pvary commented on code in PR #10179: URL: https://github.com/apache/iceberg/pull/10179#discussion_r1592011406
########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/sink/committer/TestSinkCommitter.java: ########## @@ -0,0 +1,812 @@ +/* + * 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.sink.committer; + +import static org.apache.iceberg.flink.sink.SinkTestUtil.fromOutput; +import static org.apache.iceberg.flink.sink.SinkTestUtil.toCommittableSummary; +import static org.assertj.core.api.Assertions.assertThat; +import static org.assertj.core.api.Assumptions.assumeThat; + +import java.io.File; +import java.io.IOException; +import java.nio.ByteBuffer; +import java.nio.ByteOrder; +import java.util.Collection; +import java.util.List; +import java.util.Map; +import org.apache.flink.api.common.typeutils.TypeSerializer; +import org.apache.flink.api.common.typeutils.TypeSerializerSnapshot; +import org.apache.flink.core.memory.DataInputView; +import org.apache.flink.core.memory.DataOutputView; +import org.apache.flink.runtime.checkpoint.OperatorSubtaskState; +import org.apache.flink.streaming.api.connector.sink2.CommittableMessage; +import org.apache.flink.streaming.api.connector.sink2.CommittableMessageSerializer; +import org.apache.flink.streaming.api.connector.sink2.CommittableSummary; +import org.apache.flink.streaming.api.connector.sink2.CommittableWithLineage; +import org.apache.flink.streaming.api.connector.sink2.SinkV2Assertions; +import org.apache.flink.streaming.runtime.operators.sink.CommitterOperatorFactory; +import org.apache.flink.streaming.runtime.streamrecord.StreamElement; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.streaming.util.OneInputStreamOperatorTestHarness; +import org.apache.flink.table.data.RowData; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.DeleteFile; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.Parameter; +import org.apache.iceberg.ParameterizedTestExtension; +import org.apache.iceberg.Parameters; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.SnapshotSummary; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.TestBase; +import org.apache.iceberg.flink.FlinkSchemaUtil; +import org.apache.iceberg.flink.SimpleDataUtil; +import org.apache.iceberg.flink.TableLoader; +import org.apache.iceberg.flink.sink.FlinkAppenderFactory; +import org.apache.iceberg.flink.sink.IcebergSink; +import org.apache.iceberg.io.FileAppenderFactory; +import org.apache.iceberg.io.WriteResult; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.TestTemplate; +import org.junit.jupiter.api.extension.ExtendWith; +import org.junit.jupiter.api.io.TempDir; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +@ExtendWith(ParameterizedTestExtension.class) +class TestSinkCommitter extends TestBase { + private static final Logger LOG = LoggerFactory.getLogger(TestSinkCommitter.class); + private static final Configuration CONF = new Configuration(); + + @TempDir File temporaryFolder; + + private Table table; + private TableLoader tableLoader; + + @Parameter(index = 1) + private FileFormat format; + + @Parameter(index = 2) + private Boolean isBatchMode; + + @Parameter(index = 3) + private Boolean isCheckpointingEnabled; + + private final long dataFIleRowCount = 5L; + private SinkAggregator sinkAggregator; + + private final DataFile dataFileTest1 = + DataFiles.builder(PartitionSpec.unpartitioned()) + .withPath("/path/to/data-1.parquet") + .withFileSizeInBytes(0) + .withMetrics( + new Metrics( + dataFIleRowCount, + null, // no column sizes + ImmutableMap.of(1, 5L), // value count + ImmutableMap.of(1, 0L), // null count + null, + ImmutableMap.of(1, longToBuffer(0L)), // lower bounds + ImmutableMap.of(1, longToBuffer(4L)) // upper bounds + )) + .build(); + + private final DataFile dataFileTest2 = + DataFiles.builder(PartitionSpec.unpartitioned()) + .withPath("/path/to/data-2.parquet") + .withFileSizeInBytes(0) + .withMetrics( + new Metrics( + dataFIleRowCount, + null, // no column sizes + ImmutableMap.of(1, 5L), // value count + ImmutableMap.of(1, 0L), // null count + null, + ImmutableMap.of(1, longToBuffer(0L)), // lower bounds + ImmutableMap.of(1, longToBuffer(4L)) // upper bounds + )) + .build(); + + @Parameters(name = "format={0}, isStreaming={1}, isCheckpointingEnabled={2}") + protected static List<Object> parameters() { + List<Object> parameters = Lists.newArrayList(); + for (FileFormat format : + new FileFormat[] {FileFormat.PARQUET, FileFormat.AVRO, FileFormat.ORC}) { + for (Boolean isBatchMode : new Boolean[] {true, false}) { + for (Boolean isCheckpointingEnabled : new Boolean[] {true, false}) { + parameters.add(new Object[] {2, format, isBatchMode, isCheckpointingEnabled}); + } + } + } + return parameters; + } + + @BeforeEach + public void before() throws Exception { + String warehouse = temporaryFolder.getAbsolutePath(); + + String tablePath = warehouse.concat("/test"); + assertThat(new File(tablePath).mkdir()).as("Should create the table path correctly.").isTrue(); + + Map<String, String> props = + ImmutableMap.of( + TableProperties.DEFAULT_FILE_FORMAT, format.name(), + TableProperties.FORMAT_VERSION, String.valueOf(formatVersion)); + table = SimpleDataUtil.createTable(tablePath, props, false); + tableLoader = TableLoader.fromHadoopTable(tablePath); + + sinkAggregator = new SinkAggregator(tableLoader, "flink_job"); + sinkAggregator.open(); + } + + // public TestSinkCommitter( + // int formatVersion, FileFormat format, Boolean isBatchMode, Boolean isCheckpointingEnabled) + // { + // this.formatVersion = formatVersion; + // this.format = format; + // this.isBatchMode = isBatchMode; + // this.isCheckpointingEnabled = isCheckpointingEnabled; + // } Review Comment: remove -- 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...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
