gabeiglio commented on code in PR #1443:
URL: https://github.com/apache/iceberg-python/pull/1443#discussion_r1894286043
##########
pyiceberg/io/pyarrow.py:
##########
@@ -1237,16 +1238,29 @@ def _task_to_record_batches(
# When V3 support is introduced, we will update
`downcast_ns_timestamp_to_us` flag based on
# the table format version.
file_schema = pyarrow_to_schema(physical_schema, name_mapping,
downcast_ns_timestamp_to_us=True)
+
+ if file_schema is None:
+ raise ValueError(f"Missing Iceberg schema in Metadata for file:
{path}")
+
pyarrow_filter = None
if bound_row_filter is not AlwaysTrue():
translated_row_filter = translate_column_names(bound_row_filter,
file_schema, case_sensitive=case_sensitive)
bound_file_filter = bind(file_schema, translated_row_filter,
case_sensitive=case_sensitive)
pyarrow_filter = expression_to_pyarrow(bound_file_filter)
+ # Apply column projection rules for missing partitions and default
values
+ # https://iceberg.apache.org/spec/#column-projection
file_project_schema = prune_columns(file_schema, projected_field_ids,
select_full_types=False)
+ projected_missing_fields = {}
- if file_schema is None:
- raise ValueError(f"Missing Iceberg schema in Metadata for file:
{path}")
+ for field_id in
projected_field_ids.difference(file_project_schema.field_ids):
+ if nested_field := projected_schema.find_field(field_id):
+ if nested_field.initial_default is not None:
+ projected_missing_fields[nested_field.name] =
nested_field.initial_default
+ if partition_spec is not None:
+ for partition_field in
partition_spec.fields_by_source_id(field_id):
+ if isinstance(partition_field.transform,
IdentityTransform) and task.file.partition is not None:
+ projected_missing_fields[partition_field.name] =
task.file.partition[0]
Review Comment:
Correct, missed that. `task.file.partition.__dict__[partition_field.name]`
can be used instead
--
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
