afedulov commented on a change in pull request #17598: URL: https://github.com/apache/flink/pull/17598#discussion_r779596112
########## File path: flink-formats/flink-csv/src/test/java/org/apache/flink/formats/csv/DataStreamCsvITCase.java ########## @@ -0,0 +1,351 @@ +/* + * 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.src.FileSource; +import org.apache.flink.connector.file.src.reader.StreamFormat; +import org.apache.flink.core.fs.Path; +import org.apache.flink.formats.common.Converter; +import org.apache.flink.runtime.minicluster.RpcServiceSharing; +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.StreamingFileSink; +import org.apache.flink.streaming.api.functions.sink.filesystem.bucketassigners.BasePathBucketAssigner; +import org.apache.flink.streaming.api.operators.StreamSink; +import org.apache.flink.streaming.api.operators.collect.ClientAndIterator; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.streaming.util.OneInputStreamOperatorTestHarness; +import org.apache.flink.test.util.MiniClusterWithClientResource; +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.junit.ClassRule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; + +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.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 static org.apache.flink.streaming.api.functions.sink.filesystem.rollingpolicies.OnCheckpointRollingPolicy.build; +import static org.hamcrest.MatcherAssert.assertThat; +import static org.hamcrest.core.Is.is; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; + +/** MiniCluster-based integration tests CSV data format. */ +public class DataStreamCsvITCase extends TestLogger { + + private static final int PARALLELISM = 4; + + @ClassRule public static final TemporaryFolder TMP_FOLDER = new TemporaryFolder(); + + @ClassRule + public static final MiniClusterWithClientResource miniClusterResource = + new MiniClusterWithClientResource( + new MiniClusterResourceConfiguration.Builder() + .setNumberTaskManagers(1) + .setNumberSlotsPerTaskManager(PARALLELISM) + .setRpcServiceSharing(RpcServiceSharing.DEDICATED) + .withHaLeadershipControl() + .build()); + + // ------------------------------------------------------------------------ + // test cases + // ------------------------------------------------------------------------ + @Test Review comment: It is actually also tested implicitly via `fromPojo` https://github.com/afedulov/flink/blob/02355cdca67d73500f5251834bc07df18ec1f2a8/flink-formats/flink-csv/src/main/java/org/apache/flink/formats/csv/CsvReaderFormat.java#L109 Apart from the native schema construction via Jackson there seems not much be changed in the additional test. Or do you see it differently? -- 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: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
