xxchan commented on code in PR #822: URL: https://github.com/apache/iceberg-rust/pull/822#discussion_r1899506899
########## crates/iceberg/src/metadata_scan.rs: ########## @@ -0,0 +1,265 @@ +// 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. + +//! Metadata table api. + +use std::sync::Arc; + +use arrow_array::builder::{MapBuilder, PrimitiveBuilder, StringBuilder}; +use arrow_array::types::{Int64Type, TimestampMillisecondType}; +use arrow_array::RecordBatch; +use arrow_schema::{DataType, Field, Schema, TimeUnit}; + +use crate::spec::TableMetadataRef; +use crate::table::Table; +use crate::Result; + +/// Table metadata scan. +/// +/// Used to inspect a table's history, snapshots, and other metadata as a table. +/// +/// See also <https://iceberg.apache.org/docs/latest/spark-queries/#inspecting-tables>. +#[derive(Debug)] +pub struct MetadataScan { + metadata_ref: TableMetadataRef, +} + +impl MetadataScan { + /// Creates a new metadata scan. + pub fn new(table: &Table) -> Self { + Self { + metadata_ref: table.metadata_ref(), + } + } + + /// Returns the snapshots of the table. + pub fn snapshots(&self) -> Result<RecordBatch> { + SnapshotsTable::scan(self) + } +} + +/// Table metadata scan. +/// +/// Use to inspect a table's history, snapshots, and other metadata as a table. +/// +/// References: +/// - <https://github.com/apache/iceberg/blob/ac865e334e143dfd9e33011d8cf710b46d91f1e5/core/src/main/java/org/apache/iceberg/MetadataTableType.java#L23-L39> +/// - <https://iceberg.apache.org/docs/latest/spark-queries/#querying-with-sql> +/// - <https://py.iceberg.apache.org/api/#inspecting-tables> +pub trait MetadataTable { Review Comment: Previously I thought the schema is always a constant, so I designed the interface so that query engine can get the schema without loading the table from catalog. But it seems not the case. As @rshkv mentioned https://github.com/apache/iceberg-rust/pull/822#discussion_r1898945557 e.g., `readable_metrics` is dynamic https://py.iceberg.apache.org/api/#entries Therefore, what about this alternative design: ```rust // user API table.metadata_scan().snapshots().schema() table.metadata_scan().snapshots().scan() // impl impl MetadataScan { /// Returns the snapshots of the table. pub fn snapshots(&self) -> Result<RecordBatch> { SnapshotsTable{ metadata: self } } } struct SnapshotsTable<'a> { metadata: &'a MetadataScan, } // trait is just to ensure interface, and add doc pub trait MetadataTable { /// Returns the schema of the metadata table. fn schema(&self) -> Schema; /// Scans the metadata table. fn scan(&self) -> Result<RecordBatch>; } ``` -- 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
