Fokko commented on code in PR #227:
URL: https://github.com/apache/iceberg-python/pull/227#discussion_r1433110576
##########
pyiceberg/io/pyarrow.py:
##########
@@ -720,25 +719,17 @@ def primitive(self, primitive: pa.DataType) ->
Optional[T]:
def _get_field_id(field: pa.Field) -> Optional[int]:
- for pyarrow_field_id_key in PYARROW_FIELD_ID_KEYS:
- if field_id_str := field.metadata.get(pyarrow_field_id_key):
- return int(field_id_str.decode())
- return None
+ return int(field_id_str.decode()) if (field_id_str :=
field.metadata.get(PYARROW_FIELD_ID_KEY)) else None
-def _get_field_doc(field: pa.Field) -> Optional[str]:
- for pyarrow_doc_key in PYARROW_FIELD_DOC_KEYS:
- if doc_str := field.metadata.get(pyarrow_doc_key):
- return doc_str.decode()
- return None
class _ConvertToIceberg(PyArrowSchemaVisitor[Union[IcebergType, Schema]]):
def _convert_fields(self, arrow_fields: Iterable[pa.Field], field_results:
List[Optional[IcebergType]]) -> List[NestedField]:
fields = []
for i, field in enumerate(arrow_fields):
field_id = _get_field_id(field)
- field_doc = _get_field_doc(field)
+ field_doc = doc_str.decode() if (doc_str :=
field.metadata.get(PYARROW_FIELD_DOC_KEY)) else None
Review Comment:
This is a great suggestion 👍
--
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
