def test_parse_out_path_valid(self):
# Function should not affect valid length filenames and paths.
normal_filename = 'document'
parsedPath = ScraperUtils.parse_out_path('C:\\Example\\Path',
normal_filename, 'pdf')
assert parsedPath == os.path.join(
'C:\\Example\\Path', '{}.{}'.format(normal_filename, 'pdf'))
def test_parse_out_path_shortening(self):
# 260 characters long before the extension. This is an invalid filename in Windows.
filename_too_long = '01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789'
parsed_path = ScraperUtils.parse_out_path(os.getcwd(),
filename_too_long, 'txt')
try:
open(parsed_path, 'w')
os.remove(parsed_path)
except OSError:
pytest.fail('parse_out_path() generates an invalid file path.')
def test_parse_out_path_correct_length(self):
# 260 characters long before the extension. This is an invalid filename in Windows.
filename_too_long = '01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789'
parsed_path = ScraperUtils.parse_out_path(os.getcwd(),
filename_too_long, 'txt')
assert len(parsed_path) <= 256
def test_parse_out_path_filename_extension_shortening(self):
# 252 characters long, but with the .pdf extension it becomes 256 characters long - one too many.
filename = '012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901'
parsed_filename = ScraperUtils.parse_out_path('', filename, 'pdf')
assert parsed_filename == '{}.{}'.format(filename[:-1], 'pdf')
def test_filename_invalid(self):
filename = None
parsed_path = ScraperUtils.parse_out_path(r'C:\\Example\\Path',
filename, 'pdf')
assert parsed_path == os.path.join(r'C:\\Example\\Path', '.pdf')
def test_parse_out_path_illegal_characters(self):
filename_invalid_chars = 't<>:e"/s\\t|?n*ame'
assert ScraperUtils.parse_out_path('', filename_invalid_chars,
'pdf') == os.path.join(
'', 'testname.pdf')