[GitHub] [iceberg] kbendick commented on a change in pull request #4364: Flink - Fix incorrect / old row being written into delta files when using upsert mode - DO NOT MERGE

[GitBox <gi...@apache.org>]

kbendick commented on a change in pull request #4364:
URL: https://github.com/apache/iceberg/pull/4364#discussion_r830685675



##########
File path: flink/v1.14/flink/src/test/java/org/apache/iceberg/flink/TestFlinkUpsert.java
##########
@@ -0,0 +1,302 @@
+/*
+ * 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.iceberg.flink;
+
+import java.time.LocalDate;
+import java.util.List;
+import java.util.Map;
+import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
+import org.apache.flink.table.api.EnvironmentSettings;
+import org.apache.flink.table.api.TableEnvironment;
+import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
+import org.apache.flink.test.util.MiniClusterWithClientResource;
+import org.apache.flink.types.Row;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.TableProperties;
+import org.apache.iceberg.catalog.Namespace;
+import org.apache.iceberg.flink.source.BoundedTableFactory;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.relocated.com.google.common.collect.Sets;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.ClassRule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+import org.junit.runner.RunWith;
+import org.junit.runners.Parameterized;
+
+@RunWith(Parameterized.class)
+public class TestFlinkUpsert extends FlinkCatalogTestBase {
+
+  @ClassRule
+  public static final MiniClusterWithClientResource MINI_CLUSTER_RESOURCE =
+      MiniClusterResource.createWithClassloaderCheckDisabled();
+
+  @ClassRule
+  public static final TemporaryFolder TEMPORARY_FOLDER = new TemporaryFolder();
+
+  private final boolean isStreamingJob;
+  private final Map<String, String> tableUpsertProps = Maps.newHashMap();
+  private TableEnvironment tEnv;
+
+  public TestFlinkUpsert(String catalogName, Namespace baseNamespace, FileFormat format, Boolean isStreamingJob) {
+    super(catalogName, baseNamespace);
+    this.isStreamingJob = isStreamingJob;
+    tableUpsertProps.put(TableProperties.FORMAT_VERSION, "2");
+    tableUpsertProps.put(TableProperties.UPSERT_ENABLED, "true");
+    tableUpsertProps.put(TableProperties.DEFAULT_FILE_FORMAT, format.name());
+  }
+
+  @Parameterized.Parameters(name = "catalogName={0}, baseNamespace={1}, format={2}, isStreaming={3}")
+  public static Iterable<Object[]> parameters() {
+    List<Object[]> parameters = Lists.newArrayList();
+    for (FileFormat format : new FileFormat[] {FileFormat.PARQUET, FileFormat.AVRO, FileFormat.ORC}) {
+      for (Boolean isStreaming : new Boolean[] {true, false}) {
+        for (Object[] catalogParams : FlinkCatalogTestBase.parameters()) {

Review comment:
       Yeah agreed. It's been beneficial while testing locally.
   
   And admittedly the issue did not occur with Avro originally due to the lack of stats as mentioned, so I'd be fine with just parquet and one catalog.
   
   I'd even prefer to test all 3 and only one catalog, because the test is fairly end to end. But I'm fine with only parquet and then two catalogs.




-- 
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-unsubscribe@iceberg.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org