tscottcoombes1 commented on code in PR #1534:
URL: https://github.com/apache/iceberg-python/pull/1534#discussion_r1940112272
##########
pyiceberg/table/__init__.py:
##########
@@ -1064,6 +1065,110 @@ def name_mapping(self) -> Optional[NameMapping]:
"""Return the table's field-id NameMapping."""
return self.metadata.name_mapping()
+ def merge_rows(self, df: pa.Table, join_cols: list
+ , when_matched_update_all: bool = True
+ , when_not_matched_insert_all: bool = True
+ ) -> Dict:
+ """
+ Shorthand API for performing an upsert/merge to an iceberg table.
+
+ Args:
+ df: The input dataframe to merge with the table's data.
+ join_cols: The columns to join on.
+ when_matched_update_all: Bool indicating to update rows that are
matched but require an update due to a value in a non-key column changing
+ when_not_matched_insert_all: Bool indicating new rows to be
inserted that do not match any existing rows in the table
+
+ Returns:
+ A dictionary containing the number of rows updated and inserted.
+ """
+
+ from pyiceberg.table import merge_rows_util
+
+ try:
+ from datafusion import SessionContext
+ except ModuleNotFoundError as e:
+ raise ModuleNotFoundError("For merge_rows, DataFusion needs to be
installed") from e
+
+ try:
+ from pyarrow import dataset as ds
+ except ModuleNotFoundError as e:
+ raise ModuleNotFoundError("For merge_rows, PyArrow needs to be
installed") from e
+
+ source_table_name = "source"
+ target_table_name = "target"
+
+ if when_matched_update_all == False and when_not_matched_insert_all ==
False:
+ return {'rows_updated': 0, 'rows_inserted': 0, 'msg': 'no merge
options selected...exiting'}
Review Comment:
```
from dataclasses import dataclass
@dataclass
class MergeResult:
"""docstring"""
rows_updated: int
rows_inserted: int
msg: str
```
basically removes the boilerplate of setting up a class (i.e. no __init__)
--
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
