xudong963 commented on code in PR #15503: URL: https://github.com/apache/datafusion/pull/15503#discussion_r2031021249
########## datafusion/physical-plan/src/statistics.rs: ########## @@ -0,0 +1,151 @@ +// 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. + +//! Defines the cross join plan for loading the left side of the cross join +//! and producing batches in parallel for the right partitions + +use datafusion_common::stats::Precision; +use datafusion_common::{ColumnStatistics, ScalarValue, Statistics}; +use std::mem; + +/// Generic function to compute statistics across multiple items that have statistics +pub fn compute_summary_statistics<T, I>( + items: I, + column_count: usize, + stats_extractor: impl Fn(&T) -> Option<&Statistics>, +) -> Statistics +where + I: IntoIterator<Item = T>, +{ + let mut col_stats_set = vec![ColumnStatistics::default(); column_count]; + let mut num_rows = Precision::<usize>::Absent; + let mut total_byte_size = Precision::<usize>::Absent; + + for (idx, item) in items.into_iter().enumerate() { + if let Some(item_stats) = stats_extractor(&item) { + if idx == 0 { + // First item, set values directly + num_rows = item_stats.num_rows; + total_byte_size = item_stats.total_byte_size; + for (index, column_stats) in + item_stats.column_statistics.iter().enumerate() + { + col_stats_set[index].null_count = column_stats.null_count; + col_stats_set[index].max_value = column_stats.max_value.clone(); + col_stats_set[index].min_value = column_stats.min_value.clone(); + col_stats_set[index].sum_value = column_stats.sum_value.clone(); + } + continue; + } + + // Accumulate statistics for subsequent items + num_rows = add_row_stats(item_stats.num_rows, num_rows); + total_byte_size = add_row_stats(item_stats.total_byte_size, total_byte_size); + + for (item_col_stats, col_stats) in item_stats + .column_statistics + .iter() + .zip(col_stats_set.iter_mut()) + { + col_stats.null_count = + add_row_stats(item_col_stats.null_count, col_stats.null_count); + set_max_if_greater(&item_col_stats.max_value, &mut col_stats.max_value); + set_min_if_lesser(&item_col_stats.min_value, &mut col_stats.min_value); + col_stats.sum_value = item_col_stats.sum_value.add(&col_stats.sum_value); + } + } + } + + Statistics { + num_rows, + total_byte_size, + column_statistics: col_stats_set, + } +} + +/// If the given value is numerically greater than the original maximum value, Review Comment: Recorded an issue: https://github.com/apache/datafusion/issues/15615 -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
