alexeykudinkin commented on code in PR #5943: URL: https://github.com/apache/hudi/pull/5943#discussion_r929059483
########## hudi-spark-datasource/hudi-spark3.3.x/src/main/scala/org/apache/spark/sql/execution/datasources/Spark33NestedSchemaPruning.scala: ########## @@ -0,0 +1,195 @@ +/* + * 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.spark.sql.execution.datasources + +import org.apache.hudi.HoodieBaseRelation +import org.apache.spark.sql.catalyst.expressions.{And, AttributeReference, AttributeSet, Expression, NamedExpression, ProjectionOverSchema} +import org.apache.spark.sql.catalyst.planning.PhysicalOperation +import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan, Project} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.sources.BaseRelation +import org.apache.spark.sql.types.{ArrayType, DataType, MapType, StructType} +import org.apache.spark.sql.util.SchemaUtils.restoreOriginalOutputNames + +/** + * Prunes unnecessary physical columns given a [[PhysicalOperation]] over a data source relation. + * By "physical column", we mean a column as defined in the data source format like Parquet format + * or ORC format. For example, in Spark SQL, a root-level Parquet column corresponds to a SQL + * column, and a nested Parquet column corresponds to a [[StructField]]. Review Comment: As we've discussed, please create an issue to back-port one from Spark 3.3 and revisit this one ########## hudi-spark-datasource/hudi-spark3.3.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark33HoodieParquetFileFormat.scala: ########## @@ -0,0 +1,505 @@ +/* + * 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.spark.sql.execution.datasources.parquet + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.Path +import org.apache.hadoop.mapred.FileSplit +import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl +import org.apache.hadoop.mapreduce.{JobID, TaskAttemptID, TaskID, TaskType} +import org.apache.hudi.HoodieSparkUtils +import org.apache.hudi.client.utils.SparkInternalSchemaConverter +import org.apache.hudi.common.fs.FSUtils +import org.apache.hudi.common.util.InternalSchemaCache +import org.apache.hudi.common.util.StringUtils.isNullOrEmpty +import org.apache.hudi.common.util.collection.Pair +import org.apache.hudi.internal.schema.InternalSchema +import org.apache.hudi.internal.schema.action.InternalSchemaMerger +import org.apache.hudi.internal.schema.utils.{InternalSchemaUtils, SerDeHelper} +import org.apache.parquet.filter2.compat.FilterCompat +import org.apache.parquet.filter2.predicate.FilterApi +import org.apache.parquet.format.converter.ParquetMetadataConverter.SKIP_ROW_GROUPS +import org.apache.parquet.hadoop.{ParquetInputFormat, ParquetRecordReader} +import org.apache.spark.TaskContext +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection +import org.apache.spark.sql.catalyst.expressions.{Cast, JoinedRow} +import org.apache.spark.sql.catalyst.util.DateTimeUtils +import org.apache.spark.sql.execution.datasources.parquet.Spark33HoodieParquetFileFormat._ +import org.apache.spark.sql.execution.datasources.{DataSourceUtils, PartitionedFile, RecordReaderIterator} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.sources._ +import org.apache.spark.sql.types.{AtomicType, DataType, StructField, StructType} +import org.apache.spark.util.SerializableConfiguration + +import java.net.URI + +/** + * This class is an extension of [[ParquetFileFormat]] overriding Spark-specific behavior + * that's not possible to customize in any other way + * + * NOTE: This is a version of [[AvroDeserializer]] impl from Spark 3.2.1 w/ w/ the following changes applied to it: Review Comment: Are there any changes from Spark 3.2? Can we actually revisit all such cases and if there're actually no changes from Spark 3.2 let's just re-use these classes. If this would be more than just a simple file move (to hoodie-spark3-common), then please create a JIRA ticket to follow-up which you can assign to me -- 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]
