.assertEqual(
{
'application':
'DIAMOND',
'reference':
('Buchfink et al., Fast and Sensitive Protein '
'Alignment using DIAMOND, Nature Methods, 12, '
'59-60 (2015)'),
'task':
'blastx',
'version':
'v0.8.23',
}, reader.params)
'--outfmt 6 qtitle stitle bitscore evalue qframe qseq '
'qstart qend sseq sstart send slen btop'
'Note that only each line of the output is JSON (the full '
'output is not valid JSON by itself).')
)
parser.add_argument(
'--json', metavar='JSON-output-file',
help=('The JSON filename to write the converted DIAMOND file to. If '
'omitted, standard output will be used.'))
parser.add_argument(
'--diamond', metavar='DIAMOND-file', default=sys.stdin,
help=('The DIAMOND tabular output file to convert. If omitted, '
'standard input will be read.'))
parser.add_argument(
'--bzip2', default=False, action='store_true',
help='Compress output using bzip2.')
args = parser.parse_args()
if args.bzip2:
fp = bz2file.BZ2File(args.json or sys.stdout, 'w')
else:
fp = open(args.json, 'w') if args.json else sys.stdout
reader = DiamondTabularFormatReader(args.diamond)
reader.saveAsJSON(fp, writeBytes=args.bzip2)
fp.close()
'output is not valid JSON by itself).'))
parser.add_argument(
'--json',
metavar='JSON-output-file',
help=('The JSON filename to write the converted DIAMOND file to. If '
'omitted, standard output will be used.'))
parser.add_argument(
'--diamond',
metavar='DIAMOND-file',
default=sys.stdin,
help=('The DIAMOND tabular output file to convert. If omitted, '
'standard input will be read.'))
parser.add_argument('--bzip2',
default=False,
action='store_true',
help='Compress output using bzip2.')
args = parser.parse_args()
if args.bzip2:
fp = bz2file.BZ2File(args.json or sys.stdout, 'w')
else:
fp = open(args.json, 'w') if args.json else sys.stdout
reader = DiamondTabularFormatReader(args.diamond)
reader.saveAsJSON(fp, writeBytes=args.bzip2)
fp.close()