Function compute_all_files_statistics

datafusion/datasource/src/statistics.rs:509–542

(
    file_groups: Vec<FileGroup>,
    table_schema: SchemaRef,
    collect_stats: bool,
    inexact_stats: bool,
)

/// * The summary statistics across all file groups, aka all files summary statistics
#[expect(clippy::needless_pass_by_value)]
pub fn compute_all_files_statistics(
    file_groups: Vec<FileGroup>,
    table_schema: SchemaRef,
    collect_stats: bool,
    inexact_stats: bool,
) -> Result<(Vec<FileGroup>, Statistics)> {
    let file_groups_with_stats = file_groups
        .into_iter()
        .map(|file_group| {
            compute_file_group_statistics(
                file_group,
                Arc::clone(&table_schema),
                collect_stats,
            )
        })
        .collect::<Result<Vec<_>>>()?;

    // Then summary statistics across all file groups
    let file_groups_statistics = file_groups_with_stats
        .iter()
        .filter_map(|file_group| file_group.file_statistics(None));

    let mut statistics = Statistics::try_merge_iter_with_ndv_fallback(
        file_groups_statistics,
        &table_schema,
        NdvFallback::Max,
    )?;

    if inexact_stats {
        statistics = statistics.to_inexact()
    }

    Ok((file_groups_with_stats, statistics))
}

#[deprecated(since = "47.0.0", note = "Use Statistics::add")]
pub fn add_row_stats(