rdblue commented on code in PR #40:
URL: https://github.com/apache/iceberg-python/pull/40#discussion_r1349761999
##########
pyiceberg/avro/resolver.py:
##########
@@ -233,7 +255,107 @@ def skip(self, decoder: BinaryDecoder) -> None:
pass
-class SchemaResolver(PrimitiveWithPartnerVisitor[IcebergType, Reader]):
+class WriteSchemaResolver(PrimitiveWithPartnerVisitor[IcebergType, Writer]):
+ def schema(self, schema: Schema, expected_schema: Optional[IcebergType],
result: Writer) -> Writer:
+ return result
+
+ def struct(self, struct: StructType, provided_struct:
Optional[IcebergType], field_writers: List[Writer]) -> Writer:
+ if not isinstance(provided_struct, StructType):
+ raise ResolveError(f"File/write schema are not aligned for struct,
got {provided_struct}")
+
+ provided_struct_positions: Dict[int, int] = {field.field_id: pos for
pos, field in enumerate(provided_struct.fields)}
+
+ results: List[Tuple[Optional[int], Writer]] = []
+ iter(field_writers)
+
+ for pos, write_field in enumerate(struct.fields):
+ if write_field.field_id in provided_struct_positions:
+
results.append((provided_struct_positions[write_field.field_id],
field_writers[pos]))
+ else:
+ # There is a default value
+ if isinstance(write_field, NestedField) and
write_field.write_default is not None:
+ # The field is not in the record, but there is a write
default value
+ default_writer = DefaultWriter(
+ writer=visit(write_field.field_type,
CONSTRUCT_WRITER_VISITOR), value=write_field.write_default
+ )
+ results.append((None, default_writer))
+ elif write_field.required:
+ raise ValueError(f"Field is required, and there is no
write default: {write_field}")
+ else:
+ results.append((pos, NoneWriter()))
+
+ return StructWriter(field_writers=tuple(results))
+
+ def field(self, field: NestedField, expected_field: Optional[IcebergType],
field_writer: Writer) -> Writer:
+ return field_writer if field.required else OptionWriter(field_writer)
+
+ def list(self, list_type: ListType, expected_list: Optional[IcebergType],
element_reader: Writer) -> Writer:
+ if expected_list and not isinstance(expected_list, ListType):
+ raise ResolveError(f"File/read schema are not aligned for list,
got {expected_list}")
Review Comment:
I don't think it's necessary to do these check. The PartnerAccessor is
strict and doesn't allow anything that doesn't match. For example, if the list
has no partner, then the call to fetch the partner for the element will throw
an exception because `isinstance(None, ListType)` would fail.
--
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]
