liurenjie1024 commented on code in PR #207: URL: https://github.com/apache/iceberg-rust/pull/207#discussion_r1508594423
########## crates/iceberg/src/file_record_batch_reader.rs: ########## Review Comment: Given that most of these operations are arrow related, how about rename this file into `arrow.rs`? We will also put arrow schema conversion here. ########## crates/iceberg/src/file_record_batch_reader.rs: ########## @@ -0,0 +1,83 @@ +// 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. + +//! Parquet file data reader + +use async_stream::try_stream; +use futures::stream::StreamExt; +use parquet::arrow::{ParquetRecordBatchStreamBuilder, ProjectionMask}; + +use crate::io::FileIO; +use crate::scan::{ArrowRecordBatchStream, FileScanTask, FileScanTaskStream}; +use crate::spec::SchemaRef; + +/// Default arrow record batch size +const DEFAULT_BATCH_SIZE: usize = 1024; + +/// Reads data from Parquet files +pub struct FileRecordBatchReader { + batch_size: Option<usize>, + #[allow(dead_code)] + schema: SchemaRef, + file_io: FileIO, +} + +impl FileRecordBatchReader { + /// Constructs a new FileRecordBatchReader + pub fn new(file_io: FileIO, schema: SchemaRef, batch_size: Option<usize>) -> Self { Review Comment: How about replacing this with builder pattern? ########## crates/iceberg/src/scan.rs: ########## @@ -445,4 +494,22 @@ mod tests { format!("{}/3.parquet", &fixture.table_location) ); } + + #[tokio::test] + async fn test_open_parquet_no_deletions() { Review Comment: While this is currently fine for unit tests, it would be better to add integrations for this. ########## crates/iceberg/src/scan.rs: ########## @@ -163,24 +164,32 @@ impl TableScan { Ok(iter(file_scan_tasks).boxed()) } + + pub async fn execute( + &self, + batch_size: Option<usize>, Review Comment: This should be put in `TableScanBuilder` rather than just passing as function argument. ########## crates/iceberg/src/scan.rs: ########## @@ -163,24 +164,32 @@ impl TableScan { Ok(iter(file_scan_tasks).boxed()) } + + pub async fn execute( Review Comment: ```suggestion pub async fn to_arrow( ``` How about making things more explicit ? -- 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
