abnobdoss commented on code in PR #3384:
URL: https://github.com/apache/iceberg-python/pull/3384#discussion_r4020824836
##########
pyiceberg/table/__init__.py:
##########
@@ -861,10 +782,46 @@ def upsert(
if not when_matched_update_all and not when_not_matched_insert_all:
raise ValueError("no upsert options selected...exiting")
- if upsert_util.has_duplicate_rows(df, join_cols):
- raise ValueError("Duplicate rows found in source dataset based on
the key columns. No upsert executed")
+ from pyiceberg.io.pyarrow import _check_pyarrow_schema_compatible,
schema_to_pyarrow
- from pyiceberg.io.pyarrow import _check_pyarrow_schema_compatible
+ table_arrow_schema = schema_to_pyarrow(self.table_metadata.schema(),
include_field_ids=False)
+ df_column_names = set(df.schema.names)
+
+ for col in join_cols:
Review Comment:
Good call, done!
--
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]
