def test_fetches_line_content_for_key(sample_data):
expected = [[
'A011', '', 'A011', 'Paratyphoid fever A', 'Paratyphoid fever A',
'Paratyphoid fever A'
]]
reader = weetabix.Reader(sample_data)
rows = list(reader.fetch('A011'))
assert rows == expected, 'returned expected row content'
def test_gets_correct_number_of_lines_for_each_key(sample_data):
expected = (('A010', 2), ('A011', 1), ('A012', 1), ('A013', 1),
('A014', 1), ('A02', 2), ('W5622', 1))
reader = weetabix.Reader(sample_data)
for k, count in expected:
rows = reader.fetch(k)
assert len(
list(rows)
) == count, 'found expected number of rows for key {}'.format(k)
def test_writer_indexes_tsv(sample_data_tsv):
# Index the file on exact contents of column 1
writer = weetabix.Writer(sample_data_tsv, skip_lines=1, delimiter='\t')
writer.make_index(1)
keys = list(writer.get_entries())
assert keys == ['2', '1'], 'Indexed correct keys for tab delimited file'
reader = weetabix.Reader(sample_data_tsv)
first_row = next(reader.fetch('2'))
assert len(first_row) == 5, 'Reader was able to parse tab delimited file'
def test_nonstrict_mode_returns_empty_list_for_absent_key(sample_data):
reader = weetabix.Reader(sample_data)
result = reader.fetch('not_a_key', strict=False)
assert result == []
def test_strict_mode_fails_if_key_not_in_index(sample_data):
with pytest.raises(KeyError):
reader = weetabix.Reader(sample_data)
reader.fetch('not_a_key', strict=True)
def test_uses_secondary_index(sample_data, secondary_index):
reader = weetabix.Reader(sample_data, index_fn=secondary_index)
keys = list(reader.get_entries())
assert len(keys) == 2
assert keys == ['A', 'W']