def test_len_h5(self):
# HdfSubreadSet
# len means something else in bax/bas land. These numbers may actually
# be correct...
sset = HdfSubreadSet(data.getXml(17), strict=True)
self.assertEqual(len(sset), 9)
self.assertEqual(sset._length, (9, 128093))
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
# AlignmentSet with cmp.h5
aln = AlignmentSet(upstreamData.getBamAndCmpH5()[1], strict=True)
self.assertEqual(len(aln), 112)
self.assertEqual(aln._length, (112, 59970))
self.assertEqual(aln.totalLength, 59970)
self.assertEqual(aln.numRecords, 112)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 59970)
self.assertEqual(aln.numRecords, 112)
def test_len(self):
# AlignmentSet
aln = AlignmentSet(data.getXml(7), strict=True)
assert len(aln) == 92
assert aln._length == (92, 123588)
assert aln.totalLength == 123588
assert aln.numRecords == 92
aln.totalLength = -1
aln.numRecords = -1
assert aln.totalLength == -1
assert aln.numRecords == -1
aln.updateCounts()
assert aln.totalLength == 123588
assert aln.numRecords == 92
assert sum(1 for _ in aln) == 92
assert sum(len(rec) for rec in aln) == 123588
# AlignmentSet with filters
aln = AlignmentSet(data.getXml(14), strict=True)
assert len(aln) == 40
assert aln._length == (40, 52023)
assert aln.totalLength == 52023
assert aln.numRecords == 40
aln.totalLength = -1
aln.numRecords = -1
assert aln.totalLength == -1
assert aln.numRecords == -1
aln.updateCounts()
assert aln.totalLength == 52023
assert aln.numRecords == 40
# SubreadSet
sset = SubreadSet(data.getXml(9), strict=True)
assert len(sset) == 92
assert sset._length == (92, 124093)
assert sset.totalLength == 124093
assert sset.numRecords == 92
sset.totalLength = -1
sset.numRecords = -1
assert sset.totalLength == -1
assert sset.numRecords == -1
sset.updateCounts()
assert sset.totalLength == 124093
assert sset.numRecords == 92
assert sum(1 for _ in sset) == 92
assert sum(len(rec) for rec in sset) == 124093
# ReferenceSet
sset = ReferenceSet(data.getXml(8), strict=True)
assert len(sset) == 59
assert sset.totalLength == 85774
assert sset.numRecords == 59
sset.totalLength = -1
sset.numRecords = -1
assert sset.totalLength == -1
assert sset.numRecords == -1
sset.updateCounts()
assert sset.totalLength == 85774
assert sset.numRecords == 59
def test_len(self):
# AlignmentSet
aln = AlignmentSet(data.getXml(8), strict=True)
self.assertEqual(len(aln), 92)
self.assertEqual(aln._length, (92, 123588))
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
self.assertEqual(sum(1 for _ in aln), 92)
self.assertEqual(sum(len(rec) for rec in aln), 123588)
# AlignmentSet with filters
aln = AlignmentSet(data.getXml(15), strict=True)
self.assertEqual(len(aln), 40)
self.assertEqual(aln._length, (40, 52023))
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
# SubreadSet
sset = SubreadSet(data.getXml(10), strict=True)
self.assertEqual(len(sset), 92)
self.assertEqual(sset._length, (92, 124093))
self.assertEqual(sset.totalLength, 124093)
