Skip to content

[common] Handle empty null counts in statistics filtering #10852

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

Open
yuzelin wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[common] Handle empty null counts in statistics filtering #10852

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
6 changes: 5 additions & 1 deletion paimon-common/src/main/java/org/apache/paimon/predicate/LeafPredicate.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,8 +157,12 @@ public boolean test(

Object min = get(minValues, index, type);
Object max = get(maxValues, index, type);
Long nullCount = nullCounts.isNullAt(index) ? null : nullCounts.getLong(index);
Long nullCount =
nullCounts.size() == 0 || nullCounts.isNullAt(index)
? null
: nullCounts.getLong(index);
if (nullCount == null || rowCount != nullCount) {
// missing null counts
// not all null
// min or max is null
// unknown stats
Expand Down
28 changes: 28 additions & 0 deletions paimon-common/src/test/java/org/apache/paimon/predicate/LeafPredicateTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,12 @@

package org.apache.paimon.predicate;

import org.apache.paimon.data.BinaryArray;
import org.apache.paimon.data.BinaryRow;
import org.apache.paimon.data.BinaryString;
import org.apache.paimon.data.GenericArray;
import org.apache.paimon.data.GenericRow;
import org.apache.paimon.data.serializer.InternalRowSerializer;
import org.apache.paimon.types.DataTypes;
import org.apache.paimon.types.RowType;
import org.apache.paimon.utils.InstantiationUtil;
Expand Down Expand Up @@ -123,6 +126,31 @@ public void testArraySetPredicateSerializationUsesElementSerializer()
assertThat(InstantiationUtil.clone(containsAll).test(row)).isTrue();
}

@Test
public void testEmptyNullCountsWithCompleteBounds() {
RowType type = RowType.of(DataTypes.STRING(), DataTypes.STRING());
PredicateBuilder builder = new PredicateBuilder(type);
InternalRowSerializer serializer = new InternalRowSerializer(type);
BinaryRow bounds =
serializer
.toBinaryRow(
GenericRow.of(
BinaryString.fromString("sample"),
BinaryString.fromString("1")))
.copy();
BinaryArray nullCounts = BinaryArray.fromLongArray(new Long[0]);
Predicate first = builder.equal(0, BinaryString.fromString("other"));
Predicate second = builder.equal(1, BinaryString.fromString("1"));

assertThat(first.test(1, bounds, bounds, nullCounts)).isFalse();
assertThat(second.test(1, bounds, bounds, nullCounts)).isTrue();
assertThat(builder.isNull(0).test(1, bounds, bounds, nullCounts)).isTrue();
assertThat(builder.isNotNull(1).test(1, bounds, bounds, nullCounts)).isTrue();
assertThat(PredicateBuilder.and(first, second).test(1, bounds, bounds, nullCounts))
.isFalse();
assertThat(PredicateBuilder.or(first, second).test(1, bounds, bounds, nullCounts)).isTrue();
}

private LeafPredicate create() {
List<Object> inputs = new ArrayList<>();
inputs.add(new FieldRef(0, "f0", DataTypes.STRING()));
Expand Down
Loading