def test_inputs_are_allowlisted():
allowlist = config.read_allowlist()
for source_file_name in os.listdir(path_utils.path_to('downloaded_dir')):
source_key = os.path.splitext(source_file_name)[0]
assert source_key in allowlist
for source_file_name in os.listdir(path_utils.path_to('scraped_dir')):
if source_file_name == 'spreadsheets':
continue
source_key = os.path.splitext(source_file_name)[0]
assert source_key in allowlist
def test_inputs_are_allowed():
allowlist = config.read_allowlist()
for source_file_name in os.listdir(DOWNLOADED_DIR):
source_key = os.path.splitext(source_file_name)[0]
assert source_key in allowlist
for source_file_name in os.listdir(SCRAPED_DIR):
if source_file_name == 'spreadsheets':
continue
source_key = os.path.splitext(source_file_name)[0]
assert source_key in allowlist
def test_spreadsheet_tabs_against_allowlist():
allowlist = config.read_allowlist()
dirpath, subdirs, filenames = next(os.walk(SPREADSHEET_DIR))
for subdir in subdirs:
subdir_path = os.path.join(dirpath, subdir)
hosp_file = os.path.join(subdir_path, 'hospitalizations.xlsx')
xl = pd.ExcelFile(hosp_file)
sheet_names = xl.sheet_names
print('File: ', hosp_file)
print('Sheet names in spreadsheet: ', sheet_names)
print('Sheet names allowed in allowlist: ', allowlist)
for sheet in sheet_names:
assert sheet in allowlist, \
"Spreadsheet {} contains a sheet name {} that is not on the allowlist.".format(hosp_file, sheet)
def test_source_files_are_allowlisted():
allowlist = config.read_allowlist()
for source_file_name in os.listdir(path_utils.path_to('sources_dir')):
source_key = os.path.splitext(source_file_name)[0]
assert source_key in allowlist
def test_data_is_allowed():
sources_with_data = config.get_sources_with_data()
allowlist = config.read_allowlist()
for source in sources_with_data:
assert source in allowlist
def test_source_files_are_allowed():
allowlist = config.read_allowlist()
for source_file_name in os.listdir(SOURCES_DIR):
source_key = os.path.splitext(source_file_name)[0]
assert source_key in allowlist