qzyu999 commented on code in PR #3124: URL: https://github.com/apache/iceberg-python/pull/3124#discussion_r2897698723
########## tests/table/test_maintenance.py: ########## @@ -0,0 +1,106 @@ +# 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 random + +import pyarrow as pa + +from pyiceberg.catalog import Catalog +from pyiceberg.exceptions import NoSuchNamespaceError +from pyiceberg.partitioning import PartitionField, PartitionSpec +from pyiceberg.schema import Schema +from pyiceberg.transforms import IdentityTransform + + +def test_maintenance_compact(catalog: Catalog) -> None: + # Setup Schema and specs + from pyiceberg.types import LongType, NestedField, StringType + + schema = Schema( + NestedField(1, "id", LongType()), + NestedField(2, "category", StringType()), + NestedField(3, "value", LongType()), + ) + spec = PartitionSpec(PartitionField(source_id=2, field_id=1000, transform=IdentityTransform(), name="category")) + + # Create the namespace and table + try: + catalog.create_namespace("default") + except NoSuchNamespaceError: + pass + table = catalog.create_table( + "default.test_compaction", + schema=schema, + partition_spec=spec, + ) + + # Append many small data files + categories = ["cat1", "cat2", "cat3"] + for i in range(12): + table.append( + pa.table( + { + "id": list(range(i * 10, (i + 1) * 10)), + "category": [categories[i % 3]] * 10, + "value": [random.randint(1, 100) for _ in range(10)], + } + ) + ) + + # Verify state before compaction + before_files = list(table.scan().plan_files()) + assert len(before_files) == 12 + assert table.scan().to_arrow().num_rows == 120 + + # Execute Compaction + table.maintenance.compact() + + # Verify state after compaction + table.refresh() + after_files = list(table.scan().plan_files()) + assert len(after_files) == 3 # Should be 1 optimized data file per partition + assert table.scan().to_arrow().num_rows == 120 + Review Comment: Hi @kevinjqliu, made a change in 64200276bfe3be9ef6af60e1c5a99c60bde1ccea to check that the columns and the primary keys remain the same before/after compaction. -- 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]
