benWize commented on a change in pull request #16609: URL: https://github.com/apache/beam/pull/16609#discussion_r816076966
########## File path: examples/java/src/test/java/org/apache/beam/examples/cookbook/CombinePerKeyExamplesIT.java ########## @@ -0,0 +1,99 @@ +/* + * 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.beam.examples.cookbook; + +import static org.junit.Assert.assertEquals; + +import com.google.api.client.util.BackOff; +import com.google.api.client.util.BackOffUtils; +import com.google.api.client.util.Sleeper; +import com.google.api.services.bigquery.model.QueryResponse; +import org.apache.beam.sdk.extensions.gcp.options.GcpOptions; +import org.apache.beam.sdk.extensions.gcp.util.BackOffAdapter; +import org.apache.beam.sdk.io.gcp.testing.BigqueryClient; +import org.apache.beam.sdk.options.PipelineOptionsFactory; +import org.apache.beam.sdk.testing.TestPipeline; +import org.apache.beam.sdk.testing.TestPipelineOptions; +import org.apache.beam.sdk.util.FluentBackoff; +import org.joda.time.Duration; +import org.junit.After; +import org.junit.Before; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.JUnit4; + +/** An end-to-end test for {@link org.apache.beam.examples.cookbook.CombinePerKeyExamples}. */ +@RunWith(JUnit4.class) +public class CombinePerKeyExamplesIT { + private CombinePerKeyExamplesOptions options; + private final String timestamp = Long.toString(System.currentTimeMillis()); + private final String outputDatasetId = "combine_per_key_examples" + timestamp; + private final String outputTable = "combine_per_key_examples_table"; + private final Long defaultExpiration = 1000L * 60 * 60; + private String projectId; + private BigqueryClient bqClient; + + /** Options for the CombinePerKeyExamples Integration Test. */ + public interface CombinePerKeyExamplesOptions + extends TestPipelineOptions, CombinePerKeyExamples.Options {} + + @Before + public void setupTestEnvironment() throws Exception { + PipelineOptionsFactory.register(TestPipelineOptions.class); + this.options = TestPipeline.testingPipelineOptions().as(CombinePerKeyExamplesOptions.class); + this.projectId = TestPipeline.testingPipelineOptions().as(GcpOptions.class).getProject(); + this.bqClient = new BigqueryClient("CombinePerKeyExamplesIT"); + this.bqClient.createNewDataset(this.projectId, this.outputDatasetId, defaultExpiration); Review comment: I have seen both scenarios, for example, this existing test https://github.com/apache/beam/blob/master/examples/java/src/test/java/org/apache/beam/examples/complete/TrafficMaxLaneFlowIT.java#L63 I think creating and deleting a dataset inside the test could help to avoid side effects because of leftover data, but I don't have a strong preference. -- 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]
