def test_parse_filename():
excel_file = 'ID8_FM3_SUMMARY_150422_AF_ML.xlsx'
data = parse_filname(excel_file)
assert data['id'] == 'ID8'
assert data['date'].year == 15
assert data['date'].month == 4
assert data['date'].day == 22
def post_samples(input_type, input_path, rs_stream, prepend=None,
include_key=None, force=False):
"""Add samples from VCF or Excel sheet."""
if input_type == 'vcf':
logger.info("loading genotypes from VCF: {}".format(input_path))
gt_samples = load_vcf(db, input_path, rs_stream,
experiment='sequencing', force=force)
source_id = input_path
elif input_type == 'excel':
logger.info("loading genotypes from Excel: {}".format(input_path))
file_name = path(input_path).normpath().basename()
source_data = parse_filname(file_name)
source_id = source_data['id']
sample_prepend = prepend or "{}-{}".format(source_id, include_key or '')
gt_samples = maf_results(db, input_path, prepend=sample_prepend,
include_key=include_key)
else:
raise ValueError("'input_type' must be either 'vcf' or 'excel'")
return dict(samples=gt_samples, source_id=source_id)
