def test_load_existing():
"""Load existing index"""
i = Index('test/data/index.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
assert len(i) == 36
def test_open_string():
"""Test open with string parameter"""
i = Index()
assert i is not None
i.set_format('test/data/format.json')
i.open('test/data/index.txt')
assert len(i) == 36
def test_lookup_full_index():
"""Test export"""
i = Index('test/data/index.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
result = i.lookup(type='gtf')
assert result.export()[0][0] != '.'
def test_lookup_more_types_index_id():
"""Test export"""
i = Index('test/data/index_gfs.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
result = i.lookup(id='WWP.1')
assert result.export()[0][0] != '.'
def test_export_ol_no_map_tab_path():
"""Test export"""
i = Index('test/data/index_oneline.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None, export_type='tab', tags=['path'])
assert exp[0] == 'aWL3.2/aWL3.2_4204_ACTGAT_transcript.gtf'
def test_open_file():
"""Test open with file parameter"""
i = Index()
assert i is not None
i.set_format('test/data/format.json')
f = open('test/data/index.txt', 'r')
i.open(f)
f.close()
assert len(i) == 36
def test_export_ol_no_map_tab_all():
"""Test export"""
i = Index('test/data/index_oneline.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None, export_type='tab')
assert exp[
0] == '''ACTGAT(A)\tL3\tAR025\tanterior\trnaSeq\taWL3.2\t"5.8 ng/uL (30 nM) 08/04/2013"\tcell\t297\t37478754\tdmel\taWL3.2/aWL3.2_4204_ACTGAT_transcript.gtf\t2\tMATE1_SENSE\t2x75D\t2\tlongPolyA\t100\twing\tgtf\tTranscriptFB554'''
def test_export_oneline():
"""Test export one known line"""
i = Index('test/data/index_oneline.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export()
assert exp[
0] == '''aWL3.2/aWL3.2_4204_ACTGAT_transcript.gtf\tLIBRARY_ID=aWL3.2; RNA_quantity=100; barcode=AR025; cell=anterior; dataType=rnaSeq; developmental_point=L3; library_Bioanalyser="5.8 ng/uL (30 nM) 08/04/2013"; localization=cell; max_peak=297; n_sequences=37478754; organism=dmel; pool_ID=2; readStrand=MATE1_SENSE; readType=2x75D; replicate=2; rnaExtract=longPolyA; sequence=ACTGAT(A); tissue=wing; type=gtf; view=TranscriptFB554;'''
def test_export_oneline_no_map():
"""Test export one known line"""
i = Index('test/data/index_oneline.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None)
assert exp[
0] == '''aWL3.2/aWL3.2_4204_ACTGAT_transcript.gtf\tadaptor=ACTGAT(A); age=L3; barcode=AR025; cell=anterior; dataType=rnaSeq; labExpId=aWL3.2; libBio="5.8 ng/uL (30 nM) 08/04/2013"; localization=cell; maxPeak=297; nReads=37478754; organism=dmel; poolId=2; readStrand=MATE1_SENSE; readType=2x75D; replicate=2; rnaExtract=longPolyA; rnaQuantity=100; tissue=wing; type=gtf; view=TranscriptFB554;'''
def test_export_no_map():
"""Test export"""
i = Index('test/data/index.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None)
assert len(exp) == 216
assert 'labExpId' in exp[0]
assert 'fileinfo' not in exp[0]
def test_export():
"""Test export"""
i = Index('test/data/index.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export()
assert type(exp) == list
assert len(exp) == 216
assert 'LIBRARY_ID' in exp[0]
def test_lookup_more_types_index():
"""Test export"""
i = Index('test/data/index_one_gfs.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
result = i.lookup(type='gtf')
assert result != None
assert result.datasets != {}
assert result.export()[0][0] != '.'
