liurenjie1024 commented on code in PR #1602: URL: https://github.com/apache/iceberg-rust/pull/1602#discussion_r2306919244
########## crates/integrations/datafusion/src/physical_plan/project.rs: ########## @@ -0,0 +1,692 @@ +// 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. + +use std::any::Any; +use std::fmt::{Debug, Formatter}; +use std::sync::Arc; + +use datafusion::arrow::array::{ArrayRef, RecordBatch, StructArray}; +use datafusion::arrow::datatypes::{ + DataType, Field, Schema as ArrowSchema, SchemaRef as ArrowSchemaRef, +}; +use datafusion::common::Result as DFResult; +use datafusion::error::DataFusionError; +use datafusion::execution::{SendableRecordBatchStream, TaskContext}; +use datafusion::physical_expr::EquivalenceProperties; +use datafusion::physical_plan::execution_plan::{Boundedness, EmissionType}; +use datafusion::physical_plan::stream::RecordBatchStreamAdapter; +use datafusion::physical_plan::{ + DisplayAs, DisplayFormatType, ExecutionPlan, ExecutionPlanProperties, PlanProperties, + execute_input_stream, +}; +use futures::StreamExt; +use iceberg::spec::{PartitionSpec, Schema}; + +use crate::to_datafusion_error; + +/// Column name for the combined partition values struct +const PARTITION_VALUES_COLUMN: &str = "_iceberg_partition_values"; + +/// An execution plan node that calculates partition values for Iceberg tables. +/// +/// This execution plan takes input data from a child execution plan and adds a single struct column +/// containing all partition values based on the table's partition specification. The partition values +/// are computed by applying the appropriate transforms to the source columns. +/// +/// The output schema includes all original columns plus a single `_iceberg_partition_values` struct column. +#[derive(Debug, Clone)] +pub(crate) struct IcebergProjectExec { + input: Arc<dyn ExecutionPlan>, + partition_spec: Arc<PartitionSpec>, + table_schema: Arc<Schema>, + output_schema: ArrowSchemaRef, + plan_properties: PlanProperties, +} + +/// IcebergProjectExec is responsible for calculating partition values for Iceberg tables. +/// It takes input data from a child execution plan and adds a single struct column containing +/// all partition values based on the table's partition specification. The partition values are +/// computed by applying the appropriate transforms to the source columns. The output schema +/// includes all original columns plus a single `_iceberg_partition_values` struct column. +/// This approach simplifies downstream repartitioning operations by providing a single column +/// that can be directly used for sorting and repartitioning. +impl IcebergProjectExec { Review Comment: Sharing similar concerns as #1620 , I don't think we need a new execution node. -- 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]
