liurenjie1024 commented on code in PR #176: URL: https://github.com/apache/iceberg-rust/pull/176#discussion_r1477561649
########## crates/iceberg/src/writer/file_writer/location_generator.rs: ########## @@ -0,0 +1,108 @@ +// 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. + +//! This module contains the location generator and file name generator for generating path of data file. + +use std::sync::{atomic::AtomicU64, Arc}; + +/// `LocationGenerator` used to generate the location of data file. +pub trait LocationGenerator: Clone + Send + 'static { + /// Generate a absolute path for the given file name. + /// e.g + /// For file name "part-00000.parquet", the generated location maybe "/table/data/part-00000.parquet" + fn generate_location(&self, file_name: &str) -> String; Review Comment: We also need to add `partition_value` as parameter? This may affect the absolute path of file. ########## crates/iceberg/src/writer/file_writer/location_generator.rs: ########## @@ -0,0 +1,108 @@ +// 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. + +//! This module contains the location generator and file name generator for generating path of data file. + +use std::sync::{atomic::AtomicU64, Arc}; + +/// `LocationGenerator` used to generate the location of data file. +pub trait LocationGenerator: Clone + Send + 'static { + /// Generate a absolute path for the given file name. Review Comment: ```suggestion /// Generate an absolute path for the given file name. ``` ########## crates/iceberg/src/writer/file_writer/location_generator.rs: ########## @@ -0,0 +1,108 @@ +// 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. + +//! This module contains the location generator and file name generator for generating path of data file. + +use std::sync::{atomic::AtomicU64, Arc}; + +/// `LocationGenerator` used to generate the location of data file. +pub trait LocationGenerator: Clone + Send + 'static { + /// Generate a absolute path for the given file name. + /// e.g + /// For file name "part-00000.parquet", the generated location maybe "/table/data/part-00000.parquet" + fn generate_location(&self, file_name: &str) -> String; +} + +/// `FileNameGeneratorTrait` used to generate file name for data file. The file name can be passed to `LocationGenerator` to generate the location of the file. +pub trait FileNameGenerator: Clone + Send + 'static { + /// Generate a file name. + fn generate_file_name(&self) -> String; +} + +/// `DefaultFileNameGenerator` used to generate file name for data file. The file name can be +/// passed to `LocationGenerator` to generate the location of the file. +/// The rule of file name is aligned with the OutputFileFactory in iceberg-java +#[derive(Clone)] +pub struct DefaultFileNameGenerator { + partition_id: u64, + task_id: u64, + // The purpose of this id is to be able to know from two paths that they were written by the + // same operation. + // That's useful, for example, if a Spark job dies and leaves files in the file system, you can + // identify them all + // with a recursive listing and grep. + operator_id: String, + suffix: String, Review Comment: It's safer to use `DataFileFormat`? ########## crates/iceberg/src/writer/file_writer/location_generator.rs: ########## @@ -0,0 +1,108 @@ +// 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. + +//! This module contains the location generator and file name generator for generating path of data file. + +use std::sync::{atomic::AtomicU64, Arc}; + +/// `LocationGenerator` used to generate the location of data file. +pub trait LocationGenerator: Clone + Send + 'static { + /// Generate a absolute path for the given file name. + /// e.g + /// For file name "part-00000.parquet", the generated location maybe "/table/data/part-00000.parquet" + fn generate_location(&self, file_name: &str) -> String; +} + +/// `FileNameGeneratorTrait` used to generate file name for data file. The file name can be passed to `LocationGenerator` to generate the location of the file. +pub trait FileNameGenerator: Clone + Send + 'static { + /// Generate a file name. + fn generate_file_name(&self) -> String; +} + +/// `DefaultFileNameGenerator` used to generate file name for data file. The file name can be +/// passed to `LocationGenerator` to generate the location of the file. +/// The rule of file name is aligned with the OutputFileFactory in iceberg-java +#[derive(Clone)] +pub struct DefaultFileNameGenerator { + partition_id: u64, Review Comment: I'm hesitating to add these concepts `partition_id`, `task_id`, `operator_id` in the core crate, since these are all computation related concepts. As default, I this a random uuid would be enough. Compute engines can always override this trait. -- 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
