dramaticlly commented on code in PR #4717:
URL: https://github.com/apache/iceberg/pull/4717#discussion_r876496116
##########
python/src/iceberg/table/partitioning.py:
##########
@@ -29,38 +36,76 @@ class PartitionField:
name(str): The name of this partition field
"""
- def __init__(self, source_id: int, field_id: int, transform: Transform,
name: str):
- self._source_id = source_id
- self._field_id = field_id
- self._transform = transform
- self._name = name
+ source_id: int
+ field_id: int
+ transform: Transform
+ name: str
- @property
- def source_id(self) -> int:
- return self._source_id
+ def __str__(self):
+ return f"{self.field_id}: {self.name}:
{self.transform}({self.source_id})"
+
+
+@dataclass(eq=False, frozen=True)
+class PartitionSpec:
+ """
+ PartitionSpec capture the transformation from table data to partition
values
- @property
- def field_id(self) -> int:
- return self._field_id
+ Attributes:
+ schema(Schema): the schema of data table
+ spec_id(int): any change to PartitionSpec will produce a new specId
+ fields(List[PartitionField): list of partition fields to produce
partition values
+ last_assigned_field_id(int): auto-increment partition field id
starting from PARTITION_DATA_ID_START
+ """
- @property
- def name(self) -> str:
- return self._name
+ schema: Schema
+ spec_id: int
+ fields: Tuple[PartitionField]
+ last_assigned_field_id: int
+ source_id_to_fields_map: Dict[int, List[PartitionField]] =
field(init=False)
- @property
- def transform(self) -> Transform:
- return self._transform
+ def __post_init__(self):
+ source_id_to_fields_map = dict()
+ for partition_field in self.fields:
+ source_column =
self.schema.find_column_name(partition_field.source_id)
+ if not source_column:
+ raise ValueError(f"Cannot find source column:
{partition_field.source_id}")
+ existing = source_id_to_fields_map.get(partition_field.source_id,
[])
+ existing.append(partition_field)
+ source_id_to_fields_map[partition_field.source_id] = existing
+ object.__setattr__(self, "source_id_to_fields_map",
source_id_to_fields_map)
Review Comment:
based on
https://docs.python.org/3.8/library/dataclasses.html#frozen-instances and
https://stackoverflow.com/questions/53756788/how-to-set-the-value-of-dataclass-field-in-post-init-when-frozen-true
##########
python/src/iceberg/table/partitioning.py:
##########
@@ -29,38 +36,76 @@ class PartitionField:
name(str): The name of this partition field
"""
- def __init__(self, source_id: int, field_id: int, transform: Transform,
name: str):
- self._source_id = source_id
- self._field_id = field_id
- self._transform = transform
- self._name = name
+ source_id: int
+ field_id: int
+ transform: Transform
+ name: str
- @property
- def source_id(self) -> int:
- return self._source_id
+ def __str__(self):
+ return f"{self.field_id}: {self.name}:
{self.transform}({self.source_id})"
+
+
+@dataclass(eq=False, frozen=True)
+class PartitionSpec:
+ """
+ PartitionSpec capture the transformation from table data to partition
values
- @property
- def field_id(self) -> int:
- return self._field_id
+ Attributes:
+ schema(Schema): the schema of data table
+ spec_id(int): any change to PartitionSpec will produce a new specId
+ fields(List[PartitionField): list of partition fields to produce
partition values
+ last_assigned_field_id(int): auto-increment partition field id
starting from PARTITION_DATA_ID_START
+ """
- @property
- def name(self) -> str:
- return self._name
+ schema: Schema
+ spec_id: int
+ fields: Tuple[PartitionField]
+ last_assigned_field_id: int
+ source_id_to_fields_map: Dict[int, List[PartitionField]] =
field(init=False)
- @property
- def transform(self) -> Transform:
- return self._transform
+ def __post_init__(self):
+ source_id_to_fields_map = dict()
+ for partition_field in self.fields:
+ source_column =
self.schema.find_column_name(partition_field.source_id)
+ if not source_column:
+ raise ValueError(f"Cannot find source column:
{partition_field.source_id}")
+ existing = source_id_to_fields_map.get(partition_field.source_id,
[])
+ existing.append(partition_field)
+ source_id_to_fields_map[partition_field.source_id] = existing
+ object.__setattr__(self, "source_id_to_fields_map",
source_id_to_fields_map)
def __eq__(self, other):
- return (
- self.field_id == other.field_id
- and self.source_id == other.source_id
- and self.name == other.name
- and self.transform == other.transform
- )
+ """
+ Equality check on spec_id and partition fields only
+ """
+ return self.spec_id == other.spec_id and self.fields == other.fields
def __str__(self):
- return f"{self.field_id}: {self.name}:
{self.transform}({self.source_id})"
+ """
+ PartitionSpec str method highlight the partition field only
+ """
+ result_str = "["
+ for partition_field in self.fields:
+ result_str += f"\n {str(partition_field)}"
+ if len(self.fields) > 0:
+ result_str += "\n"
+ result_str += "]"
+ return result_str
- def __repr__(self):
- return f"PartitionField(field_id={self.field_id}, name={self.name},
transform={repr(self.transform)}, source_id={self.source_id})"
Review Comment:
FYI using default`__repr__` from dataclass now also include the derived
attribute such as `source_id_to_fields_map` into consideration, please let me
know if anyone feels strongly to override and keep the original behaviour
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