self.assertEqual(sset.numRecords, 92)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 124093)
self.assertEqual(sset.numRecords, 92)
self.assertEqual(sum(1 for _ in sset), 92)
self.assertEqual(sum(len(rec) for rec in sset), 124093)
# ReferenceSet
sset = ReferenceSet(data.getXml(9), strict=True)
self.assertEqual(len(sset), 59)
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
def test_updateCounts(self):
log.info("Testing updateCounts without filters")
aln = AlignmentSet(data.getBam(0))
readers = aln.resourceReaders()
expLen = 0
for reader in readers:
for record in reader:
expLen += record.readLength
self.assertEqual(
record.aStart, record.bam.pbi[record.rowNumber]['aStart'])
self.assertEqual(
record.aEnd, record.bam.pbi[record.rowNumber]['aEnd'])
expNum = 0
for reader in readers:
expNum += len(reader)
accLen = aln.metadata.totalLength
accNum = aln.metadata.numRecords
self.assertEqual(expLen, accLen)
self.assertEqual(expNum, accNum)
log.info("Testing whether filters are respected")
aln.filters.addRequirement(rname=[('=', 'E.faecalis.1')])
aln.updateCounts()
accLen = aln.metadata.totalLength
accNum = aln.metadata.numRecords
def count(gen):
count = 0
for _ in gen:
count += 1
return count
expLen = 0
for reader in readers:
for record in reader:
expLen += record.readLength
bfile = openIndexedAlignmentFile(data.getBam(0))
rWin = (bfile.referenceInfo('E.faecalis.1').ID,
0,
bfile.referenceInfo('E.faecalis.1').Length)
reads = bfile.readsInRange(*rWin)
expNum = count(reads)
expLen = 0
reads = bfile.readsInRange(*rWin)
for read in reads:
expLen += read.readLength
self.assertEqual(expLen, accLen)
self.assertEqual(expNum, accNum)
def test_updateCounts(self):
log.info("Testing updateCounts without filters")
aln = AlignmentSet(data.getBam(0))
readers = aln.resourceReaders()
expLen = 0
for reader in readers:
for record in reader:
expLen += record.readLength
self.assertEqual(record.aStart,
record.bam.pbi[record.rowNumber]['aStart'])
self.assertEqual(record.aEnd,
record.bam.pbi[record.rowNumber]['aEnd'])
expNum = 0
for reader in readers:
expNum += len(reader)
accLen = aln.metadata.totalLength
accNum = aln.metadata.numRecords
self.assertEqual(expLen, accLen)
self.assertEqual(expNum, accNum)
log.info("Testing whether filters are respected")
aln.filters.addRequirement(rname=[('=', 'E.faecalis.1')])
aln.updateCounts()
accLen = aln.metadata.totalLength
accNum = aln.metadata.numRecords
def count(gen):
count = 0
for _ in gen:
count += 1
return count
expLen = 0
for reader in readers:
for record in reader:
expLen += record.readLength
bfile = openIndexedAlignmentFile(data.getBam(0))
rWin = (bfile.referenceInfo('E.faecalis.1').ID, 0,
bfile.referenceInfo('E.faecalis.1').Length)
reads = bfile.readsInRange(*rWin)
expNum = count(reads)
expLen = 0
reads = bfile.readsInRange(*rWin)
for read in reads:
expLen += read.readLength
self.assertEqual(expLen, accLen)
self.assertEqual(expNum, accNum)
def test_filter_cli(self):
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
outfn = os.path.join(outdir, "filtered8.xml")
