Skip to content

Set boolean values in table properties to lowercase string #924

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 13, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyiceberg/types.py
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ def transform_dict_value_to_str(dict: Dict[str, Any]) -> Dict[str, str]:
for key, value in dict.items():
if value is None:
raise ValueError(f"None type is not a supported value in properties: {key}")
return {k: str(v) for k, v in dict.items()}
return {k: str(v).lower() if isinstance(v, bool) else str(v) for k, v in dict.items()}


def _parse_decimal_type(decimal: Any) -> Tuple[int, int]:
Expand Down
9 changes: 6 additions & 3 deletions tests/cli/test_console.py
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ def mock_datetime_now(monkeypatch: pytest.MonkeyPatch) -> None:
NestedField(3, "z", LongType(), required=True),
)
TEST_TABLE_PARTITION_SPEC = PartitionSpec(PartitionField(name="x", transform=IdentityTransform(), source_id=1, field_id=1000))
TEST_TABLE_PROPERTIES = {"read.split.target.size": "134217728"}
TEST_TABLE_PROPERTIES = {"read.split.target.size": "134217728", "write.parquet.bloom-filter-enabled.column.x": True}
TEST_TABLE_UUID = uuid.UUID("d20125c8-7284-442c-9aea-15fee620737c")
TEST_TIMESTAMP = 1602638573874
MOCK_ENVIRONMENT = {"PYICEBERG_CATALOG__PRODUCTION__URI": "test://doesnotexist"}
Expand Down Expand Up @@ -367,7 +367,10 @@ def test_properties_get_table(catalog: InMemoryCatalog) -> None:
runner = CliRunner()
result = runner.invoke(run, ["properties", "get", "table", "default.my_table"])
assert result.exit_code == 0
assert result.output == "read.split.target.size 134217728\n"
assert (
result.output
== "read.split.target.size 134217728\nwrite.parquet.bloom-filter-enabled.column.x true \n"
)


def test_properties_get_table_specific_property(catalog: InMemoryCatalog) -> None:
Expand Down Expand Up @@ -763,7 +766,7 @@ def test_json_properties_get_table(catalog: InMemoryCatalog) -> None:
runner = CliRunner()
result = runner.invoke(run, ["--output=json", "properties", "get", "table", "default.my_table"])
assert result.exit_code == 0
assert result.output == """{"read.split.target.size": "134217728"}\n"""
assert result.output == """{"read.split.target.size": "134217728", "write.parquet.bloom-filter-enabled.column.x": "true"}\n"""


def test_json_properties_get_table_specific_property(catalog: InMemoryCatalog) -> None:
Expand Down
12 changes: 12 additions & 0 deletions tests/test_types.py
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,7 @@
TimeType,
UUIDType,
strtobool,
transform_dict_value_to_str,
)

non_parameterized_types = [
Expand Down Expand Up @@ -649,3 +650,14 @@ def test_strtobool() -> None:
for val in invalid_values:
with pytest.raises(ValueError, match=f"Invalid truth value: {val!r}"):
strtobool(val)


def test_transform_dict_value_to_str() -> None:
input_dict = {"key1": 1, "key2": 2.0, "key3": "3", "key4: ": True, "key5": False}
expected_dict = {"key1": "1", "key2": "2.0", "key3": "3", "key4: ": "true", "key5": "false"}
# valid values
assert transform_dict_value_to_str(input_dict) == expected_dict
# Null value not allowed, should raise ValueError
input_dict["key6"] = None
with pytest.raises(ValueError, match="None type is not a supported value in properties: key6"):
transform_dict_value_to_str(input_dict)