Skip to content

Removes an extra line jump in distributed explains #95

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 14, 2025
Merged

Removes an extra line jump in distributed explains #95

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 0 additions & 19 deletions src/physical_optimizer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,6 @@ mod tests {
assert_snapshot!(plan, @r"
┌───── Stage 1 Task: partitions: 0,unassigned]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[MinTemp, MaxTemp, Rainfall, Evaporation, Sunshine, WindGustDir, WindGustSpeed, WindDir9am, WindDir3pm, WindSpeed9am, WindSpeed3pm, Humidity9am, Humidity3pm, Pressure9am, Pressure3pm, Cloud9am, Cloud3pm, Temp9am, Temp3pm, RainToday, RISK_MM, RainTomorrow], file_type=parquet
│
└──────────────────────────────────────────────────
");
}
Expand All @@ -209,18 +208,15 @@ mod tests {
│partitions [out:4 <-- in:4 ] AggregateExec: mode=FinalPartitioned, gby=[RainToday@0 as RainToday], aggr=[count(Int64(1))]
│partitions [out:4 <-- in:4 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:4 ] ArrowFlightReadExec: Stage 2
│
└──────────────────────────────────────────────────
┌───── Stage 2 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:4 ] RepartitionExec: partitioning=Hash([RainToday@0], 4), input_partitions=4
│partitions [out:4 ] ArrowFlightReadExec: Stage 1
│
└──────────────────────────────────────────────────
┌───── Stage 1 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:1 ] RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
│partitions [out:1 <-- in:1 ] AggregateExec: mode=Partial, gby=[RainToday@0 as RainToday], aggr=[count(Int64(1))]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[RainToday], file_type=parquet
│
└──────────────────────────────────────────────────
");
}
Expand All @@ -239,20 +235,17 @@ mod tests {
│partitions [out:4 <-- in:4 ] AggregateExec: mode=FinalPartitioned, gby=[RainToday@0 as RainToday], aggr=[count(Int64(1))]
│partitions [out:4 <-- in:4 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:4 ] ArrowFlightReadExec: Stage 2
│
└──────────────────────────────────────────────────
┌───── Stage 2 Task: partitions: 0,1,unassigned],Task: partitions: 2,3,unassigned]
│partitions [out:4 <-- in:2 ] RepartitionExec: partitioning=Hash([RainToday@0], 4), input_partitions=2
│partitions [out:2 <-- in:4 ] PartitionIsolatorExec [providing upto 2 partitions]
│partitions [out:4 ] ArrowFlightReadExec: Stage 1
│
└──────────────────────────────────────────────────
┌───── Stage 1 Task: partitions: 0,1,unassigned],Task: partitions: 2,3,unassigned]
│partitions [out:4 <-- in:2 ] RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=2
│partitions [out:2 <-- in:1 ] PartitionIsolatorExec [providing upto 2 partitions]
│partitions [out:1 <-- in:1 ] AggregateExec: mode=Partial, gby=[RainToday@0 as RainToday], aggr=[count(Int64(1))]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[RainToday], file_type=parquet
│
└──────────────────────────────────────────────────
");
}
Expand All @@ -267,7 +260,6 @@ mod tests {
│partitions [out:1 <-- in:1 ] HashJoinExec: mode=Partitioned, join_type=Left, on=[(RainToday@1, RainToday@1)], projection=[MinTemp@0, MaxTemp@2]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[MinTemp, RainToday], file_type=parquet
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[MaxTemp, RainToday], file_type=parquet
│
└──────────────────────────────────────────────────
");
}
Expand Down Expand Up @@ -312,35 +304,28 @@ mod tests {
│partitions [out:4 <-- in:4 ] AggregateExec: mode=FinalPartitioned, gby=[RainTomorrow@0 as RainTomorrow], aggr=[avg(weather.MaxTemp)]
│partitions [out:4 <-- in:4 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:4 ] ArrowFlightReadExec: Stage 4
│
└──────────────────────────────────────────────────
┌───── Stage 2 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:4 ] RepartitionExec: partitioning=Hash([RainTomorrow@0], 4), input_partitions=4
│partitions [out:4 <-- in:4 ] AggregateExec: mode=Partial, gby=[RainTomorrow@1 as RainTomorrow], aggr=[avg(weather.MinTemp)]
│partitions [out:4 <-- in:4 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:4 <-- in:4 ] FilterExec: RainToday@1 = yes, projection=[MinTemp@0, RainTomorrow@2]
│partitions [out:4 ] ArrowFlightReadExec: Stage 1
│
└──────────────────────────────────────────────────
┌───── Stage 1 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:1 ] RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[MinTemp, RainToday, RainTomorrow], file_type=parquet, predicate=RainToday@1 = yes, pruning_predicate=RainToday_null_count@2 != row_count@3 AND RainToday_min@0 <= yes AND yes <= RainToday_max@1, required_guarantees=[RainToday in (yes)]
│
│
└──────────────────────────────────────────────────
┌───── Stage 4 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:4 ] RepartitionExec: partitioning=Hash([RainTomorrow@0], 4), input_partitions=4
│partitions [out:4 <-- in:4 ] AggregateExec: mode=Partial, gby=[RainTomorrow@1 as RainTomorrow], aggr=[avg(weather.MaxTemp)]
│partitions [out:4 <-- in:4 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:4 <-- in:4 ] FilterExec: RainToday@1 = no, projection=[MaxTemp@0, RainTomorrow@2]
│partitions [out:4 ] ArrowFlightReadExec: Stage 3
│
└──────────────────────────────────────────────────
┌───── Stage 3 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:1 ] RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[MaxTemp, RainToday, RainTomorrow], file_type=parquet, predicate=RainToday@1 = no, pruning_predicate=RainToday_null_count@2 != row_count@3 AND RainToday_min@0 <= no AND no <= RainToday_max@1, required_guarantees=[RainToday in (no)]
│
│
└──────────────────────────────────────────────────
");
}
Expand All @@ -353,7 +338,6 @@ mod tests {
┌───── Stage 1 Task: partitions: 0,unassigned]
│partitions [out:1 <-- in:1 ] SortExec: expr=[MinTemp@0 DESC], preserve_partitioning=[false]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[MinTemp, MaxTemp, Rainfall, Evaporation, Sunshine, WindGustDir, WindGustSpeed, WindDir9am, WindDir3pm, WindSpeed9am, WindSpeed3pm, Humidity9am, Humidity3pm, Pressure9am, Pressure3pm, Cloud9am, Cloud3pm, Temp9am, Temp3pm, RainToday, RISK_MM, RainTomorrow], file_type=parquet
│
└──────────────────────────────────────────────────
");
}
Expand All @@ -367,18 +351,15 @@ mod tests {
│partitions [out:4 <-- in:4 ] AggregateExec: mode=FinalPartitioned, gby=[RainToday@0 as RainToday, WindGustDir@1 as WindGustDir], aggr=[]
│partitions [out:4 <-- in:4 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:4 ] ArrowFlightReadExec: Stage 2
│
└──────────────────────────────────────────────────
┌───── Stage 2 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:4 ] RepartitionExec: partitioning=Hash([RainToday@0, WindGustDir@1], 4), input_partitions=4
│partitions [out:4 ] ArrowFlightReadExec: Stage 1
│
└──────────────────────────────────────────────────
┌───── Stage 1 Task: partitions: 0..3,unassigned]
│partitions [out:4 <-- in:1 ] RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
│partitions [out:1 <-- in:1 ] AggregateExec: mode=Partial, gby=[RainToday@0 as RainToday, WindGustDir@1 as WindGustDir], aggr=[]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[RainToday, WindGustDir], file_type=parquet
│
└──────────────────────────────────────────────────
");
}
Expand Down
7 changes: 5 additions & 2 deletions src/stage/display.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,8 +48,11 @@ impl DisplayAs for ExecutionStage {
)?;
let plan_str = display_plan_with_partition_in_out(self.plan.as_ref())
.map_err(|_| std::fmt::Error {})?;
let plan_str =
plan_str.replace('\n', &format!("\n{}{}", " ".repeat(self.depth), VERTICAL));
let plan_str = plan_str
.split('\n')
.filter(|v| !v.is_empty())
.collect::<Vec<_>>()
.join(&format!("\n{}{}", " ".repeat(self.depth), VERTICAL));
writeln!(f, "{}{}{}", " ".repeat(self.depth), VERTICAL, plan_str)?;
write!(
f,
Expand Down
2 changes: 2 additions & 0 deletions src/test_utils/plan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,9 @@ use datafusion::common::plan_err;
use datafusion::common::tree_node::{Transformed, TreeNode};
use datafusion::error::DataFusionError;
use datafusion::physical_expr::Partitioning;
use datafusion::physical_optimizer::PhysicalOptimizerRule;
use datafusion::physical_plan::aggregates::{AggregateExec, AggregateMode};
use datafusion::physical_plan::repartition::RepartitionExec;
use datafusion::physical_plan::ExecutionPlan;
use std::sync::Arc;