log.debug(outfn)
cmd = "dataset filter {i} {o} {f}".format(i=data.getXml(7),
o=outfn,
f="rname=E.faecalis.1")
self._run_cmd_with_output(cmd, outfn)
aln = AlignmentSet(data.getXml(7))
aln.filters.addRequirement(rname=[('=', 'E.faecalis.1')])
aln.updateCounts()
dset = AlignmentSet(outfn)
assert str(aln.filters) == str(dset.filters)
assert aln.totalLength == dset.totalLength
assert aln.numRecords == dset.numRecords
def test_filter_cli(self):
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
outfn = os.path.join(outdir, "filtered8.xml")
log.debug(outfn)
cmd = "dataset filter {i} {o} {f}".format(i=data.getXml(8),
o=outfn,
f="rname=E.faecalis.1")
log.debug(cmd)
o, r, m = backticks(cmd)
if r != 0:
log.debug(m)
self.assertEqual(r, 0)
self.assertTrue(os.path.exists(outfn))
aln = AlignmentSet(data.getXml(8))
aln.filters.addRequirement(rname=[('=', 'E.faecalis.1')])
aln.updateCounts()
dset = AlignmentSet(outfn)
self.assertEqual(str(aln.filters), str(dset.filters))
self.assertEqual(aln.totalLength, dset.totalLength)
self.assertEqual(aln.numRecords, dset.numRecords)
def test_filter_cli(self):
outdir = tempfile.mkdtemp(suffix="dataset-unittest")
outfn = os.path.join(outdir, "filtered8.xml")
log.debug(outfn)
cmd = "dataset filter {i} {o} {f}".format(
i=data.getXml(8),
o=outfn,
f="rname=E.faecalis.1")
log.debug(cmd)
o, r, m = backticks(cmd)
if r != 0:
log.debug(m)
self.assertEqual(r, 0)
self.assertTrue(os.path.exists(outfn))
aln = AlignmentSet(data.getXml(8))
aln.filters.addRequirement(rname=[('=', 'E.faecalis.1')])
aln.updateCounts()
dset = AlignmentSet(outfn)
self.assertEqual(str(aln.filters), str(dset.filters))
self.assertEqual(aln.totalLength, dset.totalLength)
self.assertEqual(aln.numRecords, dset.numRecords)
def test_len(self):
# AlignmentSet
aln = AlignmentSet(data.getXml(8), strict=True)
self.assertEqual(len(aln), 92)
self.assertEqual(aln._length, (92, 123588))
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
self.assertEqual(sum(1 for _ in aln), 92)
self.assertEqual(sum(len(rec) for rec in aln), 123588)
# AlignmentSet with filters
aln = AlignmentSet(data.getXml(15), strict=True)
self.assertEqual(len(aln), 40)
self.assertEqual(aln._length, (40, 52023))
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
# AlignmentSet with cmp.h5
aln = AlignmentSet(upstreamData.getBamAndCmpH5()[1], strict=True)
self.assertEqual(len(aln), 112)
self.assertEqual(aln._length, (112, 59970))
self.assertEqual(aln.totalLength, 59970)
self.assertEqual(aln.numRecords, 112)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 59970)
self.assertEqual(aln.numRecords, 112)
# SubreadSet
sset = SubreadSet(data.getXml(10), strict=True)
self.assertEqual(len(sset), 92)
self.assertEqual(sset._length, (92, 124093))
self.assertEqual(sset.totalLength, 124093)
self.assertEqual(sset.numRecords, 92)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 124093)
self.assertEqual(sset.numRecords, 92)
self.assertEqual(sum(1 for _ in sset), 92)
self.assertEqual(sum(len(rec) for rec in sset), 124093)
