Fokko commented on code in PR #5627:
URL: https://github.com/apache/iceberg/pull/5627#discussion_r958815658
##########
python/pyiceberg/schema.py:
##########
@@ -638,3 +724,61 @@ def map(self, map_type: MapType, key_result: int,
value_result: int) -> int:
def primitive(self, primitive: PrimitiveType) -> int:
return 0
+
+
+def assign_fresh_schema_ids(schema: Schema) -> Schema:
+ """Traverses the schema, and sets new IDs"""
+ schema_struct = pre_order_visit(schema.as_struct(), _SetFreshIDs())
+
+ fresh_identifier_field_ids = []
+ new_schema = Schema(*schema_struct.fields)
+ for field_id in schema.identifier_field_ids:
+ original_field_name = schema.find_column_name(field_id)
+ if original_field_name is None:
+ raise ValueError(f"Could not find field: {field_id}")
+ fresh_field = new_schema.find_field(original_field_name)
+ if fresh_field is None:
+ raise ValueError(f"Could not lookup field in new schema:
{original_field_name}")
+ fresh_identifier_field_ids.append(fresh_field.field_id)
+
+ return new_schema.copy(update={"identifier_field_ids":
fresh_identifier_field_ids})
+
+
+class _SetFreshIDs(PreOrderSchemaVisitor[IcebergType]):
+ """Traverses the schema and assigns monotonically increasing ids"""
+
+ counter: itertools.count
+
+ def __init__(self, start: int = 1) -> None:
+ self.counter = itertools.count(start)
+
+ def _get_and_increment(self) -> int:
+ return next(self.counter)
+
+ def schema(self, schema: Schema, struct_result: Callable[[], StructType])
-> Schema:
+ return Schema(*struct_result().fields,
identifier_field_ids=schema.identifier_field_ids)
Review Comment:
Yes, we do that in the function itself:
```python
def assign_fresh_schema_ids(schema: Schema) -> Schema:
"""Traverses the schema, and sets new IDs"""
schema_struct = pre_order_visit(schema.as_struct(), _SetFreshIDs())
fresh_identifier_field_ids = []
new_schema = Schema(*schema_struct.fields)
for field_id in schema.identifier_field_ids:
original_field_name = schema.find_column_name(field_id)
if original_field_name is None:
raise ValueError(f"Could not find field: {field_id}")
fresh_field = new_schema.find_field(original_field_name)
if fresh_field is None:
raise ValueError(f"Could not lookup field in new schema:
{original_field_name}")
fresh_identifier_field_ids.append(fresh_field.field_id)
return new_schema.copy(update={"identifier_field_ids":
fresh_identifier_field_ids})
```
This is because we first want to know all the IDs
--
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
