deniskuzZ commented on code in PR #6152: URL: https://github.com/apache/hive/pull/6152#discussion_r2618512887
########## iceberg/iceberg-handler/src/main/java/org/apache/iceberg/parquet/VariantUtil.java: ########## @@ -0,0 +1,103 @@ +/* + * 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.parquet; + +import java.util.Map; +import java.util.Optional; +import java.util.function.Supplier; +import org.apache.iceberg.Schema; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.mr.InputFormatConfig; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.variants.Variant; + +public class VariantUtil { + + private VariantUtil() { + } + + /** + * Create a VariantShreddingFunction if variant shredding is enabled and the schema has variant columns. + * + * @param schema The Iceberg schema + * @param sampleRecord A sample record to infer variant schemas from actual data (can be null) + * @param properties Table properties to check if variant shredding is enabled + * @return An Optional containing the VariantShreddingFunction if applicable + */ + public static Optional<VariantShreddingFunction> variantShreddingFunc( + Schema schema, + Supplier<Record> sampleRecord, + Map<String, String> properties) { + + // Preconditions: must have variant columns + property enabled + if (!hasVariantColumns(schema) || !isVariantShreddingEnabled(properties)) { + return Optional.empty(); + } + + VariantShreddingFunction fn = + constructVariantShreddingFunc(sampleRecord.get(), schema); + + return Optional.of(fn); + } + + private static VariantShreddingFunction constructVariantShreddingFunc( + Record sampleRecord, Schema schema) { + + return (id, name) -> { + // Validate the field exists and is a variant type + Types.NestedField field = schema.findField(id); + + if (field == null || !(field.type() instanceof Types.VariantType)) { + return null; // Not a variant field, no shredding + } + + // If we have a sample record, try to generate schema from actual data + if (sampleRecord != null) { + try { + Object variantValue = sampleRecord.getField(name); + if (variantValue instanceof Variant variant) { + // Use ParquetVariantUtil to generate schema from actual variant value + return ParquetVariantUtil.toParquetSchema(variant.value()); + } + } catch (Exception e) { + // Fall through to default schema + } + } + return null; + }; + } + + /** + * Check if the schema contains any variant columns. + */ + private static boolean hasVariantColumns(Schema schema) { + return schema.columns().stream() + .anyMatch(field -> field.type() instanceof Types.VariantType); Review Comment: > This is very common haven't found this on any resources, documentation of variant shredding is pretty limited. Storing the schema as: ```` STRUCT< metadata: STRUCT<ts, source, version>, payload: VARIANT > ```` has some downsides: - Query complexity: Every time you want to filter or join by metadata.ts or metadata.source, you have to dig into the nested struct (PPD for structs is not supported by Hive-Iceberg). - Schema evolution: If you want to add new metadata fields later, nested structs can make evolution tricky without rewriting the table. not sure we even support this `ALTER TABLE my_table ADD COLUMN metadata.new_field STRING;` - Analytical usefulness: Often, metadata like ts, source, version is used more frequently for filtering, auditing, or incremental ingestion than the payload itself. Keeping it separate makes this more convenient. ########## iceberg/iceberg-handler/src/main/java/org/apache/iceberg/parquet/VariantUtil.java: ########## @@ -0,0 +1,103 @@ +/* + * 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.parquet; + +import java.util.Map; +import java.util.Optional; +import java.util.function.Supplier; +import org.apache.iceberg.Schema; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.mr.InputFormatConfig; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.variants.Variant; + +public class VariantUtil { + + private VariantUtil() { + } + + /** + * Create a VariantShreddingFunction if variant shredding is enabled and the schema has variant columns. + * + * @param schema The Iceberg schema + * @param sampleRecord A sample record to infer variant schemas from actual data (can be null) + * @param properties Table properties to check if variant shredding is enabled + * @return An Optional containing the VariantShreddingFunction if applicable + */ + public static Optional<VariantShreddingFunction> variantShreddingFunc( + Schema schema, + Supplier<Record> sampleRecord, + Map<String, String> properties) { + + // Preconditions: must have variant columns + property enabled + if (!hasVariantColumns(schema) || !isVariantShreddingEnabled(properties)) { + return Optional.empty(); + } + + VariantShreddingFunction fn = + constructVariantShreddingFunc(sampleRecord.get(), schema); + + return Optional.of(fn); + } + + private static VariantShreddingFunction constructVariantShreddingFunc( + Record sampleRecord, Schema schema) { + + return (id, name) -> { + // Validate the field exists and is a variant type + Types.NestedField field = schema.findField(id); + + if (field == null || !(field.type() instanceof Types.VariantType)) { + return null; // Not a variant field, no shredding + } + + // If we have a sample record, try to generate schema from actual data + if (sampleRecord != null) { + try { + Object variantValue = sampleRecord.getField(name); + if (variantValue instanceof Variant variant) { + // Use ParquetVariantUtil to generate schema from actual variant value + return ParquetVariantUtil.toParquetSchema(variant.value()); + } + } catch (Exception e) { + // Fall through to default schema + } + } + return null; + }; + } + + /** + * Check if the schema contains any variant columns. + */ + private static boolean hasVariantColumns(Schema schema) { + return schema.columns().stream() + .anyMatch(field -> field.type() instanceof Types.VariantType); Review Comment: > This is very common haven't found this on any resources, documentation of variant shredding is pretty limited. Storing the schema as: ```` STRUCT< metadata: STRUCT<ts, source, version>, payload: VARIANT > ```` has some downsides: - Query complexity: Every time you want to filter or join by metadata.ts or metadata.source, you have to dig into the nested struct (PPD for structs is not supported by Hive-Iceberg). - Schema evolution: If you want to add new metadata fields later, nested structs can make evolution tricky without rewriting the table. not sure we even support this `ALTER TABLE my_table ADD COLUMN metadata.new_field STRING;` - Analytical usefulness: Often, metadata like ts, source, version is used more frequently for filtering, auditing, or incremental ingestion than the payload itself. Keeping it separate makes this more convenient. -- 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]
