pvary commented on code in PR #10823: URL: https://github.com/apache/iceberg/pull/10823#discussion_r1698204457
########## flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/sink/shuffle/TestSketchRangePartitioner.java: ########## @@ -0,0 +1,88 @@ +/* + * 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.shuffle; + +import static org.assertj.core.api.Assertions.assertThat; + +import org.apache.flink.table.data.GenericRowData; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.data.StringData; +import org.apache.flink.table.types.logical.RowType; +import org.apache.iceberg.SortKey; +import org.apache.iceberg.SortOrder; +import org.apache.iceberg.flink.FlinkSchemaUtil; +import org.apache.iceberg.flink.RowDataWrapper; +import org.apache.iceberg.flink.TestFixtures; +import org.junit.jupiter.api.Test; + +public class TestSketchRangePartitioner { + // sort on the long id field + private static final SortOrder SORT_ORDER = + SortOrder.builderFor(TestFixtures.SCHEMA).asc("id").build(); + private static final SortKey SORT_KEY = new SortKey(TestFixtures.SCHEMA, SORT_ORDER); + private static final RowType ROW_TYPE = FlinkSchemaUtil.convert(TestFixtures.SCHEMA); + private static final int NUM_PARTITIONS = 16; + private static final long RANGE_STEP = 1_000; + private static final long MAX_ID = RANGE_STEP * NUM_PARTITIONS; + private static final SortKey[] RANGE_BOUNDS = createRangeBounds(); + + /** + * To understand how range bounds are used in range partitioning, here is an example for human + * ages with 4 partitions: [15, 32, 60]. The 4 ranges would be + * + * <ul> + * <li>age <= 15 + * <li>age > 15 && age <= 32 + * <li>age >32 && age <= 60 + * <li>age > 60 + * </ul> + */ + private static SortKey[] createRangeBounds() { + SortKey[] rangeBounds = new SortKey[NUM_PARTITIONS - 1]; + for (int i = 0; i < NUM_PARTITIONS - 1; ++i) { + RowData rowData = + GenericRowData.of( + StringData.fromString("data"), + RANGE_STEP * (i + 1), + StringData.fromString("2023-06-20")); + RowDataWrapper keyWrapper = new RowDataWrapper(ROW_TYPE, TestFixtures.SCHEMA.asStruct()); + keyWrapper.wrap(rowData); + SortKey sortKey = new SortKey(TestFixtures.SCHEMA, SORT_ORDER); + sortKey.wrap(keyWrapper); + rangeBounds[i] = sortKey; + } + + return rangeBounds; + } + + @Test + public void test() { Review Comment: Could we have a more meaningful name? -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
