ebyhr commented on code in PR #3717: URL: https://github.com/apache/iceberg-python/pull/3717#discussion_r3688775077
########## tests/integration/test_hive_catalog.py: ########## @@ -0,0 +1,76 @@ +# 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. +import time + +import pytest +from pyspark.sql import SparkSession + +from pyiceberg.catalog.hive import HiveCatalog + + [email protected] +def test_list_views( + session_catalog_hive: HiveCatalog, + spark: SparkSession, +) -> None: + """ + Verify that a view created by Spark through the Iceberg Hive catalog + can be discovered by PyIceberg HiveCatalog.list_views(). + + The test also verifies that: + - Iceberg tables are not returned as views. + - Multiple views are returned. + - Returned identifiers use the expected (namespace, view_name) format. + """ + suffix = int(time.time()) + catalog_name = "hive" + namespace = "default" + table_name = f"table_{suffix}" + first_view_name = f"first_view_{suffix}" + second_view_name = f"second_view_{suffix}" + table_identifier = f"{catalog_name}.{namespace}.{table_name}" + first_view_identifier = f"{catalog_name}.{namespace}.{first_view_name}" + second_view_identifier = f"{catalog_name}.{namespace}.{second_view_name}" + + spark.sql(f""" + CREATE TABLE {table_identifier} ( + id INTEGER, + name STRING, + dt DATE + ) + USING iceberg + """) + + spark.sql(f""" + CREATE VIEW {first_view_identifier} AS + SELECT id, name + FROM {table_identifier} + """) + + spark.sql(f""" + CREATE VIEW {second_view_identifier} AS + SELECT id, name, dt + FROM {table_identifier} + """) + + views = set(session_catalog_hive.list_views(namespace)) + + assert (namespace, first_view_name) in views + assert (namespace, second_view_name) in views Review Comment: Can we ensure `views` don't contain a table? ########## tests/catalog/test_hive.py: ########## @@ -1144,6 +1144,38 @@ def test_create_database_already_exists() -> None: assert "Database default already exists" in str(exc_info.value) +def test_list_views(hive_table: HiveTable) -> None: + catalog = HiveCatalog(HIVE_CATALOG_NAME, uri=HIVE_METASTORE_FAKE_URL) + + tbl1 = deepcopy(hive_table) + tbl1.tableName = "table1" + tbl1.dbName = "database" + tbl1.parameters["table_type"] = "iceberg-view" + tbl2 = deepcopy(hive_table) + tbl2.tableName = "table2" + tbl2.dbName = "database" + tbl2.parameters["table_type"] = "iceberg-view" + tbl3 = deepcopy(hive_table) + tbl3.tableName = "table3" + tbl3.dbName = "database" + tbl3.parameters["table_type"] = "iceberg" + tbl4 = deepcopy(hive_table) + tbl4.tableName = "table4" + tbl4.dbName = "database" + tbl4.parameters.pop("table_type") + + catalog._client = MagicMock() + catalog._client.__enter__().get_all_tables.return_value = ["table1", "table2", "table3", "table4"] + catalog._client.__enter__().get_table_objects_by_name.return_value = [tbl1, tbl2, tbl3, tbl4] + + got_tables = catalog.list_views("database") + assert got_tables == [("database", "table1"), ("database", "table2")] + catalog._client.__enter__().get_all_tables.assert_called_with(db_name="database") + catalog._client.__enter__().get_table_objects_by_name.assert_called_with( + dbname="database", tbl_names=["table1", "table2", "table3", "table4"] + ) + + Review Comment: I don't think the added test is helpful. The actual behavior still returns an empty list. I recommend testing the behavior with integration tests. -- 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]
