gabeiglio commented on code in PR #1443:
URL: https://github.com/apache/iceberg-python/pull/1443#discussion_r1903117970
##########
tests/io/test_pyarrow.py:
##########
@@ -1122,6 +1127,63 @@ def test_projection_concat_files(schema_int: Schema,
file_int: str) -> None:
assert repr(result_table.schema) == "id: int32"
+def test_projection_partition_inference(tmp_path: str, catalog:
InMemoryCatalog) -> None:
+ schema = Schema(
+ NestedField(1, "other_field", StringType(), required=False),
NestedField(2, "partition_id", IntegerType(), required=False)
+ )
+
+ partition_spec = PartitionSpec(PartitionField(2, 1000,
IdentityTransform(), "partition_id"))
+
+ table = catalog.create_table(
+ "default.test_projection_partition_inference",
+ schema=schema,
+ partition_spec=partition_spec,
+ properties={TableProperties.DEFAULT_NAME_MAPPING:
create_mapping_from_schema(schema).model_dump_json()},
+ )
+
+ file_data = pa.array(["foo"], type=pa.string())
+ file_loc = f"{tmp_path}/test.parquet"
+ pq.write_table(pa.table([file_data], names=["other_field"]), file_loc)
+
+ statistics = data_file_statistics_from_parquet_metadata(
+ parquet_metadata=pq.read_metadata(file_loc),
+ stats_columns=compute_statistics_plan(table.schema(),
table.metadata.properties),
+ parquet_column_mapping=parquet_path_to_id_mapping(table.schema()),
+ )
+
+ unpartitioned_file = DataFile(
+ content=DataFileContent.DATA,
+ file_path=file_loc,
+ file_format=FileFormat.PARQUET,
+ partition=Record(partition_id=1),
+ file_size_in_bytes=os.path.getsize(file_loc),
+ sort_order_id=None,
+ spec_id=table.metadata.default_spec_id,
+ equality_ids=None,
+ key_metadata=None,
+ **statistics.to_serialized_dict(),
+ )
+
+ with table.transaction() as transaction:
+ with transaction.update_snapshot().overwrite() as update:
+ update.append_data_file(unpartitioned_file)
Review Comment:
Will do. I'll add that ideally we want to create the data file with a table
instead of manually, and also explain the test.
--
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
