swapna267 commented on code in PR #16450: URL: https://github.com/apache/iceberg/pull/16450#discussion_r3320407537
########## flink/v2.1/flink/src/main/java/org/apache/iceberg/flink/sink/dynamic/VariantAvroDynamicTableRecordGenerator.java: ########## @@ -0,0 +1,203 @@ +/* + * 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.dynamic; + +import java.util.Map; +import org.apache.avro.Schema.Parser; +import org.apache.flink.api.common.functions.OpenContext; +import org.apache.flink.configuration.ConfigOption; +import org.apache.flink.configuration.Configuration; +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.flink.table.types.logical.VarCharType; +import org.apache.flink.table.types.logical.VariantType; +import org.apache.flink.types.variant.Variant; +import org.apache.flink.util.Collector; +import org.apache.iceberg.DistributionMode; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.avro.AvroSchemaUtil; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.FlinkCreateTableOptions; +import org.apache.iceberg.flink.FlinkSchemaUtil; +import org.apache.iceberg.flink.FlinkWriteOptions; +import org.apache.iceberg.flink.data.VariantRowDataWrapper; +import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.base.Splitter; + +public class VariantAvroDynamicTableRecordGenerator extends DynamicTableRecordGenerator { + + @VisibleForTesting static final String DATA_COLUMN = "data"; + @VisibleForTesting static final String AVRO_SCHEMA_COLUMN = "avro_schema"; + @VisibleForTesting static final String AVRO_SCHEMA_ID_COLUMN = "avro_schema_id"; Review Comment: This particular implementation `VariantAvroDynamicTableRecordGenerator` of `DynamicTableRecordGenerator` is basically taking care of Flink's Variant / Avro schema combination for most common ingestion pipelines. Plan is also to add one more implementation of `DynamicTableRecordGenerator` , where we will not have any Schema passed and Schema will be inferred directly from Variant column itself. Idea was like, these 2 concrete implementations can provide basis and example for any other custom implementations like one which can take Iceberg schema directly. -- 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]
