Fokko commented on code in PR #139:
URL: https://github.com/apache/iceberg-python/pull/139#discussion_r1398855771
##########
pyiceberg/table/__init__.py:
##########
@@ -350,6 +357,241 @@ class RemovePropertiesUpdate(TableUpdate):
removals: List[str]
+class TableMetadataUpdateContext:
+ updates: List[TableUpdate]
+ last_added_schema_id: Optional[int]
+
+ def __init__(self) -> None:
+ self.updates = []
+ self.last_added_schema_id = None
+
+ def is_added_snapshot(self, snapshot_id: int) -> bool:
+ return any(
+ update.snapshot.snapshot_id == snapshot_id
+ for update in self.updates
+ if update.action == TableUpdateAction.add_snapshot
+ )
+
+ def is_added_schema(self, schema_id: int) -> bool:
+ return any(
+ update.schema_.schema_id == schema_id for update in self.updates
if update.action == TableUpdateAction.add_schema
+ )
+
+
+@singledispatch
+def apply_table_update(update: TableUpdate, base_metadata: TableMetadata,
context: TableMetadataUpdateContext) -> TableMetadata:
+ """Apply a table update to the table metadata.
+
+ Args:
+ update: The update to be applied.
+ base_metadata: The base metadata to be updated.
+ context: Contains previous updates, last_added_snapshot_id and other
change tracking information in the current transaction.
+
+ Returns:
+ The updated metadata.
+
+ """
+ raise NotImplementedError(f"Unsupported table update: {update}")
+
+
+@apply_table_update.register(UpgradeFormatVersionUpdate)
+def _(update: UpgradeFormatVersionUpdate, base_metadata: TableMetadata,
context: TableMetadataUpdateContext) -> TableMetadata:
+ if update.format_version > SUPPORTED_TABLE_FORMAT_VERSION:
+ raise ValueError(f"Unsupported table format version:
{update.format_version}")
+
+ if update.format_version < base_metadata.format_version:
+ raise ValueError(f"Cannot downgrade v{base_metadata.format_version}
table to v{update.format_version}")
+
+ if update.format_version == base_metadata.format_version:
+ return base_metadata
+
+ updated_metadata_data = copy(base_metadata.model_dump())
+ updated_metadata_data["format-version"] = update.format_version
Review Comment:
While this is a very safe way of doing the copy, it is also rather expensive
since we convert everything to a Python dict, and then create a new object
again. Pydantic has the `model_copy` argument that seems to do what we're
looking for:
```suggestion
updated_metadata_data = base_metadata.model_copy(**{"format-version":
update.format_version})
```
We could construct a `dict` where we add all the changes (for the more
complicated updated below), and then call `model_copy` for each update.
This will make a shallow copy by default (which I think is okay, since the
model is immutable).
--
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]
