def from_path(cls, path, frequency='per_session', format=None, # @ReservedAssignment @IgnorePep8
**kwargs):
if not os.path.exists(path):
raise ArcanaUsageError(
"Attempting to read Fileset from path '{}' but it "
"does not exist".format(path))
if os.path.isdir(path):
within_exts = frozenset(
split_extension(f)[1] for f in os.listdir(path)
if not f.startswith('.'))
if format is None:
# Try to guess format
try:
format = FileFormat.by_within_dir_exts(within_exts) # @ReservedAssignment @IgnorePep8
except ArcanaFileFormatNotRegisteredError:
# Fall back to general directory format
format = directory_format # @ReservedAssignment
name = os.path.basename(path)
else:
filename = os.path.basename(path)
name, ext = split_extension(filename)
if format is None:
try:
format = FileFormat.by_ext(ext) # @ReservedAssignment @IgnorePep8
except ArcanaFileFormatNotRegisteredError as e:
raise ArcanaFileFormatNotRegisteredError(
str(e) + ", which is required to identify the "
"format of the fileset at '{}'".format(path))
return cls(name, format, frequency=frequency,
path=path, **kwargs)
def __init__(
self,
path,
type,
subject_id,
visit_id,
repository, # @ReservedAssignment @IgnorePep8
modality=None,
task=None,
checksums=None):
Fileset.__init__(self,
name=op.basename(path),
format=FileFormat.by_ext(split_extension(path)[1]),
frequency='per_session',
path=path,
subject_id=subject_id,
visit_id=visit_id,
repository=repository,
checksums=checksums)
BaseBidsFileset.__init__(self, type, modality, task)
analyze_format.set_converter(nifti_format, MrtrixConverter)
analyze_format.set_converter(nifti_gz_format, MrtrixConverter)
analyze_format.set_converter(mrtrix_image_format, MrtrixConverter)
mrtrix_image_format.set_converter(dicom_format, MrtrixConverter)
mrtrix_image_format.set_converter(nifti_format, MrtrixConverter)
mrtrix_image_format.set_converter(nifti_gz_format, MrtrixConverter)
mrtrix_image_format.set_converter(analyze_format, MrtrixConverter)
STD_IMAGE_FORMATS = [
dicom_format, nifti_format, nifti_gz_format, nifti_gz_x_format,
analyze_format, mrtrix_image_format
]
multi_nifti_gz_format = FileFormat(name='multi_nifti_gz',
extension=None,
directory=True,
within_dir_exts=['.nii.gz'])
multi_nifti_gz_format.set_converter(zip_format, UnzipConverter)
multi_nifti_gz_format.set_converter(targz_format, UnTarGzConverter)
# Tractography formats
mrtrix_track_format = FileFormat(name='mrtrix_track', extension='.tck')
# Tabular formats
rfile_format = FileFormat(name='rdata', extension='.RData')
tsv_format = FileFormat(name='tab_separated', extension='.tsv')
# matlab_format = FileFormat(name='matlab', extension='.mat')
csv_format = FileFormat(name='comma_separated', extension='.csv')
text_matrix_format = FileFormat(name='text_matrix', extension='.mat')
# Diffusion gradient-table data formats
tree = self.repository.tree()
for subj_id, visits in self.PROJECT_STRUCTURE.items():
for visit_id in visits:
session = tree.subject(subj_id).session(visit_id)
fileset = session.fileset('thousand', study=self.STUDY_NAME)
self.assertContentsEqual(fileset, targets[subj_id][visit_id],
"{}:{}".format(subj_id, visit_id))
if subj_id == 'subject1' and visit_id == 'visit3':
self.assertNotIn(
'ten', [d.name for d in session.filesets],
"'ten' should not be generated for "
"subject1:visit3 as hundred and thousand are "
"already present")
test1_format = FileFormat('test1', extension='.t1')
test2_format = FileFormat('test2',
extension='.t2',
converters={'test1': IdentityConverter})
test3_format = FileFormat('test3', extension='.t3')
FileFormat.register(test1_format)
FileFormat.register(test2_format)
FileFormat.register(test3_format)
class TestInputValidationStudy(with_metaclass(StudyMetaClass, Study)):
add_data_specs = [
AcquiredFilesetSpec('a', (test1_format, test2_format)),
AcquiredFilesetSpec('b', test3_format),
nifti_gz_format.set_converter(nifti_gz_x_format, IdentityConverter)
analyze_format.set_converter(dicom_format, MrtrixConverter)
analyze_format.set_converter(nifti_format, MrtrixConverter)
analyze_format.set_converter(nifti_gz_format, MrtrixConverter)
analyze_format.set_converter(mrtrix_image_format, MrtrixConverter)
mrtrix_image_format.set_converter(dicom_format, MrtrixConverter)
mrtrix_image_format.set_converter(nifti_format, MrtrixConverter)
mrtrix_image_format.set_converter(nifti_gz_format, MrtrixConverter)
mrtrix_image_format.set_converter(analyze_format, MrtrixConverter)
STD_IMAGE_FORMATS = [dicom_format, nifti_format, nifti_gz_format,
nifti_gz_x_format, analyze_format, mrtrix_image_format]
