def testRightVersion(self):
repo = datarepo.SqlDataRepository(self._repoPath)
repo.open(datarepo.MODE_WRITE)
repo.initialise()
anotherRepo = datarepo.SqlDataRepository(self._repoPath)
anotherRepo.open(datarepo.MODE_READ)
self.assertEqual(anotherRepo._schemaVersion, str(repo.version))
def testWrongVersion(self):
repo = datarepo.SqlDataRepository(self._repoPath)
repo.version = datarepo.SqlDataRepository.SchemaVersion(
"wrong.version")
repo.open(datarepo.MODE_WRITE)
repo.initialise()
anotherRepo = datarepo.SqlDataRepository(self._repoPath)
with self.assertRaises(
exceptions.RepoSchemaVersionMismatchException):
anotherRepo.open(datarepo.MODE_READ)
def setUp(self):
dataRepository = datarepo.SqlDataRepository(paths.testDataRepo)
dataRepository.open(datarepo.MODE_READ)
self.backend = backend.Backend(dataRepository)
self.dataset = self.backend.getDataRepository().getDatasets()[0]
self.dataset_id = self.dataset.getId()
self.access_map = {self.dataset.getLocalId(): 4}
def __enter__(self):
self._repo = repo.SqlDataRepository(self._filename)
self._repo.open(repo.MODE_WRITE)
if not os.path.isfile(self._filename):
self._repo.initialise()
return self
def __init__(self, rnaQuantificationLocalId, baseDir):
self._dataset = datasets.Dataset(_datasetName)
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._referenceSet = references.AbstractReferenceSet("test_rs")
rnaQuantificationId = rnaQuantificationLocalId[:-3] # remove '.db'
super(RnaQuantificationTest, self).__init__(
rnaQuantificationId, baseDir)
def setUp(self):
self._maxDiff = None
repoPath = paths.testDataRepo
self._dataUrl = moduleTestServer.getUrl()
dataRepository = datarepo.SqlDataRepository(repoPath)
dataRepository.open(datarepo.MODE_READ)
self._backend = backend.Backend(dataRepository)
self._client = client.LocalClient(self._backend,
serialization="application/json")
def _createContinuousSet(self):
"""
Creates a ContinuousSet from the specified directory.
"""
self._continuousSetName = "testContinuous"
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._dataset = datasets.Dataset("testDs")
self._continuousSet = continuous.readSet(
self._dataset, self._continuousSetName)
def __init__(self, featureSetLocalName, dataPath):
"""
:param localId: Name of the GFF3 resource corresponding to a pair
of files, .db and .gff3
:param dataPath: string representing full path to the .db file
:return:
"""
self._dataset = datasets.Dataset(_datasetName)
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._ontology = self._repo.getOntologyByName(paths.ontologyName)
self._referenceSet = references.AbstractReferenceSet("test_rs")
featureSetLocalName = featureSetLocalName[:-3] # remove '.db'
self._testData = _testDataForFeatureSetName[featureSetLocalName]
super(FeatureSetTests, self).__init__(featureSetLocalName, dataPath)
def _createVariantAnnotationSet(self, vcfDir):
"""
Creates a VariantAnnotationSet from the specified directory of
VCF files.
"""
self._variantSetName = "testVariantSet"
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._dataset = datasets.Dataset("testDs")
self._variantSet = variants.HtslibVariantSet(self._dataset,
self._variantSetName)
self._variantSet.populateFromDirectory(vcfDir)
self._variantAnnotationSet = variants.HtslibVariantAnnotationSet(
self._variantSet, "testVAs")
self._variantAnnotationSet.setOntology(
self._repo.getOntologyByName(paths.ontologyName))
def createRepo(self):
"""
Creates the repository for all the data we've just downloaded.
"""
repo = datarepo.SqlDataRepository(self.repoPath)
repo.open("w")
repo.initialise()
referenceSet = references.HtslibReferenceSet("GRCh37-subset")
referenceSet.populateFromFile(self.fastaFilePath)
referenceSet.setDescription("Subset of GRCh37 used for demonstration")
referenceSet.setSpeciesFromJson(
'{"id": "9606",'
+ '"term": "H**o sapiens", "source_name": "NCBI"}')
for reference in referenceSet.getReferences():
reference.setSpeciesFromJson(
'{"id": "9606",'
+ '"term": "H**o sapiens", "source_name": "NCBI"}')
reference.setSourceAccessions(
self.accessions[reference.getName()] + ".subset")
repo.insertReferenceSet(referenceSet)
dataset = datasets.Dataset("1kg-p3-subset")
dataset.setDescription("Sample data from 1000 Genomes phase 3")
repo.insertDataset(dataset)
variantSet = variants.HtslibVariantSet(dataset, "mvncall")
variantSet.setReferenceSet(referenceSet)
dataUrls = [vcfFile for vcfFile, _ in self.vcfFilePaths]
indexFiles = [indexFile for _, indexFile in self.vcfFilePaths]
variantSet.populateFromFile(dataUrls, indexFiles)
variantSet.checkConsistency()
repo.insertVariantSet(variantSet)
for sample, (bamFile, indexFile) in zip(
self.samples, self.bamFilePaths):
readGroupSet = reads.HtslibReadGroupSet(dataset, sample)
readGroupSet.populateFromFile(bamFile, indexFile)
readGroupSet.setReferenceSet(referenceSet)
repo.insertReadGroupSet(readGroupSet)
repo.commit()
repo.close()
self.log("Finished creating the repository; summary:\n")
repo.open("r")
repo.printSummary()
def __init__(self, inputDirectory, outputDirectory, force):
"""
Converts human readable dataset from compliance repository,
and translates it into a reference-server readable filesystem
with binary files.
