liurenjie1024 commented on code in PR #880: URL: https://github.com/apache/iceberg-rust/pull/880#discussion_r1908168716
########## crates/integrations/datafusion/src/statistics.rs: ########## @@ -0,0 +1,112 @@ +// 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::collections::HashMap; + +use datafusion::common::stats::Precision; +use datafusion::common::{ColumnStatistics, Statistics}; +use iceberg::spec::ManifestStatus; +use iceberg::table::Table; +use iceberg::Result; + +use crate::physical_plan::expr_to_predicate::datum_to_scalar_value; + +// Compute DataFusion table statistics for a given table/snapshot +pub async fn compute_statistics(table: &Table, snapshot_id: Option<i64>) -> Result<Statistics> { + let file_io = table.file_io(); + let metadata = table.metadata(); + let snapshot = table.snapshot(snapshot_id)?; + + let mut num_rows = 0; + let mut lower_bounds = HashMap::new(); + let mut upper_bounds = HashMap::new(); + let mut null_counts = HashMap::new(); + + let manifest_list = snapshot.load_manifest_list(file_io, metadata).await?; + + // For each existing/added manifest in the snapshot aggregate the row count, as well as null + // count and min/max values. + for manifest_file in manifest_list.entries() { + let manifest = manifest_file.load_manifest(file_io).await?; Review Comment: > I assume that data files with associated row-level deletes don't get lower-upper bounds updated during commit time. Sorry, I don't get why it's not updated. If a row level deletion deletes a row with least values, should this be updated? For point 1, I agree that adding an option would be useful to enable it or not. For point 2, there are many problems, not only about deletions. For example, for vary length columns, the stored value maybe truncated, then it's not appropricate to use them to calculate upper/lower bounds. Also deletion not only change lower/upper bounds, but also row count, nvd, etc. -- 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