def test_open_empty():
"""Open empty index"""
i = Index()
assert i is not None
# Disable warning about:
# - missing pytest.raises
# - statement with no effect
# pylint: disable=E1101,W0104
with pytest.raises(AttributeError):
i.open()
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_lookup_no_path():
i = Index('test/data/index.txt')
i.set_format('test/data/format.json')
i.open()
assert i.datasets.get('WLP.2') is not None
selected = i.lookup(id='WLP.2')
assert selected.datasets != i.datasets
assert len(selected.datasets) == 1
dataset = selected.datasets.get('WLP.2')
assert dataset is not None
dataset.id = 'WLP.2'
def test_export_ol_no_map_tab_all_header():
"""Test export"""
i = Index('test/data/index_oneline.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None, export_type='tab', header=True)
assert exp[
0] == 'adaptor\tage\tbarcode\tcell\tdataType\tlabExpId\tlibBio\tlocalization\tmaxPeak\tnReads\torganism\tpath\tpoolId\treadStrand\treadType\treplicate\trnaExtract\trnaQuantity\ttissue\ttype\tview'
assert exp[
1] == '''ACTGAT(A)\tL3\tAR025\tanterior\trnaSeq\taWL3.2\t"5.8 ng/uL (30 nM) 08/04/2013"\tcell\t297\t37478754\tdmel\taWL3.2/aWL3.2_4204_ACTGAT_transcript.gtf\t2\tMATE1_SENSE\t2x75D\t2\tlongPolyA\t100\twing\tgtf\tTranscriptFB554'''
def test_export_ol_no_map_tab_repeated_tags_header():
"""Test export"""
i = Index('test/data/index_oneline.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None,
export_type='tab',
tags=['id', 'id', 'path'],
header=True)
assert exp[0] == 'labExpId\tlabExpId\tpath'
assert exp[1] == 'aWL3.2\taWL3.2\taWL3.2/aWL3.2_4204_ACTGAT_transcript.gtf'
def test_export_no_map_tab_repeated_tags():
"""Test export tab output with repeated tags"""
i = Index('test/data/index.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None,
export_type='tab',
tags=['id', 'id', 'path'],
hide_missing=True)
assert len(exp) == 200
assert exp[
0] == 'EL3.1\tEL3.1\t/users/rg/epalumbo/projects/ERC/fly/bp.pipeline/EL3.1/EL3.1_5355_ATCACG.minusRaw.bigwig'
def test_export_no_map_tab_path_template():
"""Test export tab output with path template"""
i = Index('test/data/index.txt')
assert i is not None
i.set_format('test/data/format.json')
i.open()
exp = i.export(map=None,
export_type='tab',
tags=['path', '{dirname}/{id}.{view}.{ext}'],
hide_missing=True)
assert len(exp) == 200
assert exp[
0] == '/users/rg/epalumbo/projects/ERC/fly/bp.pipeline/EL3.1/EL3.1_5355_ATCACG.minusRaw.bigwig\t/users/rg/epalumbo/projects/ERC/fly/bp.pipeline/EL3.1/EL3.1.MinusRawSignal.bigwig'
def open_index(config):
"""Open index file from config dictionary"""
i = Index()
index = config.get('index')
idx_format = config.get('format')
try:
i.set_format(idx_format)
i.open(index)
except csv.Error:
index = config.get('index')
i.open(index)
except AttributeError:
pass
return i
def open_index(config):
"""Open index file from config dictionary"""
i = Index()
index = config.get('index')
idx_format = config.get('format')
try:
i.set_format(idx_format)
i.open(index)
except csv.Error:
index = config.get('index')
i.open(index)
except AttributeError:
pass
return i
def test_replicates():
"""Test merged datasets"""
i = Index('test/data/index.txt')
i.set_format('test/data/format.json')
dsid = i.format.get('id', 'id')
i.open()
reps = i.find_replicates(id="EWP.1,EWP.2")
dataset = reps[0]
others = reps[1:]
merged = dataset.merge(others, dsid=dsid)
for key in merged.get_meta_tags():
vals = [getattr(d, key) for d in reps]
if len(set(vals)) > 1:
if key == dsid:
vals = ','.join(vals)
assert getattr(merged, key) == vals
else:
assert getattr(merged, key) == vals[0]