def test_next_row():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx',
'data/T2D_xls2xml_v1.conf')
xls_reader.set_current_conf_key('Sample')
row = xls_reader.next()
assert isinstance(row, dict)
assert 0 == cmp(
row, {
'Hispanic or Latino; of Spanish origin': None,
'Phenotype': 'MeSH:D006262',
'row_num': 2,
'Description': 'Male normal',
'Center_name': 'WTGC cambridge',
'Case_Control': 'Control',
'T2D': 0L,
'Analysis_alias': 'AN001',
'Geno_ID': None,
'Year of first visit': None,
'Cell Type': 'Blood',
'Maternal_id': 'SAM111113',
'Gender': 'male',
'Subject_ID': 'SAM111111',
'Paternal_id': 'SAM111115',
'Cohort ID': 'CO1111',
'Novel Attributes': None,
'Ethnicity Description': None,
'Year of Birth': 1986L,
'Sample_ID': 'SAM111111',
'Age': 31L,
'Ethnicity': 'EUWH'
})
def test_validate_file():
validation_schema = 'data/T2D_xls2xml_v1.schema'
tsv_reader = TSVReader('data/example_samples.tsv', 'data/T2D_xls2xml_v1.conf', 'Sample')
assert utils.validate_file(tsv_reader, validation_schema)
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
xls_reader.set_current_conf_key('Sample')
assert utils.validate_file(xls_reader, validation_schema)
def test_validate_xls():
validation_schema = '../T2D_xlsx.schema'
xls_reader = XLSReader(
'data/example_AMP_T2D_Submission_form_V2_DB_12_03_18.xlsx',
'../T2D_xlsx.conf')
assert xls_reader.is_valid()
assert utils.validate_file(xls_reader, validation_schema)
def test_write_empty_xml():
rows = []
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
assert utils.extract_rows(xls_reader, 'File', 'data/T2D_xls2xml_v1.schema', rows)
input_xml = utils.rows_to_xml(rows, 'File')
transformed_xml = utils.transform_xml(input_xml, 'data/T2D_xls2xml_v1.xslt')
assert transformed_xml.getroot() is None # to make sure the transformed_xml is empty
with open('data/out_empty.xml', 'w') as xml_file:
utils.save_xml(transformed_xml, xml_file)
def test_transform_xml():
rows = []
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
assert utils.extract_rows(xls_reader, 'Sample', 'data/T2D_xls2xml_v1.schema', rows)
input_xml = utils.rows_to_xml(rows, 'Sample')
output_xml = utils.transform_xml(input_xml, 'data/T2D_xls2xml_v1.xslt')
with open('data/example_samples.xml') as example_xml:
assert example_xml.readline() == "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
assert etree.tostring(output_xml, pretty_print=True) == example_xml.read()
def test_xls2xml_study():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2_DB_12_03_18.xlsx',
'../T2D_xlsx.conf')
xls_readers = [ ('Project', xls_reader) ]
output_xml = utils.multiple_objects_to_xml(xls_readers, '../T2D_xlsx.schema',
'../T2D_xls2xml.xslt')
with open('data/example_study.xml', 'r') as study_example:
assert study_example.readline()
assert etree.tostring(output_xml, pretty_print=True) == study_example.read()
def test_xls2xml_sample():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2_DB_12_03_18.xlsx',
'../T2D_xlsx.conf')
conf_keys = ['Sample', 'Cohort']
xls_readers = [ (key, xls_reader) for key in conf_keys ]
output_xml = utils.multiple_objects_to_xml(xls_readers, '../T2D_xlsx.schema',
'../T2D_xls2xml.xslt')
with open('data/example_sample.xml', 'r') as sample_example:
assert sample_example.readline()
assert etree.tostring(output_xml, pretty_print=True) == sample_example.read()
def test_save_xml():
rows = []
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
assert utils.extract_rows(xls_reader, 'Sample', 'data/T2D_xls2xml_v1.schema', rows)
input_xml = utils.rows_to_xml(rows, 'Sample')
transformed_xml = utils.transform_xml(input_xml, 'data/T2D_xls2xml_v1.xslt')
io_stream = StringIO()
utils.save_xml(transformed_xml, io_stream)
io_stream.seek(0)
assert io_stream.read() == open('data/example_samples.xml').read()
io_stream.close()
def test_multiple_sheets_to_xml():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
output_xml = utils.multiple_sheets_to_xml(xls_reader, str('Analysis,File').split(','),
'data/T2D_xls2xml_v1.schema', 'data/T2D_xls2xml_v2.xslt')
with open('data/example_analysis.xml', 'r') as analysis_example:
assert analysis_example.readline()
assert etree.tostring(output_xml, pretty_print=True) == analysis_example.read()
with pytest.raises(Exception):
utils.multiple_sheets_to_xml(xls_reader, str('Exception,Expected').split(','),
'data/T2D_xls2xml_v1.schema', 'data/T2D_xls2xml_v2.xslt')
def test_xls2xml_sample():
