This is an automated email from the ASF dual-hosted git repository.
fokko pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new 3f44dfe7 Lowercase bool values in table properties (#924)
3f44dfe7 is described below
commit 3f44dfe711e96beda6aa8622cf5b0baffa6eb0f2
Author: Soumya Ghosh <[email protected]>
AuthorDate: Sun Jul 14 00:35:38 2024 +0530
Lowercase bool values in table properties (#924)
---
pyiceberg/types.py | 2 +-
tests/cli/test_console.py | 9 ++++++---
tests/test_types.py | 12 ++++++++++++
3 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/pyiceberg/types.py b/pyiceberg/types.py
index cd662c73..97ddea0e 100644
--- a/pyiceberg/types.py
+++ b/pyiceberg/types.py
@@ -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]:
diff --git a/tests/cli/test_console.py b/tests/cli/test_console.py
index 92a7f80c..e55ff9a9 100644
--- a/tests/cli/test_console.py
+++ b/tests/cli/test_console.py
@@ -83,7 +83,7 @@ TEST_TABLE_SCHEMA = Schema(
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"}
@@ -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:
@@ -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:
diff --git a/tests/test_types.py b/tests/test_types.py
index 1e386bb7..52bdce4d 100644
--- a/tests/test_types.py
+++ b/tests/test_types.py
@@ -44,6 +44,7 @@ from pyiceberg.types import (
TimeType,
UUIDType,
strtobool,
+ transform_dict_value_to_str,
)
non_parameterized_types = [
@@ -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)
