afedulov commented on a change in pull request #17598: URL: https://github.com/apache/flink/pull/17598#discussion_r789562890
########## File path: flink-formats/flink-csv/src/test/java/org/apache/flink/formats/csv/DataStreamCsvITCase.java ########## @@ -0,0 +1,363 @@ +/* + * 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.formats.csv; + +import org.apache.flink.api.common.eventtime.WatermarkStrategy; +import org.apache.flink.api.common.restartstrategy.RestartStrategies; +import org.apache.flink.api.common.serialization.BulkWriter; +import org.apache.flink.connector.file.sink.FileSink; +import org.apache.flink.connector.file.src.FileSource; +import org.apache.flink.connector.file.src.reader.StreamFormat; +import org.apache.flink.core.fs.Path; +import org.apache.flink.core.testutils.AllCallbackWrapper; +import org.apache.flink.formats.common.Converter; +import org.apache.flink.runtime.minicluster.RpcServiceSharing; +import org.apache.flink.runtime.testutils.MiniClusterExtension; +import org.apache.flink.runtime.testutils.MiniClusterResourceConfiguration; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.datastream.DataStreamUtils; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.streaming.api.functions.sink.filesystem.bucketassigners.BasePathBucketAssigner; +import org.apache.flink.streaming.api.operators.collect.ClientAndIterator; +import org.apache.flink.util.TestLogger; +import org.apache.flink.util.function.FunctionWithException; + +import org.apache.flink.shaded.jackson2.com.fasterxml.jackson.annotation.JsonPropertyOrder; +import org.apache.flink.shaded.jackson2.com.fasterxml.jackson.dataformat.csv.CsvMapper; +import org.apache.flink.shaded.jackson2.com.fasterxml.jackson.dataformat.csv.CsvSchema; + +import org.apache.commons.io.FileUtils; +import org.jetbrains.annotations.NotNull; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.extension.RegisterExtension; +import org.junit.jupiter.api.io.TempDir; + +import java.io.File; +import java.io.FileOutputStream; +import java.io.IOException; +import java.io.OutputStream; +import java.io.OutputStreamWriter; +import java.io.PrintWriter; +import java.io.Serializable; +import java.math.BigDecimal; +import java.nio.charset.StandardCharsets; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collection; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Objects; +import java.util.UUID; +import java.util.stream.Collectors; + +import static org.assertj.core.api.Assertions.assertThat; +import static org.junit.jupiter.api.Assertions.assertEquals; +import static org.junit.jupiter.api.Assertions.assertTrue; + +/** MiniCluster-based integration tests CSV data format. */ +public class DataStreamCsvITCase extends TestLogger { + + private static final int PARALLELISM = 4; + + @TempDir File outDir; + + public static final MiniClusterExtension MINI_CLUSTER_RESOURCE = + new MiniClusterExtension( + new MiniClusterResourceConfiguration.Builder() + .setNumberTaskManagers(1) + .setNumberSlotsPerTaskManager(PARALLELISM) + .setRpcServiceSharing(RpcServiceSharing.DEDICATED) + .withHaLeadershipControl() + .build()); + + @RegisterExtension + public static AllCallbackWrapper<MiniClusterExtension> allCallbackWrapper = + new AllCallbackWrapper<>(MINI_CLUSTER_RESOURCE); + + // ------------------------------------------------------------------------ + // test cases + // ------------------------------------------------------------------------ + @Test + public void testBoundedTextFileSourceWithJackson() throws Exception { + writeFile(outDir, "data.csv", CSV_LINES); + + final CsvReaderFormat<CityPojo> csvFormat = CsvReaderFormat.forPojo(CityPojo.class); + final List<CityPojo> result = initializeSourceAndReadData(outDir, csvFormat); + + assertEquals(Arrays.asList(pojos), result); + } + + @Test + public void testCustomBulkWriter() throws Exception { + + final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); + env.setParallelism(PARALLELISM); + env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0)); + + // fromCollection is not bounded, using fromSequence instead + final List<CityPojo> pojosList = Arrays.asList(pojos); // needs to be Serializable + final DataStream<Integer> sequence = + env.fromSequence(0, pojos.length - 1).map(Long::intValue); + final DataStream<CityPojo> stream = sequence.map(pojosList::get).returns(CityPojo.class); + + FileSink<CityPojo> sink = + FileSink.forBulkFormat(new Path(outDir.toURI()), factoryForPojo(CityPojo.class)) + .withBucketAssigner(new BasePathBucketAssigner<>()) + .build(); + + stream.sinkTo(sink); + env.execute(); + + String[] result = getResultsFromSinkFiles(outDir); + + assertThat(result).containsExactlyInAnyOrder(CSV_LINES); Review comment: Not sure what you mean, the call is checking that the lines are there in any order (containsExactlyIn*Any*Order) -- 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]
