ZENOTME commented on code in PR #703: URL: https://github.com/apache/iceberg-rust/pull/703#discussion_r1858083873
########## crates/iceberg/src/arrow/record_batch_projector.rs: ########## @@ -0,0 +1,261 @@ +// 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::sync::Arc; + +use arrow_array::{ArrayRef, RecordBatch, StructArray}; +use arrow_schema::{DataType, Field, FieldRef, Fields, Schema, SchemaRef}; + +use crate::error::Result; +use crate::{Error, ErrorKind}; + +/// Help to project specific field from `RecordBatch`` according to the fields id of meta of field. +#[derive(Clone)] +pub struct RecordBatchProjector { + // A vector of vectors, where each inner vector represents the index path to access a specific field in a nested structure. + // E.g. [[0], [1, 2]] means the first field is accessed directly from the first column, + // while the second field is accessed from the second column and then from its third subcolumn (second column must be a struct column). + field_indices: Vec<Vec<usize>>, + // The schema reference after projection. This schema is derived from the original schema based on the given field IDs. + projected_schema: SchemaRef, +} + +impl RecordBatchProjector { + /// Init ArrowFieldProjector + pub fn new<F>( + original_schema: SchemaRef, + field_ids: &[i32], + field_id_fetch_func: F, + ) -> Result<Self> + where + F: Fn(&Field) -> Option<i64>, + { + let mut field_indices = Vec::with_capacity(field_ids.len()); + let mut fields = Vec::with_capacity(field_ids.len()); + for &id in field_ids { + let mut field_index = vec![]; + if let Ok(field) = Self::fetch_field_index( + original_schema.fields(), + &mut field_index, + id as i64, + &field_id_fetch_func, + ) { + fields.push(field.clone()); + field_indices.push(field_index); + } else { + return Err(Error::new( + ErrorKind::DataInvalid, + format!( + "Can't find source column id or column data type invalid: {}", + id + ), + )); + } + } + let delete_arrow_schema = Arc::new(Schema::new(fields)); + Ok(Self { + field_indices, + projected_schema: delete_arrow_schema, + }) + } + + fn fetch_field_index<F>( + fields: &Fields, + index_vec: &mut Vec<usize>, + target_field_id: i64, + field_id_fetch_func: &F, + ) -> Result<FieldRef> + where + F: Fn(&Field) -> Option<i64>, + { + for (pos, field) in fields.iter().enumerate() { + match field.data_type() { + DataType::Float16 | DataType::Float32 | DataType::Float64 => { + return Err(Error::new( + ErrorKind::DataInvalid, + "Delete column data type cannot be float or double", + )); + } Review Comment: Yes, my bad. I'm trying to separate this out. -- 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
