rdblue commented on code in PR #4717:
URL: https://github.com/apache/iceberg/pull/4717#discussion_r868759430
##########
python/src/iceberg/table/partitioning.py:
##########
@@ -64,3 +67,100 @@ def __str__(self):
def __repr__(self):
return f"PartitionField(field_id={self.field_id}, name={self.name},
transform={repr(self.transform)}, source_id={self.source_id})"
+
+ def __hash__(self):
+ return hash((self.source_id, self.field_id, self.name, self.transform))
+
+
+class PartitionSpec:
+ """
+ PartitionSpec capture the transformation from table data to partition
values
+
+ 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
+ """
+
+ PARTITION_DATA_ID_START: int = 1000
+
+ def __init__(self, schema: Schema, spec_id: int, fields:
Tuple[PartitionField], last_assigned_field_id: int):
Review Comment:
Should `fields` be `Iterable` rather than being so strict? This could easily
convert to a tuple.
--
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]
