def test_lookup_multiple_or():
i = Index()
i.insert(id='1', age=65, path='test1.txt', type='txt')
i.insert(id='2', age=63, path='test2.txt', type='txt')
i.insert(id='3', age=70, path='test3.jpg', type='jpg')
i.insert(id='4', age=45, path='test4.pdf', type='pdf')
selected = i.lookup(type='txt', path='test3.jpg', or_query=True)
assert selected.datasets != i.datasets
assert len(selected.datasets) == 3
def test_remove_file():
i = Index()
i.insert(id='1', age=65, path='test.txt', type='txt')
i.insert(id='1', path='test1.txt', type='txt')
assert len(i.datasets) == 1
dataset = i.datasets.get('1')
assert len(dataset) == 2
i.remove(path='test.txt')
assert len(i.datasets) == 1
assert len(i.datasets.get('1')) == 1
def test_lookup_simple_dataset():
i = Index()
i.insert(id='1', age=65, path='test.txt', type='txt')
selected = i.lookup(id='1')
assert selected.datasets == i.datasets
dataset = selected.datasets.get('1')
assert dataset is not None
assert dataset.id == '1'
assert dataset.age == 65
assert len(dataset) == 1
def test_replicates_w_metadata():
"""Test merged datasets with metadata"""
i = Index('test/data/index.txt')
i.set_format('test/data/format.json')
i.open()
i.insert(id='aWL3.1,aWL3.2',
path='test/data/format.json',
type='json',
view='json')
i.lookup(id='aWL3.1,aWL3.2')
i.remove(path='test/data/format.json', clear=True)
def test_export_no_format_no_map():
"""Test export"""
i = Index()
#assert i is not None
i.insert(id="myId",
path="test/data/index.txt",
type="text",
view="TxtFile")
exp = i.export(map=None, export_type='tab', tags=['id'])
assert len(exp) == 1
assert exp[0] == 'myId'
def test_insert_update_exc():
"""Test insertion into the index adding non-existing keys"""
i = Index()
i.insert(id='1', age=65, path='test.txt', type='txt')
with pytest.raises(AttributeError):
i.insert(id='1',
age=70,
path='test.txt',
type='text',
length=20,
update=True)
def test_lookup_path():
i = Index()
i.insert(id='1', age=65, path='test1.txt', type='txt')
i.insert(id='2', age=63, path='test2.txt', type='txt')
i.insert(id='3', age=70, path='test3.jpg', type='jpg')
selected = i.lookup(path='test3.jpg')
assert selected.datasets != i.datasets
dataset = selected.datasets.get('3')
assert dataset is not None
assert dataset.id == '3'
assert dataset.age == 70
assert len(dataset) == 1
def test_add_file_external():
index = '''.\tage=-; cell=Neutrophils; dataType=RNA-Seq; dateSubmittedFirst=2012-10-17T09:49:23+0200; donorId=C000XW; ethnicity=NA; lab=MPIMG; labExpId=ERR180946; labProtocolId=C000XWB1; libProtocol=I_bc_pelib_858; localization="Primary Cell"; quality=phred; readStrand=MATE2_SENSE; readType=2x76D; rnaExtract=total; seqPlatform=ILLUMINA; seqRun=1; sex=Male; sraSampleAccession=ERS150362; sraStudyAccession=ERP001664; tissue="Cord blood";'''
i = Index()
i.set_format('test/data/tsv_format.json')
i.insert(**Index.parse_line(index, **i.format))
i.insert(
id="ERR180946",
path=
"/users/rg/epalumbo/projects/BluePrint/reads/20130805/data/ERR180946_1.fastq.gz",
view="FastqRd1",
type="fastq")
assert i.export(
map=None
)[0] == '''/users/rg/epalumbo/projects/BluePrint/reads/20130805/data/ERR180946_1.fastq.gz\tage=-; cell=Neutrophils; dataType=RNA-Seq; dateSubmittedFirst=2012-10-17T09:49:23+0200; donorId=C000XW; ethnicity=NA; lab=MPIMG; labExpId=ERR180946; labProtocolId=C000XWB1; libProtocol=I_bc_pelib_858; localization="Primary Cell"; quality=phred; readStrand=MATE2_SENSE; readType=2x76D; rnaExtract=total; seqPlatform=ILLUMINA; seqRun=1; sex=Male; sraSampleAccession=ERS150362; sraStudyAccession=ERP001664; tissue="Cord blood"; type=fastq; view=FastqRd1;'''
def test_insert_update():
"""Test insertion into the index"""
i = Index()
i.insert(id='1', age=65, path='test.txt', type='txt')
i.insert(id='1', age=70, path='test.txt', type='text', update=True)
assert len(i.datasets) == 1
dataset = i.datasets.get('1')
assert dataset is not None
assert len(dataset) == 1
assert hasattr(dataset, 'id')
assert hasattr(dataset, 'age')
assert dataset.id == '1'
assert dataset.age == 70
assert len(dataset['test.txt']) == 1
assert hasattr(dataset['test.txt'], 'type')
assert dataset['test.txt'].type == 'text'
def test_remove_fileinfo():
i = Index()
i.insert(id='1', age=65, path='test.txt', type='txt')
i.insert(id='1', path='test1.txt', type='txt')
i.insert(id='1', path='test1.jpg', type='jpeg')
assert len(i.datasets) == 1
dataset = i.datasets.get('1')
assert len(dataset) == 3
i.remove(type='jpeg')
print i.datasets.get('1')._files
assert len(i.datasets) == 1
assert len(i.datasets.get('1')) == 2
def test_remove_dataset():
i = Index()
i.insert(id='1', age=65, path='test.txt', type='txt')
i.remove(id='1')
assert len(i.datasets) == 0
def test_lookup_multiple_or():
i = Index()
i.insert(id='1', age=65, path='test1.txt', type='txt')
i.insert(id='1', age=65, path='test1.gff', type='gff')
selected = i.lookup(type='txt')
assert len(selected.datasets.values()[0]) == 1