[GitHub] [hudi] JerryYue-M commented on a diff in pull request #5445: [HUDI-3953]Flink Hudi module should support low-level source and sink…

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

JerryYue-M commented on code in PR #5445:
URL: https://github.com/apache/hudi/pull/5445#discussion_r862311102


##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/sink/utils/ITTestHoodiePipeline.java:
##########
@@ -0,0 +1,220 @@
+
+/*
+ * 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.hudi.sink.utils;
+
+import org.apache.hudi.common.model.HoodieTableType;
+import org.apache.hudi.configuration.FlinkOptions;
+import org.apache.hudi.util.AvroSchemaConverter;
+import org.apache.hudi.util.HoodiePipeline;
+import org.apache.hudi.util.StreamerUtil;
+import org.apache.hudi.utils.TestConfigurations;
+import org.apache.hudi.utils.TestData;
+import org.apache.hudi.utils.TestUtils;
+import org.apache.hudi.utils.source.ContinuousFileSource;
+
+import org.apache.flink.api.common.JobStatus;
+import org.apache.flink.api.common.io.FilePathFilter;
+import org.apache.flink.api.common.typeinfo.BasicTypeInfo;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.java.io.TextInputFormat;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.core.execution.JobClient;
+import org.apache.flink.core.fs.Path;
+import org.apache.flink.formats.common.TimestampFormat;
+import org.apache.flink.formats.json.JsonRowDataDeserializationSchema;
+import org.apache.flink.streaming.api.CheckpointingMode;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
+import org.apache.flink.streaming.api.functions.sink.SinkFunction;
+import org.apache.flink.streaming.api.functions.source.FileProcessingMode;
+import org.apache.flink.table.api.EnvironmentSettings;
+import org.apache.flink.table.api.TableEnvironment;
+import org.apache.flink.table.api.config.ExecutionConfigOptions;
+import org.apache.flink.table.api.internal.TableEnvironmentImpl;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.runtime.typeutils.InternalTypeInfo;
+import org.apache.flink.table.types.logical.RowType;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.io.TempDir;
+
+import java.io.File;
+import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Objects;
+import java.util.concurrent.TimeUnit;
+
+import static org.apache.hudi.sink.ITTestDataStreamWrite.EXPECTED;
+import static org.apache.hudi.utils.TestData.assertRowDataEquals;
+
+/**
+ *  IT test for test hoodie pipeline.
+ */
+public class ITTestHoodiePipeline {
+
+  public static final List<RowData> RESULT = new ArrayList<>();
+  @TempDir
+  File tempFile;
+  private StreamExecutionEnvironment execEnv;
+  private boolean isMor;
+  private Map<String, String> options = new HashMap<>();
+  private TableEnvironment streamTableEnv;
+
+  @BeforeEach
+  void beforEach() {
+    this.execEnv = StreamExecutionEnvironment.getExecutionEnvironment();
+    execEnv.getConfig().disableObjectReuse();
+    execEnv.setParallelism(4);
+    // set up checkpoint interval
+    execEnv.enableCheckpointing(4000, CheckpointingMode.EXACTLY_ONCE);
+    execEnv.getCheckpointConfig().setMaxConcurrentCheckpoints(1);
+
+    options.put(FlinkOptions.INDEX_TYPE.key(), "FLINK_STATE");
+    options.put(FlinkOptions.PATH.key(), tempFile.getAbsolutePath());
+    options.put(FlinkOptions.BUCKET_INDEX_NUM_BUCKETS.key(), "4");
+    options.put("table.type", HoodieTableType.MERGE_ON_READ.name());
+    options.put(FlinkOptions.INDEX_KEY_FIELD.key(), "id");
+    options.put(FlinkOptions.COMPACTION_DELTA_COMMITS.key(), "1");
+    options.put(FlinkOptions.TABLE_TYPE.key(), HoodieTableType.MERGE_ON_READ.name());
+    options.put(FlinkOptions.SOURCE_AVRO_SCHEMA_PATH.key(), Objects.requireNonNull(Thread.currentThread().getContextClassLoader().getResource("test_read_schema.avsc")).toString());
+
+    this.isMor = options.get(FlinkOptions.TABLE_TYPE.key()).equals(HoodieTableType.MERGE_ON_READ.name());
+
+    EnvironmentSettings settings = EnvironmentSettings.newInstance().build();
+    streamTableEnv = TableEnvironmentImpl.create(settings);
+    streamTableEnv.getConfig().getConfiguration().setInteger(ExecutionConfigOptions.TABLE_EXEC_RESOURCE_DEFAULT_PARALLELISM, 1);
+    Configuration execConf = streamTableEnv.getConfig().getConfiguration();
+    execConf.setString("execution.checkpointing.interval", "2s");
+    // configure not to retry after failure
+    execConf.setString("restart-strategy", "fixed-delay");
+    execConf.setString("restart-strategy.fixed-delay.attempts", "0");
+  }
+
+  @Test
+  public void testSink() throws Exception {
+    DataStream<RowData> dataStream = inputDataStream(this.execEnv, options, isMor);
+

Review Comment:
   yes. I will move testSink() to ITTestDataStreamWrite and move testSource() to ITTestHoodieDataSource



-- 
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: commits-unsubscribe@hudi.apache.org

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