xls_reader = XLSReader(
'data/example_AMP_T2D_Submission_form_V2_DB_12_03_18.xlsx',
'../T2D_xlsx.conf')
output_xml = utils.multiple_sheets_to_xml(xls_reader,
str('Sample,Cohort').split(','),
'../T2D_xlsx.schema',
'../T2D_xls2xml.xslt')
with open('data/example_sample.xml', 'r') as sample_example:
assert sample_example.readline()
assert etree.tostring(output_xml,
pretty_print=True) == sample_example.read()
def test_valid_data():
validator = MetadataValidator('data/T2D_xls2xml_v1.schema')
reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx',
'data/T2D_xls2xml_v1.conf')
reader.active_worksheet = 'Sample'
row = reader.next()
assert validator.validate_data(row, 'Sample')
reader.active_worksheet = 'Analysis'
row = reader.next()
assert validator.validate_data(row, 'Analysis')
reader = TSVReader('data/example_samples.tsv', 'data/T2D_xls2xml_v1.conf',
'Sample')
row = reader.next()
assert validator.validate_data(row, 'Sample')
def test_rows_to_xml():
rows = []
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
assert utils.extract_rows(xls_reader, 'Sample', 'data/T2D_xls2xml_v1.schema', rows)
xml = utils.rows_to_xml(rows, 'Sample')
assert isinstance(xml, etree._Element)
assert xml.tag == 'SampleSet'
assert len(rows) == len(xml)
for row, child in zip(rows, xml):
assert child.tag == 'Sample'
assert {header : str(row.get(header, '')) for header in row} !=\
{e.tag: e.text for e in child}
assert {utils.header_to_xml_tag(header) : str('' if row.get(header, '') is None else row.get(header, ''))
for header in row} == {e.tag : e.text for e in child}
def test_set_current_conf_key():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx',
'data/T2D_xls2xml_v1.conf')
active_worksheet = xls_reader.active_worksheet
assert active_worksheet is None
xls_reader.set_current_conf_key('Sample')
active_worksheet = xls_reader.active_worksheet
assert active_worksheet == 'Sample'
xls_reader.set_current_conf_key('Analysis')
active_worksheet = xls_reader.active_worksheet
assert active_worksheet == 'Analysis'
def test_extract_rows():
validation_schema = 'data/T2D_xls2xml_v1.schema'
rows = []
tsv_reader = TSVReader('data/example_samples.tsv', 'data/T2D_xls2xml_v1.conf', 'Sample')
assert utils.extract_rows(tsv_reader, 'Sample', validation_schema, rows)
assert isinstance(rows, list)
assert 6 == len(rows)
tsv_reader = TSVReader('data/example_samples.tsv', 'data/T2D_xls2xml_v1.conf', 'Sample')
for a, b in zip(rows, tsv_reader):
assert 0 == cmp(a, b)
rows = []
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
assert utils.extract_rows(xls_reader, 'Sample', validation_schema, rows)
assert isinstance(rows, list)
assert 6 == len(rows)
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx', 'data/T2D_xls2xml_v1.conf')
xls_reader.set_current_conf_key('Sample')
for a, b in zip(rows, xls_reader):
assert 0 == cmp(a, b)
rows = []
assert not utils.extract_rows(xls_reader, 'FalseExpected', validation_schema, rows)
def test_valid_worksheets():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx',
'data/T2D_xls2xml_v1.conf')
worksheets = xls_reader.valid_worksheets()
assert isinstance(worksheets, list)
assert set(worksheets) == {'Sample', 'Analysis', 'File'}
def test_get_current_headers():
xls_reader = XLSReader('data/example_AMP_T2D_Submission_form_V2.xlsx',
'data/T2D_xls2xml_v1.conf')
xls_reader.set_current_conf_key('Sample')
headers = xls_reader.get_current_headers()
assert isinstance(headers, list)
assert set(headers) == {
u'Sample_ID', u'Subject_ID', u'Geno_ID', u'Phenotype', u'Gender',
u'Analysis_alias', u'Cohort ID', u'Ethnicity',
u'Ethnicity Description', u'T2D', u'Case_Control', u'Description',
u'Center_name', u'Hispanic or Latino; of Spanish origin', u'Age',
u'Year of Birth', u'Year of first visit', u'Cell Type', u'Maternal_id',
u'Paternal_id', u'Novel Attributes'
}
xls_reader.set_current_conf_key('Analysis')
headers = xls_reader.get_current_headers()
assert isinstance(headers, list)
assert set(headers) == {
u'Analysis_name', u'Analysis_alias', u'Title', u'Description',
u'Project_name', u'Experiment_type', u'Platform',
u'Standard_refname or Sequence_accession', u'Imputation',
u'Sequence_accession_label', u'External_link', u'Software',
u'Pipeline Description', u'Run Accession(s)', u'Center_name',
u'Analysis_date'
}
xls_reader.set_current_conf_key('ExceptionExpected')
with pytest.raises(Exception):
xls_reader.get_current_headers()
