Skip to content

Fix bug in CombineApproxPercentileFunctions with duplicate aggregation expressions #18889

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
rschlussel merged 1 commit into from
Jan 3, 2023
Merged

Fix bug in CombineApproxPercentileFunctions with duplicate aggregation expressions #18889

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
8 changes: 7 additions & 1 deletion ...java/com/facebook/presto/sql/planner/iterative/rule/CombineApproxPercentileFunctions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,9 @@
import static com.facebook.presto.sql.relational.Expressions.call;
import static com.facebook.presto.sql.relational.Expressions.constant;
import static com.google.common.base.Preconditions.checkState;
import static com.google.common.collect.ImmutableList.toImmutableList;
import static java.util.Objects.requireNonNull;
import static java.util.function.Function.identity;

/**
* For multiple approx_percentile() function calls on the same column with different percentile arguments, combine them to one call on an array of percentile arguments.
Expand Down Expand Up @@ -224,9 +226,13 @@ public Result apply(AggregationNode aggregationNode, Captures captures, Context
x -> x.getCall().getDisplayName().equals(APPROX_PERCENTILE) && !(x.getCall().getType() instanceof ArrayType)
).collect(Collectors.toList());

// Remove aggregations which occurs more than once, as we assumes that there are no duplicates in later stage
Map<AggregationNode.Aggregation, Long> aggregationOccurrences = approxPercentile.stream().collect(Collectors.groupingBy(identity(), Collectors.counting()));
ImmutableList<AggregationNode.Aggregation> candidateApproxPercentile = approxPercentile.stream().filter(x -> aggregationOccurrences.get(x) == 1).collect(toImmutableList());

// Group the aggregations on the same column and have the same function handle
Map<RowExpression, Map<FunctionHandle, List<AggregationNode.Aggregation>>> sameColumnHandle =
approxPercentile.stream().collect(Collectors.groupingBy(x -> x.getCall().getArguments().get(0), LinkedHashMap::new,
candidateApproxPercentile.stream().collect(Collectors.groupingBy(x -> x.getCall().getArguments().get(0), LinkedHashMap::new,
Collectors.groupingBy(x -> x.getFunctionHandle(), LinkedHashMap::new, Collectors.toList())));

// Each list contains the aggregations which can be combined
Expand Down
15 changes: 15 additions & 0 deletions .../com/facebook/presto/sql/planner/iterative/rule/TestCombineApproxPercentileFunctions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -232,4 +232,19 @@ public void testArrayLimit()
}
})).doesNotFire();
}

@Test
public void testWithDuplicate()
{
tester().assertThat(new CombineApproxPercentileFunctions(getMetadata().getFunctionAndTypeManager()))
.on(p -> p.aggregation(af -> {
p.variable("col", BIGINT);
af.globalGrouping()
.addAggregation(p.variable("approx_percentile_1"), p.rowExpression("approx_percentile(col, 0.1)", ParsingOptions.DecimalLiteralTreatment.AS_DOUBLE))
.addAggregation(p.variable("approx_percentile_2"), p.rowExpression("approx_percentile(col, 0.1)", ParsingOptions.DecimalLiteralTreatment.AS_DOUBLE))
.addAggregation(p.variable("approx_percentile_3"), p.rowExpression("approx_percentile(col, 0.2)", ParsingOptions.DecimalLiteralTreatment.AS_DOUBLE))
.addAggregation(p.variable("approx_percentile_4"), p.rowExpression("approx_percentile(col, 0.2)", ParsingOptions.DecimalLiteralTreatment.AS_DOUBLE))
.source(p.values(p.variable("col")));
})).doesNotFire();
}
}
12 changes: 11 additions & 1 deletion presto-tests/src/main/java/com/facebook/presto/tests/AbstractTestQueries.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6156,7 +6156,9 @@ public void testApproxPercentileMerged()
" approx_percentile(totalprice, 2, 0.5)," +
" approx_percentile(totalprice, 2, 0.8)," +
" approx_percentile(totalprice, 2, 0.4, 0.001)," +
" approx_percentile(totalprice, 2, 0.7, 0.001)\n" +
" approx_percentile(totalprice, 2, 0.7, 0.001)," +
" approx_percentile(orderkey, 0.9)," +
" approx_percentile(orderkey, 0.8+0.1)\n" +
"FROM orders\n" +
"GROUP BY orderstatus");

Expand All @@ -6172,6 +6174,8 @@ public void testApproxPercentileMerged()
Double totalPrice08Weighted = (Double) row.getField(8);
Double totalPrice04WeightedAccuracy = (Double) row.getField(9);
Double totalPrice07WeightedAccuracy = (Double) row.getField(10);
Long orderKey09v1 = ((Number) row.getField(11)).longValue();
Long orderKey09v2 = ((Number) row.getField(12)).longValue();

List<Long> orderKeys = Ordering.natural().sortedCopy(orderKeyByStatus.get(status));
List<Double> totalPrices = Ordering.natural().sortedCopy(totalPriceByStatus.get(status));
Expand Down Expand Up @@ -6206,6 +6210,12 @@ public void testApproxPercentileMerged()

assertTrue(totalPrice07WeightedAccuracy >= totalPrices.get((int) (0.69 * totalPrices.size())));
assertTrue(totalPrice07WeightedAccuracy <= totalPrices.get((int) (0.71 * totalPrices.size())));

assertTrue(orderKey09v1 >= orderKeys.get((int) (0.89 * orderKeys.size())));
assertTrue(orderKey09v1 <= orderKeys.get((int) (0.91 * orderKeys.size())));

assertTrue(orderKey09v2 >= orderKeys.get((int) (0.89 * orderKeys.size())));
assertTrue(orderKey09v2 <= orderKeys.get((int) (0.91 * orderKeys.size())));
}
}

Expand Down