stream.write('testfile')
self.result_map = ResultMap()
- for lib_id in [u'11154', u'12345']:
+ for lib_id in ['11154', '12345']:
subname = 'sub-%s' % (lib_id,)
sub_dir = os.path.join(self.tempdir, subname)
os.mkdir(sub_dir)
seqs = self.extract.find_archive_sequence_files(self.result_map)
expected = set([
- (u'11154', u'42JUYAAXX', '5', 1, 76, True, 'qseq'),
- (u'11154', u'42JUYAAXX', '5', 2, 76, True, 'qseq'),
- (u'11154', u'61MJTAAXX', '6', 1, 76, False, 'qseq'),
- (u'11154', u'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
- (u'11154', u'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
- (u'11154', u'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
- (u'11154', u'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
- (u'12345', u'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
- (u'12345', u'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
- (u'12345', u'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
- (u'12345', u'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
- (u'12345', u'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
- (u'12345', u'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
- (u'11154', u'30221AAXX', '4', 1, 33, False, 'srf'),
- (u'11154', u'30DY0AAXX', '8', 1, 151, True, 'srf')
+ ('11154', '42JUYAAXX', '5', 1, 76, True, 'qseq'),
+ ('11154', '42JUYAAXX', '5', 2, 76, True, 'qseq'),
+ ('11154', '61MJTAAXX', '6', 1, 76, False, 'qseq'),
+ ('11154', 'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
+ ('11154', 'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
+ ('11154', 'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
+ ('11154', 'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
+ ('12345', 'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
+ ('12345', 'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
+ ('12345', 'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
+ ('12345', 'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
+ ('12345', 'C02F9ACXX', '3', 1, 202, True, 'split_fastq'),
+ ('12345', 'C02F9ACXX', '3', 2, 202, True, 'split_fastq'),
+ ('11154', '30221AAXX', '4', 1, 33, False, 'srf'),
+ ('11154', '30DY0AAXX', '8', 1, 151, True, 'srf')
])
found = set([(l.library_id, l.flowcell_id, l.lane_number, l.read, l.cycle, l.ispaired, l.filetype) for l in seqs])
self.assertEqual(expected, found)
lib_db)
self.assertEqual(len(needed_targets), 9)
srf_30221 = needed_targets[
- self.result_map['11154'] + u'/11154_30221AAXX_c33_l4.fastq']
+ self.result_map['11154'] + '/11154_30221AAXX_c33_l4.fastq']
qseq_42JUY_r1 = needed_targets[
- self.result_map['11154'] + u'/11154_42JUYAAXX_c76_l5_r1.fastq']
+ self.result_map['11154'] + '/11154_42JUYAAXX_c76_l5_r1.fastq']
qseq_42JUY_r2 = needed_targets[
- self.result_map['11154'] + u'/11154_42JUYAAXX_c76_l5_r2.fastq']
+ self.result_map['11154'] + '/11154_42JUYAAXX_c76_l5_r2.fastq']
qseq_61MJT = needed_targets[
- self.result_map['11154'] + u'/11154_61MJTAAXX_c76_l6.fastq']
+ self.result_map['11154'] + '/11154_61MJTAAXX_c76_l6.fastq']
split_C02F9_r1 = needed_targets[
- self.result_map['11154'] + u'/11154_C02F9ACXX_c202_l3_r1.fastq']
+ self.result_map['11154'] + '/11154_C02F9ACXX_c202_l3_r1.fastq']
split_C02F9_r2 = needed_targets[
- self.result_map['11154'] + u'/11154_C02F9ACXX_c202_l3_r2.fastq']
+ self.result_map['11154'] + '/11154_C02F9ACXX_c202_l3_r2.fastq']
self.assertEqual(len(srf_30221['srf']), 1)
self.assertEqual(len(qseq_42JUY_r1['qseq']), 1)