Expand Down
3 changes: 0 additions & 3 deletions tests/distributed_aggregation.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,19 +53,16 @@ mod tests {
│partitions [out:8 <-- in:8 ] ProjectionExec: expr=[count(Int64(1))@1 as count(*), RainToday@0 as RainToday, count(Int64(1))@1 as count(Int64(1))]
│partitions [out:8 <-- in:8 ] AggregateExec: mode=FinalPartitioned, gby=[RainToday@0 as RainToday], aggr=[count(Int64(1))]
│partitions [out:8 ] ArrowFlightReadExec: Stage 2
│
└──────────────────────────────────────────────────
┌───── Stage 2 Task: partitions: 0..2,unassigned]
│partitions [out:3 <-- in:3 ] CoalesceBatchesExec: target_batch_size=8192
│partitions [out:3 <-- in:3 ] RepartitionExec: partitioning=Hash([RainToday@0], 3), input_partitions=3
│partitions [out:3 <-- in:1 ] RepartitionExec: partitioning=RoundRobinBatch(3), input_partitions=1
│partitions [out:1 <-- in:1 ] AggregateExec: mode=Partial, gby=[RainToday@0 as RainToday], aggr=[count(Int64(1))]
│partitions [out:1 ] ArrowFlightReadExec: Stage 1
│
└──────────────────────────────────────────────────
┌───── Stage 1 Task: partitions: 0,unassigned]
│partitions [out:1 ] DataSourceExec: file_groups={1 group: [[/testdata/weather.parquet]]}, projection=[RainToday], file_type=parquet
│
└──────────────────────────────────────────────────
",
);
Expand Down