HuangXingBo commented on a change in pull request #14775: URL: https://github.com/apache/flink/pull/14775#discussion_r569215914
########## File path: flink-python/src/test/java/org/apache/flink/table/runtime/operators/python/aggregate/PythonStreamGroupWindowAggregateOperatorTest.java ########## @@ -0,0 +1,1129 @@ +/* + * 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. + */ + +package org.apache.flink.table.runtime.operators.python.aggregate; + +import org.apache.flink.configuration.Configuration; +import org.apache.flink.core.memory.DataInputDeserializer; +import org.apache.flink.core.memory.DataOutputSerializer; +import org.apache.flink.python.PythonFunctionRunner; +import org.apache.flink.python.PythonOptions; +import org.apache.flink.streaming.api.operators.InternalTimer; +import org.apache.flink.streaming.api.operators.InternalTimerServiceImpl; +import org.apache.flink.streaming.api.operators.OneInputStreamOperator; +import org.apache.flink.streaming.api.operators.Triggerable; +import org.apache.flink.streaming.api.watermark.Watermark; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.streaming.util.OneInputStreamOperatorTestHarness; +import org.apache.flink.table.api.DataTypes; +import org.apache.flink.table.api.TableConfig; +import org.apache.flink.table.data.GenericRowData; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.data.StringData; +import org.apache.flink.table.data.TimestampData; +import org.apache.flink.table.data.UpdatableRowData; +import org.apache.flink.table.data.binary.BinaryRowData; +import org.apache.flink.table.data.util.RowDataUtil; +import org.apache.flink.table.data.utils.JoinedRowData; +import org.apache.flink.table.expressions.FieldReferenceExpression; +import org.apache.flink.table.functions.python.PythonAggregateFunctionInfo; +import org.apache.flink.table.planner.codegen.CodeGeneratorContext; +import org.apache.flink.table.planner.codegen.ProjectionCodeGenerator; +import org.apache.flink.table.planner.expressions.PlannerWindowReference; +import org.apache.flink.table.planner.plan.logical.LogicalWindow; +import org.apache.flink.table.planner.plan.logical.SlidingGroupWindow; +import org.apache.flink.table.planner.typeutils.DataViewUtils; +import org.apache.flink.table.runtime.generated.GeneratedProjection; +import org.apache.flink.table.runtime.generated.Projection; +import org.apache.flink.table.runtime.operators.python.scalar.PythonScalarFunctionOperatorTestBase; +import org.apache.flink.table.runtime.operators.window.TimeWindow; +import org.apache.flink.table.runtime.operators.window.assigners.SlidingWindowAssigner; +import org.apache.flink.table.runtime.operators.window.assigners.WindowAssigner; +import org.apache.flink.table.runtime.utils.PassThroughStreamGroupWindowAggregatePythonFunctionRunner; +import org.apache.flink.table.runtime.utils.PythonTestUtils; +import org.apache.flink.table.types.AtomicDataType; +import org.apache.flink.table.types.logical.BigIntType; +import org.apache.flink.table.types.logical.LogicalType; +import org.apache.flink.table.types.logical.RowType; +import org.apache.flink.table.types.logical.TimestampKind; +import org.apache.flink.table.types.logical.TimestampType; +import org.apache.flink.table.types.logical.VarCharType; +import org.apache.flink.types.RowKind; + +import org.junit.Test; + +import java.io.IOException; +import java.time.Duration; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collection; +import java.util.HashMap; +import java.util.LinkedList; +import java.util.List; +import java.util.Map; +import java.util.concurrent.ConcurrentLinkedQueue; +import java.util.concurrent.LinkedBlockingQueue; +import java.util.function.Function; +import java.util.stream.Collectors; + +import scala.Some; + +import static org.apache.flink.table.expressions.ApiExpressionUtils.intervalOfMillis; + +/** + * Test for {@link PythonStreamGroupWindowAggregateOperator}. These test that: + * + * <ul> + * <li>Retraction flag is handled correctly + * <li>FinishBundle is called when checkpoint is encountered + * <li>FinishBundle is called when bundled element count reach to max bundle size + * <li>FinishBundle is called when bundled time reach to max bundle time + * <li>Watermarks are buffered and only sent to downstream when finishedBundle is triggered + * </ul> + */ +public class PythonStreamGroupWindowAggregateOperatorTest + extends AbstractPythonStreamAggregateOperatorTest { + @Test + public void testGroupWindowAggregateFunction() throws Exception { + OneInputStreamOperatorTestHarness<RowData, RowData> testHarness = + getTestHarness(new Configuration()); + long initialTime = 0L; + ConcurrentLinkedQueue<Object> expectedOutput = new ConcurrentLinkedQueue<>(); + testHarness.open(); + testHarness.processElement( + new StreamRecord<>(newRow(true, "c1", "c2", 0L, 0L), initialTime + 1)); + testHarness.processElement( + new StreamRecord<>(newRow(true, "c1", "c4", 1L, 6000L), initialTime + 2)); + testHarness.processElement( + new StreamRecord<>(newRow(true, "c1", "c6", 2L, 10000L), initialTime + 3)); + testHarness.processElement( + new StreamRecord<>(newRow(true, "c2", "c8", 3L, 0L), initialTime + 4)); + testHarness.processElement( + new StreamRecord<>(newRow(true, "c3", "c8", 3L, 0L), initialTime + 5)); + testHarness.processElement( + new StreamRecord<>(newRow(false, "c3", "c8", 3L, 0L), initialTime + 6)); + testHarness.processWatermark(Long.MAX_VALUE); + testHarness.close(); + + expectedOutput.add( Review comment: Yes. It can remove much deduplicate code in 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. For queries about this service, please contact Infrastructure at: [email protected]
