discivigour commented on code in PR #8021:
URL: https://github.com/apache/paimon/pull/8021#discussion_r3349401148
##########
paimon-python/pypaimon/read/split_read.py:
##########
@@ -823,12 +830,27 @@ def create_reader(self) -> RecordReader:
else:
reader = merge_reader
- if (not CoreOptions.blob_as_descriptor(self.table.options)
- and CoreOptions.blob_descriptor_fields(self.table.options)):
- reader = BlobDescriptorConvertReader(reader, self.table)
-
return reader
+ def _create_prescan_reader(self, field_names):
+ """Create a prescan reader by constructing a new DataEvolutionSplitRead
+ instance that only projects the specified field names."""
+ from pypaimon.read.reader.iface.record_batch_reader import
EmptyRecordBatchReader
+
+ prescan_fields = [f for f in self.read_fields if f.name in field_names]
+ if not prescan_fields:
+ return EmptyRecordBatchReader()
+
+ prescan_read = DataEvolutionSplitRead(
Review Comment:
supported.
##########
paimon-python/pypaimon/schema/schema_manager.py:
##########
@@ -166,6 +166,70 @@ def _assert_not_renaming_blob_column(
)
+def _validate_blob_fields(fields: List[DataField], options: dict,
primary_keys: List[str]):
+ """Validate blob field configurations in the schema."""
+ if options is None:
+ options = {}
+
+ blob_field_names = {
+ field.name for field in fields if 'blob' in str(field.type).lower()
Review Comment:
changed
--
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]
