def test_should_write_unicode_file(self):
with TemporaryDirectory() as path:
file_list_path = os.path.join(path, 'out.lst')
save_csv_or_tsv_file_list(file_list_path, [UNICODE_FILE_1],
column='url')
assert load_csv_or_tsv_file_list(file_list_path,
column='url') == [UNICODE_FILE_1]
def test_should_write_multiple_file_paths(self):
with TemporaryDirectory() as path:
file_list_path = os.path.join(path, 'out.csv')
save_csv_or_tsv_file_list(file_list_path, [FILE_1, FILE_2],
column='url')
assert load_csv_or_tsv_file_list(file_list_path,
column='url') == [FILE_1, FILE_2]
def test_should_raise_exception_if_column_name_is_invalid(self):
with pytest.raises(ValueError):
with NamedTemporaryFile('w') as f:
f.write('\n'.join(['url', FILE_1, FILE_2]))
f.flush()
assert load_csv_or_tsv_file_list(f.name,
'xyz') == [FILE_1, FILE_2]
def test_should_read_unicode_file(self):
with NamedTemporaryFile('wb') as f:
f.write('\n'.join(['url', UNICODE_FILE_1]).encode('utf-8'))
f.flush()
assert load_csv_or_tsv_file_list(f.name, 'url') == [UNICODE_FILE_1]
def test_should_read_multiple_file_paths_from_file_without_header(self):
with NamedTemporaryFile('w') as f:
f.write('\n'.join([FILE_1, FILE_2]))
f.flush()
assert load_csv_or_tsv_file_list(f.name, 0,
header=False) == [FILE_1, FILE_2]
def test_should_read_multiple_file_paths_from_file_with_header_using_column_index(
self):
with NamedTemporaryFile('w') as f:
f.write('\n'.join(['url', FILE_1, FILE_2]))
f.flush()
assert load_csv_or_tsv_file_list(f.name, 0) == [FILE_1, FILE_2]
def test_should_apply_limit(self):
with NamedTemporaryFile('w') as f:
f.write('\n'.join(['url', FILE_1, FILE_2]))
f.flush()
assert load_csv_or_tsv_file_list(f.name, 'url',
limit=1) == [FILE_1]
