amogh-jahagirdar commented on code in PR #245:
URL: https://github.com/apache/iceberg-python/pull/245#discussion_r1475530412
##########
pyiceberg/table/__init__.py:
##########
@@ -2271,3 +2317,244 @@ def commit(self) -> Snapshot:
)
return snapshot
+
+
+class UpdateSpec:
+ _table: Table
+ _schema: Schema
+ _spec: PartitionSpec
+ _name_to_field: Dict[str, PartitionField] = {}
+ _name_to_added_field: Dict[str, PartitionField] = {}
+ _transform_to_field: Dict[Tuple[int, str], PartitionField] = {}
+ _transform_to_added_field: Dict[Tuple[int, str], PartitionField] = {}
+ _renames: Dict[str, str] = {}
+ _added_time_fields: Dict[int, PartitionField] = {}
+ _case_sensitive: bool
+ _adds: List[PartitionField]
+ _deletes: Set[int]
+ _last_assigned_partition_id: int
+ _transaction: Optional[Transaction]
+ _unassigned_field_name = 'unassigned_field_name'
+
+ def __init__(self, table: Table, transaction: Optional[Transaction] =
None, case_sensitive: bool = True) -> None:
+ self._table = table
+ self._schema = table.schema()
+ self._spec = table.spec()
+ self._name_to_field = {field.name: field for field in
self._spec.fields}
+ self._name_to_added_field = {}
+ self._transform_to_field = {(field.source_id, repr(field.transform)):
field for field in self._spec.fields}
+ self._transform_to_added_field = {}
+ self._adds = []
+ self._deletes = set()
+ if len(table.specs()) == 1:
Review Comment:
Actually it's really important that this self._last_assigned_partition-id is
set to the last assigned field ID across all specs not just the current spec.
I'll fix this and add a test which demonstrates the importancce
##########
pyiceberg/table/__init__.py:
##########
@@ -2271,3 +2317,244 @@ def commit(self) -> Snapshot:
)
return snapshot
+
+
+class UpdateSpec:
+ _table: Table
+ _schema: Schema
+ _spec: PartitionSpec
+ _name_to_field: Dict[str, PartitionField] = {}
+ _name_to_added_field: Dict[str, PartitionField] = {}
+ _transform_to_field: Dict[Tuple[int, str], PartitionField] = {}
+ _transform_to_added_field: Dict[Tuple[int, str], PartitionField] = {}
+ _renames: Dict[str, str] = {}
+ _added_time_fields: Dict[int, PartitionField] = {}
+ _case_sensitive: bool
+ _adds: List[PartitionField]
+ _deletes: Set[int]
+ _last_assigned_partition_id: int
+ _transaction: Optional[Transaction]
+ _unassigned_field_name = 'unassigned_field_name'
+
+ def __init__(self, table: Table, transaction: Optional[Transaction] =
None, case_sensitive: bool = True) -> None:
+ self._table = table
+ self._schema = table.schema()
+ self._spec = table.spec()
+ self._name_to_field = {field.name: field for field in
self._spec.fields}
+ self._name_to_added_field = {}
+ self._transform_to_field = {(field.source_id, repr(field.transform)):
field for field in self._spec.fields}
+ self._transform_to_added_field = {}
+ self._adds = []
+ self._deletes = set()
+ if len(table.specs()) == 1:
Review Comment:
Actually it's really important that this self._last_assigned_partition-id is
set to the last assigned field ID across all specs not just the current spec.
I'll fix this and add a test which demonstrates the importance.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
