This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new de6d5119d0 Minor: Rewrite LogicalPlan::max_rows for Join and Union,
made it easier to understand (#14012)
de6d5119d0 is described below
commit de6d5119d0de2a5ca10f71a18ed85d723abdc78d
Author: Eugene Marushchenko <[email protected]>
AuthorDate: Mon Jan 6 21:09:15 2025 +1000
Minor: Rewrite LogicalPlan::max_rows for Join and Union, made it easier to
understand (#14012)
* Refactor max_rows for join plan, made it easier to understand
* Simplified max_rows for Union
---
datafusion/expr/src/logical_plan/plan.rs | 54 +++++++++++++-------------------
1 file changed, 22 insertions(+), 32 deletions(-)
diff --git a/datafusion/expr/src/logical_plan/plan.rs
b/datafusion/expr/src/logical_plan/plan.rs
index cc922709c8..005bf4b984 100644
--- a/datafusion/expr/src/logical_plan/plan.rs
+++ b/datafusion/expr/src/logical_plan/plan.rs
@@ -1317,18 +1317,13 @@ impl LogicalPlan {
join_type,
..
}) => match join_type {
- JoinType::Inner | JoinType::Left | JoinType::Right |
JoinType::Full => {
- match (left.max_rows(), right.max_rows()) {
- (Some(left_max), Some(right_max)) => {
- let min_rows = match join_type {
- JoinType::Left => left_max,
- JoinType::Right => right_max,
- JoinType::Full => left_max + right_max,
- _ => 0,
- };
- Some((left_max * right_max).max(min_rows))
- }
- _ => None,
+ JoinType::Inner => Some(left.max_rows()? * right.max_rows()?),
+ JoinType::Left | JoinType::Right | JoinType::Full => {
+ match (left.max_rows()?, right.max_rows()?, join_type) {
+ (0, 0, _) => Some(0),
+ (max_rows, 0, JoinType::Left | JoinType::Full) =>
Some(max_rows),
+ (0, max_rows, JoinType::Right | JoinType::Full) =>
Some(max_rows),
+ (left_max, right_max, _) => Some(left_max * right_max),
}
}
JoinType::LeftSemi | JoinType::LeftAnti | JoinType::LeftMark
=> {
@@ -1337,17 +1332,12 @@ impl LogicalPlan {
JoinType::RightSemi | JoinType::RightAnti => right.max_rows(),
},
LogicalPlan::Repartition(Repartition { input, .. }) =>
input.max_rows(),
- LogicalPlan::Union(Union { inputs, .. }) => inputs
- .iter()
- .map(|plan| plan.max_rows())
- .try_fold(0usize, |mut acc, input_max| {
- if let Some(i_max) = input_max {
- acc += i_max;
- Some(acc)
- } else {
- None
- }
- }),
+ LogicalPlan::Union(Union { inputs, .. }) => {
+ inputs.iter().try_fold(0usize, |mut acc, plan| {
+ acc += plan.max_rows()?;
+ Some(acc)
+ })
+ }
LogicalPlan::TableScan(TableScan { fetch, .. }) => *fetch,
LogicalPlan::EmptyRelation(_) => Some(0),
LogicalPlan::RecursiveQuery(_) => None,
@@ -3433,15 +3423,15 @@ pub enum Partitioning {
/// input output_name
/// ┌─────────┐ ┌─────────┐
/// │{{1,2}} │ │ 1 │
-/// ├─────────┼─────►├─────────┤
-/// │{{3}} │ │ 2 │
-/// ├─────────┤ ├─────────┤
-/// │{{4},{5}}│ │ 3 │
-/// └─────────┘ ├─────────┤
-/// │ 4 │
-/// ├─────────┤
-/// │ 5 │
-/// └─────────┘
+/// ├─────────┼─────►├─────────┤
+/// │{{3}} │ │ 2 │
+/// ├─────────┤ ├─────────┤
+/// │{{4},{5}}│ │ 3 │
+/// └─────────┘ ├─────────┤
+/// │ 4 │
+/// ├─────────┤
+/// │ 5 │
+/// └─────────┘
/// ```
#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd)]
pub struct ColumnUnnestList {
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
