def test_split_by_contigs_presplit(self): # Consumes too much memory for Jenkins # Test to make sure the result of a split by contigs has an appropriate # number of records (make sure filters are appropriately aggressive) ds2 = DataSet(data.getXml(15)) bams = ds2.externalResources.resourceIds self.assertEqual(len(bams), 2) refwindows = ds2.refWindows self.assertEqual(refwindows, [(0, 0, 224992)]) res1 = openIndexedAlignmentFile(bams[0][7:]) res2 = openIndexedAlignmentFile(bams[1][7:]) def count(iterable): count = 0 for _ in iterable: count += 1 return count self.assertEqual(count(res1.readsInRange(*refwindows[0])), 1409) self.assertEqual(count(res2.readsInRange(*refwindows[0])), 1375) self.assertEqual(count(ds2.readsInRange(*refwindows[0])), 2784) self.assertEqual(count(ds2.records), 2784) ds2.disableFilters() self.assertEqual(count(ds2.records), 53552) self.assertEqual(ds2.countRecords(), 53552)
def test_split_by_contigs_presplit(self): # Consumes too much memory for Jenkins # Test to make sure the result of a split by contigs has an appropriate # number of records (make sure filters are appropriately aggressive) ds2 = DataSet(data.getXml(14)) bams = ds2.externalResources.resourceIds assert len(bams) == 2 refwindows = ds2.refWindows assert refwindows == [(0, 0, 224992)] res1 = openIndexedAlignmentFile(bams[0][7:]) res2 = openIndexedAlignmentFile(bams[1][7:]) def count(iterable): count = 0 for _ in iterable: count += 1 return count assert count(res1.readsInRange(*refwindows[0])) == 1409 assert count(res2.readsInRange(*refwindows[0])) == 1375 assert count(ds2.readsInRange(*refwindows[0])) == 2784 assert count(ds2.records) == 2784 ds2.disableFilters() assert count(ds2.records) == 53552 assert ds2.countRecords() == 53552