Rare terms aggregation false **positive** fix

docs/changelog/126884.yaml

@@ -0,0 +1,5 @@
+pr: 126884
+summary: Rare terms aggregation false **positive** fix
+area: Aggregations
+type: bug
+issues: []

server/src/main/java/org/elasticsearch/common/util/SetBackedScalingCuckooFilter.java

@@ -341,7 +341,7 @@ public void merge(SetBackedScalingCuckooFilter other) {
  } else if (isSetMode == false && other.isSetMode) {
  // Rather than converting the other to a cuckoo first, we can just
  // replay the values directly into our filter.
- other.hashes.forEach(this::add);
+ other.hashes.forEach(this::addHash);
  } else {
  // Both are in cuckoo mode, merge raw fingerprints
 

server/src/test/java/org/elasticsearch/common/util/SetBackedScalingCuckooFilterTests.java

@@ -132,6 +132,34 @@ public void testConvertTwice() {
  );
  }
 
+ public void testMergeBigSmall() {
+ int threshold = 1000;
+
+ // Setup the first filter
+ SetBackedScalingCuckooFilter filter = new SetBackedScalingCuckooFilter(threshold, Randomness.get(), 0.01);
+ int counter = 0;
+ Set<Long> values = new HashSet<>();
+ while (counter < threshold + 1) {
+ long value = randomLong();
+ filter.add(value);
+ boolean newValue = values.add(value);
+ if (newValue) {
+ counter += 1;
+ }
+ }
+
+ SetBackedScalingCuckooFilter filter2 = new SetBackedScalingCuckooFilter(threshold, Randomness.get(), 0.01);
+ long value = randomLong();
+ while (filter.mightContain(value)) {
+ value = randomLong();
+ }
+
+ filter2.add(value);
+
+ filter.merge(filter2);
+ assertTrue(filter.mightContain(value));
+ }
+
  public void testMergeSmall() {
  int threshold = 1000;