:param inputDirectory: location of
the human readable compliance dataset
:param outputDirectory: location of
the file hierarchy suitable for deploying on the reference server
"""
self.inputDirectory = inputDirectory
self.outputDirectory = outputDirectory
self.repoPath = os.path.abspath(
os.path.join(outputDirectory, "registry.db"))
self.tempdir = None
if os.path.exists(self.outputDirectory):
if force:
utils.log("Removing existing output directory at '{}'".format(
self.outputDirectory))
shutil.rmtree(self.outputDirectory)
else:
utils.log("Output directory '{}' already exists".format(
self.outputDirectory))
utils.log("Please specify an output path that does not exist")
utils.log("Exiting...")
exit(1)
# If no input directory is specified download from GitHub
if inputDirectory is None:
utils.log("Downloading test data...")
self.tempdir = tempfile.mkdtemp()
assert (os.path.exists(self.tempdir))
url = "https://github.com/ga4gh/compliance/archive/master.zip"
filePath = os.path.join(self.tempdir, 'compliance-master.zip')
downloader = file_downloader.HttpFileDownloader(url, filePath)
downloader.download()
utils.log("Extracting test data...")
with zipfile.ZipFile(filePath, "r") as z:
z.extractall(self.tempdir)
self.inputDirectory = os.path.join(self.tempdir,
'compliance-master',
'test-data')
repo = datarepo.SqlDataRepository(self.repoPath)
self.repo = repo
def __init__(self, registryDb):
repo = datarepo.SqlDataRepository(registryDb)
repo.open(datarepo.MODE_READ)
super(HeapProfilerBackend, self).__init__(repo)
self.profiler = guppy.hpy()
def setUp(self):
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._backend = backend.Backend(self._repo)
self._client = client.LocalClient(self._backend)
def testDbFileWithoutTables(self):
repo = datarepo.SqlDataRepository(self._repoPath)
with self.assertRaises(exceptions.RepoInvalidDatabaseException):
repo.open(datarepo.MODE_READ)
def __init__(self, registryDb):
repo = datarepo.SqlDataRepository(registryDb)
repo.open(datarepo.MODE_READ)
super(CpuProfilerBackend, self).__init__(repo)
self.profiler = cProfile.Profile()
def testTextFile(self):
with open(self._repoPath, 'w') as textFile:
textFile.write('This is now a text file')
repo = datarepo.SqlDataRepository(self._repoPath)
with self.assertRaises(exceptions.RepoInvalidDatabaseException):
repo.open(datarepo.MODE_READ)
def testDirectory(self):
repoPath = makeTempDir()
repo = datarepo.SqlDataRepository(repoPath)
with self.assertRaises(exceptions.RepoInvalidDatabaseException):
repo.open(datarepo.MODE_READ)
def testNonexistentFile(self):
repo = datarepo.SqlDataRepository("aFilePathThatDoesNotExist")
with self.assertRaises(exceptions.RepoNotFoundException):
repo.open(datarepo.MODE_READ)
def setUp(self):
self._dataRepo = datarepo.SqlDataRepository(paths.testDataRepo)
self._dataRepo.open(datarepo.MODE_READ)
""")
args = parser.parse_args()
registryDb = "candig-example-data/registry.db"
if args.profile == 'heap':
backendClass = HeapProfilerBackend
backend = backendClass(registryDb)
args.repeatLimit = 1
args.pageLimit = 1
elif args.profile == 'cpu':
backendClass = CpuProfilerBackend
backend = backendClass(registryDb)
else:
repo = datarepo.SqlDataRepository(registryDb)
repo.open(datarepo.MODE_READ)
backend = backend.Backend(repo)
# Get our list of callSetids
callSetIds = args.callSetIds
if callSetIds != []:
callSetIds = None
if args.callSetIds != "*":
callSetIds = args.callSetIds.split(",")
minTime = benchmarkOneQuery(_heavyQuery(args.variantSetId, callSetIds),
args.repeatLimit, args.pageLimit)
print(minTime)
if args.profile == 'cpu':
stats = pstats.Stats(backend.profiler)