Function build_is_null_column_expr

datafusion/pruning/src/pruning_predicate.rs:1316–1360

Given an expression reference to `expr`, if `expr` is a column expression, returns a pruning expression in terms of IsNull that will evaluate to true if the column may contain null, and false if definitely does not contain null. If `with_not` is true, build a pruning expression for `col IS NOT NULL`: `col_count != col_null_count` The pruning expression evaluates to true ONLY if the column definite

(
    expr: &Arc<dyn PhysicalExpr>,
    schema: &Schema,
    required_columns: &mut RequiredColumns,
    with_not: bool,
)

/// at least one NULL value.  In this case we can know that `IS NOT NULL` can not be true and
/// thus can prune the row group / value
fn build_is_null_column_expr(
    expr: &Arc<dyn PhysicalExpr>,
    schema: &Schema,
    required_columns: &mut RequiredColumns,
    with_not: bool,
) -> Option<Arc<dyn PhysicalExpr>> {
    if let Some(col) = expr.downcast_ref::<phys_expr::Column>() {
        let field = schema.field_with_name(col.name()).ok()?;

        let null_count_field = &Field::new(field.name(), DataType::UInt64, true);
        if with_not {
            if let Ok(row_count_expr) =
                required_columns.row_count_column_expr(col, expr, null_count_field)
            {
                required_columns
                    .null_count_column_expr(col, expr, null_count_field)
                    .map(|null_count_column_expr| {
                        // IsNotNull(column) => null_count != row_count
                        Arc::new(phys_expr::BinaryExpr::new(
                            null_count_column_expr,
                            Operator::NotEq,
                            row_count_expr,
                        )) as _
                    })
                    .ok()
            } else {
                None
            }
        } else {
            required_columns
                .null_count_column_expr(col, expr, null_count_field)
                .map(|null_count_column_expr| {
                    // IsNull(column) => null_count > 0
                    Arc::new(phys_expr::BinaryExpr::new(
                        null_count_column_expr,
                        Operator::Gt,
                        Arc::new(phys_expr::Literal::new(ScalarValue::UInt64(Some(0)))),
                    )) as _
                })
                .ok()
        }
    } else {
        None
    }
}

/// The maximum number of entries in an `InList` that might be rewritten into
/// an OR chain