brucearctor commented on a change in pull request #16578: URL: https://github.com/apache/beam/pull/16578#discussion_r804352117
########## File path: sdks/java/io/google-cloud-platform/src/test/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryClusteringIT.java ########## @@ -0,0 +1,176 @@ +/* + * 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.sdk.io.gcp.bigquery; + +import com.google.api.services.bigquery.Bigquery; +import com.google.api.services.bigquery.model.Clustering; +import com.google.api.services.bigquery.model.Table; +import com.google.api.services.bigquery.model.TableFieldSchema; +import com.google.api.services.bigquery.model.TableRow; +import com.google.api.services.bigquery.model.TableSchema; +import java.util.Arrays; +import org.apache.beam.sdk.Pipeline; +import org.apache.beam.sdk.coders.Coder; +import org.apache.beam.sdk.io.gcp.testing.BigqueryClient; +import org.apache.beam.sdk.options.Default; +import org.apache.beam.sdk.options.Description; +import org.apache.beam.sdk.options.ExperimentalOptions; +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.transforms.DoFn; +import org.apache.beam.sdk.transforms.ParDo; +import org.apache.beam.sdk.values.ValueInSingleWindow; +import org.checkerframework.checker.nullness.qual.Nullable; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.JUnit4; + +/** Integration test that clusters sample data in BigQuery. */ +@RunWith(JUnit4.class) +public class BigQueryClusteringIT { + private static final String WEATHER_SAMPLES_TABLE = + "clouddataflow-readonly:samples.weather_stations"; + private static final String DATASET_NAME = "BigQueryClusteringIT"; + private static final Clustering CLUSTERING = + new Clustering().setFields(Arrays.asList("station_number")); + private static final TableSchema SCHEMA = + new TableSchema() + .setFields( + Arrays.asList( + new TableFieldSchema().setName("station_number").setType("INTEGER"), + new TableFieldSchema().setName("date").setType("DATE"))); + + private Bigquery bqClient; + private BigQueryClusteringITOptions options; + + @Before + public void setUp() { + PipelineOptionsFactory.register(BigQueryClusteringITOptions.class); + options = TestPipeline.testingPipelineOptions().as(BigQueryClusteringITOptions.class); + options.setTempLocation(options.getTempRoot() + "/temp-it/"); + bqClient = BigqueryClient.getNewBigqueryClient(options.getAppName()); + } + + /** Customized PipelineOptions for BigQueryClustering Integration Test. */ + public interface BigQueryClusteringITOptions + extends TestPipelineOptions, ExperimentalOptions, BigQueryOptions { + @Description("Table to read from, specified as " + "<project_id>:<dataset_id>.<table_id>") + @Default.String(WEATHER_SAMPLES_TABLE) + String getBqcInput(); + + void setBqcInput(String value); + } + + static class KeepStationNumberAndConvertDate extends DoFn<TableRow, TableRow> { + @ProcessElement + public void processElement(ProcessContext c) { + String day = (String) c.element().get("day"); + String month = (String) c.element().get("month"); + String year = (String) c.element().get("year"); + + TableRow row = new TableRow(); + row.set("station_number", c.element().get("station_number")); + row.set("date", String.format("%s-%s-%s", year, month, day)); + c.output(row); + } + } + + static class ClusteredDestinations extends DynamicDestinations<TableRow, TableDestination> { + private final String tableName; + + public ClusteredDestinations(String tableName) { + this.tableName = tableName; + } + + @Override + public @Nullable Coder<TableDestination> getDestinationCoder() { + return TableDestinationCoderV3.of(); Review comment: Easiest way to verify ( without actually thinking much :-) ) is going to be removing these lines and see if things still work. Once I re-confirm the below (that also writing the data), I'll then try removing these lines to verify whether works without. Off handedly, I think it is needed ( I think we default to v2 coder, and need an override ... but ... is great if this is already handled and setting manually not required ). If this turns out to be necessary, then that seems like a new issue which I can at least file a ticket - and can consider addressing after this. -- 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]