'11154_30221AAXX_c33_l4.fastq'): {
'mid': None,
'ispaired': False,
- 'sources': [u'woldlab_090425_HWI-EAS229_0110_30221AAXX_4.srf'],
- 'flowcell': u'30221AAXX',
+ 'sources': ['woldlab_090425_HWI-EAS229_0110_30221AAXX_4.srf'],
+ 'flowcell': '30221AAXX',
'target': os.path.join(self.result_map['11154'],
- u'11154_30221AAXX_c33_l4.fastq'),
+ '11154_30221AAXX_c33_l4.fastq'),
},
os.path.join(self.result_map['11154'],
'11154_30DY0AAXX_c151_l8_r1.fastq'): {
'mid': None,
'ispaired': True,
- 'flowcell': u'30DY0AAXX',
- 'sources': [u'woldlab_090725_HWI-EAS229_0110_30DY0AAXX_8.srf'],
+ 'flowcell': '30DY0AAXX',
+ 'sources': ['woldlab_090725_HWI-EAS229_0110_30DY0AAXX_8.srf'],
'mid': 76,
'target':
os.path.join(self.result_map['11154'],
- u'11154_30DY0AAXX_c151_l8_r1.fastq'),
+ '11154_30DY0AAXX_c151_l8_r1.fastq'),
'target_right':
os.path.join(self.result_map['11154'],
- u'11154_30DY0AAXX_c151_l8_r2.fastq'),
+ '11154_30DY0AAXX_c151_l8_r2.fastq'),
}
}
for args in srf:
'istar': True,
'ispaired': True,
'sources': [
- u'woldlab_100826_HSI-123_0001_42JUYAAXX_l5_r1.tar.bz2']
+ 'woldlab_100826_HSI-123_0001_42JUYAAXX_l5_r1.tar.bz2']
},
os.path.join(self.result_map['11154'],
'11154_42JUYAAXX_c76_l5_r2.fastq'): {
'istar': True,
'ispaired': True,
'sources': [
- u'woldlab_100826_HSI-123_0001_42JUYAAXX_l5_r2.tar.bz2']
+ 'woldlab_100826_HSI-123_0001_42JUYAAXX_l5_r2.tar.bz2']
},
os.path.join(self.result_map['11154'],
'11154_61MJTAAXX_c76_l6.fastq'): {
'istar': True,
'ispaired': False,
'sources': [
- u'woldlab_100826_HSI-123_0001_61MJTAAXX_l6_r1.tar.bz2'],
+ 'woldlab_100826_HSI-123_0001_61MJTAAXX_l6_r1.tar.bz2'],
},
}
for args in qseq:
split_test = dict((( x['target'], x) for x in
- [{'sources': [u'11154_NoIndex_L003_R1_001.fastq.gz',
- u'11154_NoIndex_L003_R1_002.fastq.gz'],
+ [{'sources': ['11154_NoIndex_L003_R1_001.fastq.gz',
+ '11154_NoIndex_L003_R1_002.fastq.gz'],
'pyscript': 'desplit_fastq.pyc',
- 'target': u'11154_C02F9ACXX_c202_l3_r1.fastq'},
- {'sources': [u'11154_NoIndex_L003_R2_001.fastq.gz',
- u'11154_NoIndex_L003_R2_002.fastq.gz'],
+ 'target': '11154_C02F9ACXX_c202_l3_r1.fastq'},
+ {'sources': ['11154_NoIndex_L003_R2_001.fastq.gz',
+ '11154_NoIndex_L003_R2_002.fastq.gz'],
'pyscript': 'desplit_fastq.pyc',
- 'target': u'11154_C02F9ACXX_c202_l3_r2.fastq'},
- {'sources': [u'12345_CGATGT_L003_R1_001.fastq.gz',
- u'12345_CGATGT_L003_R1_002.fastq.gz',
- u'12345_CGATGT_L003_R1_003.fastq.gz',
+ 'target': '11154_C02F9ACXX_c202_l3_r2.fastq'},
+ {'sources': ['12345_CGATGT_L003_R1_001.fastq.gz',
+ '12345_CGATGT_L003_R1_002.fastq.gz',
+ '12345_CGATGT_L003_R1_003.fastq.gz',
],
'pyscript': 'desplit_fastq.pyc',
- 'target': u'12345_C02F9ACXX_c202_l3_r1.fastq'},
- {'sources': [u'12345_CGATGT_L003_R2_001.fastq.gz',
- u'12345_CGATGT_L003_R2_002.fastq.gz',
- u'12345_CGATGT_L003_R2_003.fastq.gz',
+ 'target': '12345_C02F9ACXX_c202_l3_r1.fastq'},
+ {'sources': ['12345_CGATGT_L003_R2_001.fastq.gz',
+ '12345_CGATGT_L003_R2_002.fastq.gz',
+ '12345_CGATGT_L003_R2_003.fastq.gz',
],
'pyscript': 'desplit_fastq.pyc',
- 'target': u'12345_C02F9ACXX_c202_l3_r2.fastq'}
+ 'target': '12345_C02F9ACXX_c202_l3_r2.fastq'}
]
))
for arg in split:
def suite():
- from unittest2 import TestSuite, defaultTestLoader
+ from unittest import TestSuite, defaultTestLoader
suite = TestSuite()
suite.addTests(defaultTestLoader.loadTestsFromTestCase(TestCondorFastq))
return suite
if __name__ == "__main__":
- from unittest2 import main
+ from unittest import main
main(defaultTest='suite')