Fokko commented on code in PR #569: URL: https://github.com/apache/iceberg-python/pull/569#discussion_r1594058803
########## tests/integration/test_deletes.py: ########## @@ -0,0 +1,257 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# pylint:disable=redefined-outer-name +from typing import List + +import pytest +from pyspark.sql import SparkSession + +from pyiceberg.catalog.rest import RestCatalog +from pyiceberg.expressions import EqualTo +from pyiceberg.table.snapshots import Operation, Summary + + +def run_spark_commands(spark: SparkSession, sqls: List[str]) -> None: + for sql in sqls: + spark.sql(sql) + + +@pytest.mark.integration +@pytest.mark.parametrize("format_version", [1, 2]) +def test_partitioned_table_delete_full_file(spark: SparkSession, session_catalog: RestCatalog, format_version: int) -> None: + identifier = 'default.table_partitioned_delete' + + run_spark_commands( + spark, + [ + f"DROP TABLE IF EXISTS {identifier}", + f""" + CREATE TABLE {identifier} ( + number_partitioned int, + number int + ) + USING iceberg + PARTITIONED BY (number_partitioned) + TBLPROPERTIES('format-version' = {format_version}) + """, + f""" + INSERT INTO {identifier} VALUES (10, 20), (10, 30) + """, + f""" + INSERT INTO {identifier} VALUES (11, 20), (11, 30) + """, + ], + ) + + tbl = session_catalog.load_table(identifier) + tbl.delete(EqualTo("number_partitioned", 10)) + + # No overwrite operation + assert [snapshot.summary.operation.value for snapshot in tbl.snapshots()] == ['append', 'append', 'delete'] + assert tbl.scan().to_arrow().to_pydict() == {'number_partitioned': [11, 11], 'number': [20, 30]} + + +@pytest.mark.integration +@pytest.mark.parametrize("format_version", [1, 2]) +def test_partitioned_table_rewrite(spark: SparkSession, session_catalog: RestCatalog, format_version: int) -> None: + identifier = 'default.table_partitioned_delete' + + run_spark_commands( + spark, + [ + f"DROP TABLE IF EXISTS {identifier}", + f""" + CREATE TABLE {identifier} ( + number_partitioned int, + number int + ) + USING iceberg + PARTITIONED BY (number_partitioned) + TBLPROPERTIES('format-version' = {format_version}) + """, + f""" + INSERT INTO {identifier} VALUES (10, 20), (10, 30) + """, + f""" + INSERT INTO {identifier} VALUES (11, 20), (11, 30) + """, + ], + ) + + tbl = session_catalog.load_table(identifier) + tbl.delete(EqualTo("number", 20)) + + # We don't delete a whole partition, so there is only a overwrite + assert [snapshot.summary.operation.value for snapshot in tbl.snapshots()] == ['append', 'append', 'overwrite'] + assert tbl.scan().to_arrow().to_pydict() == {'number_partitioned': [11, 10], 'number': [30, 30]} + + +@pytest.mark.integration +@pytest.mark.parametrize("format_version", [1, 2]) +def test_partitioned_table_no_match(spark: SparkSession, session_catalog: RestCatalog, format_version: int) -> None: + identifier = 'default.table_partitioned_delete' + + run_spark_commands( + spark, + [ + f"DROP TABLE IF EXISTS {identifier}", + f""" + CREATE TABLE {identifier} ( + number_partitioned int, + number int + ) + USING iceberg + PARTITIONED BY (number_partitioned) + TBLPROPERTIES('format-version' = {format_version}) + """, + f""" + INSERT INTO {identifier} VALUES (10, 20), (10, 30) + """, + ], + ) + + tbl = session_catalog.load_table(identifier) + tbl.delete(EqualTo("number_partitioned", 22)) # Does not affect any data + + # Open for discussion, do we want to create a new snapshot? Review Comment: I think that's a great solution, thank you! 👍 -- 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
