def __init__(self, metadata_file):
conf = os.path.join(ROOT_DIR, 'etc', 'eva_project_conf.yaml')
self.reader = XlsxReader(metadata_file, conf)
self.metadata_file=metadata_file
def setUp(self):
self.xls_reader = XlsxReader(self.metadata_file, self.eva_xls_reader_conf)
class EvaXlsxReader(AppLogger):
def __init__(self, metadata_file):
conf = os.path.join(ROOT_DIR, 'etc', 'eva_project_conf.yaml')
self.reader = XlsxReader(metadata_file, conf)
self.metadata_file=metadata_file
def _get_all_rows(self, active_sheet):
self.reader.active_worksheet = active_sheet
rows = []
try:
r = self.reader.next()
while r:
rows.append(r)
r = self.reader.next()
rows.append(r)
except StopIteration:
pass
return rows
@cached_property
def project(self):
self.reader.active_worksheet = 'Project'
try:
return self.reader.next()
except StopIteration:
self.error('No project was found in the spreadsheet %s', self.metadata_file)
@cached_property
def submitters(self):
return self._get_all_rows('Submitter Details')
@cached_property
def analysis(self):
return self._get_all_rows('Analysis')
@cached_property
def samples(self):
return self._get_all_rows('Sample')
@cached_property
def files(self):
return self._get_all_rows('Files')
@cached_property
def project_title(self):
if self.project:
return self.project.get('Project Title')
@property
def analysis_titles(self):
return [a.get('Analysis Title') for a in self.analysis]
@property
def references(self):
return list(set([a.get('Reference') for a in self.analysis if a.get('Reference')]))
@property
def samples_per_analysis(self):
samples_per_analysis = defaultdict(list)
for row in self.samples:
samples_per_analysis[row.get('Analysis Alias')].append(row)
return samples_per_analysis
@property
def files_per_analysis(self):
files_per_analysis = defaultdict(list)
for row in self.files:
files_per_analysis[row.get('Analysis Alias')].append(row)
return files_per_analysis
class TestXlsxReader(TestCase):
metadata_file = os.path.join(os.path.dirname(__file__), 'resources',
'metadata.xlsx')
eva_xls_reader_conf = os.path.join(os.path.dirname(__file__), 'resources',
'test_metadata_fields.yaml')
def setUp(self):
self.xls_reader = XlsxReader(self.metadata_file,
self.eva_xls_reader_conf)
def test_valid_worksheets(self):
worksheets = self.xls_reader.valid_worksheets()
assert isinstance(worksheets, list)
assert set(worksheets) == {'Project', 'Sample', 'Analysis'}
def test_get_valid_conf_keys(self):
worksheets = self.xls_reader.valid_worksheets()
assert isinstance(worksheets, list)
assert set(worksheets) == {'Project', 'Sample', 'Analysis'}
def test_next_row(self):
self.xls_reader.active_worksheet = 'Sample'
row = self.xls_reader.next()
assert isinstance(row, dict)
assert row == {
'Analysis Alias': 'GAE',
'Sample Accession': None,
'Sample ID': None,
'Sample Name': 'S1',
'Sampleset Accession': None,
'Title': 'Sample 1',
'row_num': 4
}
self.xls_reader.active_worksheet = 'Project'
row = self.xls_reader.next()
assert isinstance(row, dict)
assert row == {
'Project Title': 'Greatest project ever',
'Project Alias': 'GPE',
'Publication(s)': None,
'Parent Project(s)': None,
'Child Project(s)': None,
'row_num': 2
}
def test_get_rows(self):
self.xls_reader.active_worksheet = 'Sample'
rows = self.xls_reader.get_rows()
assert isinstance(rows, list)
assert len(rows) == 100
assert rows[0] == {
'Analysis Alias': 'GAE',
'Sample Accession': None,
'Sample ID': None,
'Sample Name': 'S1',
'Sampleset Accession': None,
'Title': 'Sample 1',
'row_num': 4
}