# HdfSubreadSet
# len means something else in bax/bas land. These numbers may actually
# be correct...
sset = HdfSubreadSet(data.getXml(17), strict=True)
self.assertEqual(len(sset), 9)
self.assertEqual(sset._length, (9, 128093))
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
# ReferenceSet
sset = ReferenceSet(data.getXml(9), strict=True)
self.assertEqual(len(sset), 59)
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
def test_len(self):
# AlignmentSet
aln = AlignmentSet(data.getXml(8), strict=True)
self.assertEqual(len(aln), 92)
self.assertEqual(aln._length, (92, 123588))
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
# AlignmentSet with filters
aln = AlignmentSet(data.getXml(15), strict=True)
self.assertEqual(len(aln), 40)
self.assertEqual(aln._length, (40, 52023))
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
# NO LONGER SUPPORTED AlignmentSet with cmp.h5
#aln = AlignmentSet(upstreamData.getCmpH5(), strict=True)
#self.assertEqual(len(aln), 84)
#self.assertEqual(aln._length, (84, 26103))
#self.assertEqual(aln.totalLength, 26103)
#self.assertEqual(aln.numRecords, 84)
#aln.totalLength = -1
#aln.numRecords = -1
#self.assertEqual(aln.totalLength, -1)
#self.assertEqual(aln.numRecords, -1)
#aln.updateCounts()
#self.assertEqual(aln.totalLength, 26103)
#self.assertEqual(aln.numRecords, 84)
# SubreadSet
# TODO Turn this back on when pbi's are fixed for subreadsets
#sset = SubreadSet(data.getXml(10), strict=True)
#self.assertEqual(len(sset), 92)
#self.assertEqual(sset._length, (92, 123588))
#self.assertEqual(sset.totalLength, 123588)
#self.assertEqual(sset.numRecords, 92)
#sset.totalLength = -1
#sset.numRecords = -1
#self.assertEqual(sset.totalLength, -1)
#self.assertEqual(sset.numRecords, -1)
#sset.updateCounts()
#self.assertEqual(sset.totalLength, 123588)
#self.assertEqual(sset.numRecords, 92)
# HdfSubreadSet
# len means something else in bax/bas land. These numbers may actually
# be correct...
sset = HdfSubreadSet(data.getXml(17), strict=True)
self.assertEqual(len(sset), 9)
self.assertEqual(sset._length, (9, 128093))
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
# ReferenceSet
sset = ReferenceSet(data.getXml(9), strict=True)
self.assertEqual(len(sset), 59)
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
def test_len(self):
# AlignmentSet
aln = AlignmentSet(data.getXml(8), strict=True)
self.assertEqual(len(aln), 92)
self.assertEqual(aln._length, (92, 123588))
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 123588)
self.assertEqual(aln.numRecords, 92)
self.assertEqual(sum(1 for _ in aln), 92)
self.assertEqual(sum(len(rec) for rec in aln), 123588)
# AlignmentSet with filters
aln = AlignmentSet(data.getXml(15), strict=True)
self.assertEqual(len(aln), 40)
self.assertEqual(aln._length, (40, 52023))
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 52023)
self.assertEqual(aln.numRecords, 40)
# AlignmentSet with cmp.h5
aln = AlignmentSet(upstreamData.getBamAndCmpH5()[1], strict=True)
self.assertEqual(len(aln), 112)
self.assertEqual(aln._length, (112, 59970))
self.assertEqual(aln.totalLength, 59970)
self.assertEqual(aln.numRecords, 112)
aln.totalLength = -1
aln.numRecords = -1
self.assertEqual(aln.totalLength, -1)
self.assertEqual(aln.numRecords, -1)
aln.updateCounts()
self.assertEqual(aln.totalLength, 59970)
self.assertEqual(aln.numRecords, 112)
# SubreadSet
sset = SubreadSet(data.getXml(10), strict=True)
self.assertEqual(len(sset), 92)
self.assertEqual(sset._length, (92, 124093))
self.assertEqual(sset.totalLength, 124093)
self.assertEqual(sset.numRecords, 92)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 124093)
self.assertEqual(sset.numRecords, 92)
self.assertEqual(sum(1 for _ in sset), 92)
self.assertEqual(sum(len(rec) for rec in sset), 124093)
# HdfSubreadSet
# len means something else in bax/bas land. These numbers may actually
# be correct...
sset = HdfSubreadSet(data.getXml(17), strict=True)
self.assertEqual(len(sset), 9)
self.assertEqual(sset._length, (9, 128093))
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 128093)
self.assertEqual(sset.numRecords, 9)
# ReferenceSet
sset = ReferenceSet(data.getXml(9), strict=True)
self.assertEqual(len(sset), 59)
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)
sset.totalLength = -1
sset.numRecords = -1
self.assertEqual(sset.totalLength, -1)
self.assertEqual(sset.numRecords, -1)
sset.updateCounts()
self.assertEqual(sset.totalLength, 85774)
self.assertEqual(sset.numRecords, 59)