Fokko commented on code in PR #7782: URL: https://github.com/apache/iceberg/pull/7782#discussion_r1295097061
########## python/pyiceberg/table/metadata.py: ########## @@ -42,55 +45,79 @@ from pyiceberg.typedef import EMPTY_DICT, IcebergBaseModel, Properties from pyiceberg.utils.datetime import datetime_to_millis -CURRENT_SNAPSHOT_ID = "current_snapshot_id" -CURRENT_SCHEMA_ID = "current_schema_id" +CURRENT_SNAPSHOT_ID = "current-snapshot-id" +CURRENT_SCHEMA_ID = "current-schema-id" SCHEMAS = "schemas" -DEFAULT_SPEC_ID = "default_spec_id" -PARTITION_SPEC = "partition_spec" -PARTITION_SPECS = "partition_specs" -SORT_ORDERS = "sort_orders" +DEFAULT_SPEC_ID = "default-spec-id" +PARTITION_SPEC = "partition-spec" +PARTITION_SPECS = "partition-specs" +SORT_ORDERS = "sort-orders" +LAST_PARTITION_ID = "last-partition-id" +LAST_ASSIGNED_FIELD_ID = "last-assigned-field-id" REFS = "refs" +SPEC_ID = "spec-id" +FIELD_ID = "field-id" +FIELDS = "fields" INITIAL_SEQUENCE_NUMBER = 0 INITIAL_SPEC_ID = 0 DEFAULT_SCHEMA_ID = 0 -def check_schemas(values: Dict[str, Any]) -> Dict[str, Any]: +def cleanup_snapshot_id(data: Dict[str, Any]) -> Dict[str, Any]: + """Runs before validation.""" + if CURRENT_SNAPSHOT_ID in data and data[CURRENT_SNAPSHOT_ID] == -1: + # We treat -1 and None the same, by cleaning this up + # in a pre-validator, we can simplify the logic later on + data[CURRENT_SNAPSHOT_ID] = None + return data + + +def check_schemas(table_metadata: TableMetadata) -> TableMetadata: Review Comment: Yes, and it also handles the aliases. For example, for the `NestedField` we both accept `field_id` and `id` as the `id`. But since `id` is a reserved keyword we map `id` to `field_id`. In the `after` validator, we make sure that `id` is converted to `field_id`, which makes it less error-prone :) -- 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]
