rdblue commented on code in PR #8374:
URL: https://github.com/apache/iceberg/pull/8374#discussion_r1304994873
##########
python/pyiceberg/table/__init__.py:
##########
@@ -889,28 +888,58 @@ def to_ray(self) -> ray.data.dataset.Dataset:
return ray.data.from_arrow(self.to_arrow())
+class MoveOperation(Enum):
+ First = 1
+ Before = 2
+ After = 3
+
+
+@dataclass
+class Move:
+ field_id: int
+ op: MoveOperation
+ other_field_id: Optional[int] = None
+
+
class UpdateSchema:
_table: Table
_schema: Schema
_last_column_id: itertools.count[int]
- _identifier_field_names: List[str]
- _adds: Dict[int, List[NestedField]]
- _added_name_to_id: Dict[str, int]
- _id_to_parent: Dict[int, str]
+ _identifier_field_names: Set[str]
+
+ _adds: Dict[int, List[NestedField]] = {}
+ _updates: Dict[int, NestedField] = {}
+ _deletes: Set[int] = set()
+ _moves: Dict[int, List[Move]] = {}
+
+ _added_name_to_id: Dict[str, int] = {}
+ _id_to_parent: Dict[int, str] = {}
_allow_incompatible_changes: bool
_case_sensitive: bool
_transaction: Optional[Transaction]
- def __init__(self, schema: Schema, table: Table, transaction:
Optional[Transaction] = None):
+ def __init__(
+ self,
+ table: Table,
+ transaction: Optional[Transaction] = None,
+ allow_incompatible_changes: bool = False,
+ case_sensitive: bool = True,
+ ) -> None:
self._table = table
- self._schema = schema
- self._last_column_id = itertools.count(schema.highest_field_id + 1)
- self._identifier_field_names = schema.column_names
+ self._schema = table.schema()
+ self._last_column_id = itertools.count(self._schema.highest_field_id +
1)
Review Comment:
The highest field ID needs to come from the table metadata, not from the
current schema. Otherwise, an ID could be reassigned if an ID is assigned, the
schema is rolled back, and another column is added.
--
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]
