kengtin commented on code in PR #7161: URL: https://github.com/apache/iceberg/pull/7161#discussion_r1169275167
########## flink/v1.16/flink/src/main/java/org/apache/iceberg/flink/sink/BucketPartitionKeySelector.java: ########## @@ -0,0 +1,80 @@ +/* + * 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; + +import java.util.List; +import java.util.stream.IntStream; +import org.apache.flink.api.java.functions.KeySelector; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.types.logical.RowType; +import org.apache.iceberg.PartitionKey; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.flink.RowDataWrapper; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; + +/** + * Very similar to the {@link PartitionKeySelector}, but optimized to extract and return an Integer + * bucketId as the key. + */ +class BucketPartitionKeySelector implements KeySelector<RowData, Integer> { + + private final Schema schema; + private final PartitionKey partitionKey; + private final RowType flinkSchema; + private final int bucketFieldPosition; + + private transient RowDataWrapper rowDataWrapper; + + BucketPartitionKeySelector(PartitionSpec spec, Schema schema, RowType flinkSchema) { + List<Tuple2<Integer, Integer>> bucketFields = BucketPartitionerUtils.getBucketFields(spec); + + // The current implementation only supports ONE bucket + Preconditions.checkArgument( + bucketFields.size() == 1, + BucketPartitionerUtils.BAD_NUMBER_OF_BUCKETS_ERROR_MESSAGE + bucketFields.size()); Review Comment: The main point here is that I'm using the function in 3 places, two of which need to fail if is not 1 bucket, but the other (in `FlinkSink`) only falls back to the default partitioning instead of failing. However all 3 places need to "check" we're only dealing with 1 bucket. -- 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