multi_nifti_gz_format = FileFormat(name='multi_nifti_gz', extension=None,
directory=True, within_dir_exts=['.nii.gz'])
multi_nifti_gz_format.set_converter(zip_format, UnzipConverter)
multi_nifti_gz_format.set_converter(targz_format, UnTarGzConverter)
# Tractography formats
mrtrix_track_format = FileFormat(name='mrtrix_track', extension='.tck')
# Tabular formats
rfile_format = FileFormat(name='rdata', extension='.RData')
tsv_format = FileFormat(name='tab_separated', extension='.tsv')
# matlab_format = FileFormat(name='matlab', extension='.mat')
csv_format = FileFormat(name='comma_separated', extension='.csv')
text_matrix_format = FileFormat(name='text_matrix', extension='.mat')
# Diffusion gradient-table data formats
fsl_bvecs_format = FileFormat(name='fsl_bvecs', extension='.bvec')
import os
import os.path as op
from arcana.data.file_format import text_format
from arcana.analysis import Analysis, AnalysisMetaClass
from arcana.data import (
Fileset, InputFilesetSpec, FilesetSpec, Field)
from arcana.utils.testing import BaseMultiSubjectTestCase
from arcana.repository import Tree
from future.utils import with_metaclass
from arcana.utils.testing import BaseTestCase
from arcana.data.file_format import FileFormat
# A dummy format that contains a header
with_header_format = FileFormat(name='with_header', extension='.whf',
aux_files={'header': '.hdr'})
class DummyAnalysis(with_metaclass(AnalysisMetaClass, Analysis)):
add_data_specs = [
InputFilesetSpec('source1', text_format),
InputFilesetSpec('source2', text_format),
InputFilesetSpec('source3', text_format),
InputFilesetSpec('source4', text_format,
optional=True),
FilesetSpec('sink1', text_format, 'dummy_pipeline'),
FilesetSpec('sink3', text_format, 'dummy_pipeline'),
FilesetSpec('sink4', text_format, 'dummy_pipeline'),
FilesetSpec('subject_sink', text_format, 'dummy_pipeline',
frequency='per_subject'),
# Import TestExistingPrereqs study to test it on XNAT
sys.path.insert(0, op.join(op.dirname(__file__), '..', 'study'))
import test_study # @UnresolvedImport @IgnorePep8
sys.path.pop(0)
# Import test_local to run TestProjectInfo on XNAT using TestOnXnat mixin
sys.path.insert(0, op.join(op.dirname(__file__)))
import test_directory # @UnresolvedImport @IgnorePep8
sys.path.pop(0)
logger = logging.getLogger('arcana')
dicom_format = FileFormat(name='dicom',
extension=None,
directory=True,
within_dir_exts=['.dcm'])
try:
SERVER = os.environ['ARCANA_TEST_XNAT']
except KeyError:
SERVER = None
SKIP_ARGS = (SERVER is None, "Skipping as ARCANA_TEST_XNAT env var not set")
class DummyStudy(with_metaclass(StudyMetaClass, Study)):
add_data_specs = [
AcquiredFilesetSpec('source1', text_format),
AcquiredFilesetSpec('source2', text_format, optional=True),
def dicom_header_loader(path):
dcm_files = [f for f in os.listdir(path) if f.endswith('.dcm')]
return pydicom.dcmread(op.join(path, dcm_files[0]))
# =====================================================================
# All Data Formats
# =====================================================================
# NeuroImaging data formats
dicom_format = FileFormat(name='dicom',
extension=None,
directory=True,
within_dir_exts=['.dcm'],
alternate_names=['secondary'],
array_loader=dicom_array_loader,
header_loader=dicom_header_loader)
nifti_format = FileFormat(name='nifti',
extension='.nii',
converters={
'dicom': Dcm2niixConverter,
'analyze': MrtrixConverter,
'nifti_gz': MrtrixConverter,
'mrtrix': MrtrixConverter
},
array_loader=nifti_array_loader,
header_loader=nifti_header_loader)
nifti_gz_format = FileFormat(name='nifti_gz',
extension='.nii.gz',
'visit2': 1110.0,
'visit3': 1000.0
}
}
tree = self.dataset.tree
for subj_id, visits in self.PROJECT_STRUCTURE.items():
for visit_id in visits:
session = tree.subject(subj_id).session(visit_id)
fileset = session.fileset('thousand',
from_analysis=self.STUDY_NAME)
fileset.format = text_format
self.assertContentsEqual(fileset, targets[subj_id][visit_id],
"{}:{}".format(subj_id, visit_id))
test1_format = FileFormat('test1', extension='.t1')
test2_format = FileFormat('test2', extension='.t2')
test3_format = FileFormat('test3', extension='.t3')
test2_format.set_converter(test1_format, IdentityConverter)
class TestInputValidationAnalysis(with_metaclass(AnalysisMetaClass, Analysis)):
add_data_specs = [
InputFilesetSpec('a', (test1_format, test2_format)),
InputFilesetSpec('b', test3_format),
FilesetSpec('c', test2_format, 'identity_pipeline'),
FilesetSpec('d', test3_format, 'identity_pipeline')
]