Feature Request / Improvement
Make sure that the UnaryPredicate predicate can be serialized to JSON:
|
class UnaryPredicate(UnboundPredicate[Any], ABC): |
|
def bind(self, schema: Schema, case_sensitive: bool = True) -> BoundUnaryPredicate[Any]: |
|
bound_term = self.term.bind(schema, case_sensitive) |
|
return self.as_bound(bound_term) |
|
|
|
def __repr__(self) -> str: |
|
"""Return the string representation of the UnaryPredicate class.""" |
|
return f"{str(self.__class__.__name__)}(term={repr(self.term)})" |
|
|
|
@property |
|
@abstractmethod |
|
def as_bound(self) -> Type[BoundUnaryPredicate[Any]]: ... |
This predicate has four implementations: IsNull, NotNull, IsNaN, and NotNan, and translates to:
{
"type": "is-null" // Or not-null, is-nan, not-nan
"term": str, // The column name
}We use Pydantic for JSON serialization, which can be enabled by deriving from the IcebergBaseModel:
|
class PartitionSpec(IcebergBaseModel): |
Example tests can be found here:
|
def test_serialize_partition_spec() -> None: |
|
partitioned = PartitionSpec( |
|
PartitionField(source_id=1, field_id=1000, transform=TruncateTransform(width=19), name="str_truncate"), |
|
PartitionField(source_id=2, field_id=1001, transform=BucketTransform(num_buckets=25), name="int_bucket"), |
|
spec_id=3, |
|
) |
|
assert ( |
|
partitioned.model_dump_json() |
|
== """{"spec-id":3,"fields":[{"source-id":1,"field-id":1000,"transform":"truncate[19]","name":"str_truncate"},{"source-id":2,"field-id":1001,"transform":"bucket[25]","name":"int_bucket"}]}""" |
|
) |
|
|
|
|
|
def test_deserialize_unpartition_spec() -> None: |
|
json_partition_spec = """{"spec-id":0,"fields":[]}""" |
|
spec = PartitionSpec.model_validate_json(json_partition_spec) |
|
|
|
assert spec == PartitionSpec(spec_id=0) |
