Add unit tests for terms aggregation objects. (#23149)

Relates #22278

4 files changed, 281 insertions, 0 deletions

diff --git a/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/DoubleTermsTests.java b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/DoubleTermsTests.java
new file mode 100644
index 0000000000..757d5647a1
--- /dev/null
+++ b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/DoubleTermsTests.java
@@ -0,0 +1,66 @@
+/*
+ * Licensed to Elasticsearch under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.elasticsearch.search.aggregations.bucket.terms;
+
+import org.elasticsearch.common.io.stream.Writeable.Reader;
+import org.elasticsearch.search.DocValueFormat;
+import org.elasticsearch.search.aggregations.InternalAggregations;
+import org.elasticsearch.search.aggregations.pipeline.PipelineAggregator;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+public class DoubleTermsTests extends InternalTermsTestCase {
+
+    @Override
+    protected InternalTerms<?, ?> createTestInstance(
+            String name,
+            List<PipelineAggregator> pipelineAggregators,
+            Map<String, Object> metaData) {
+        Terms.Order order = Terms.Order.count(false);
+        long minDocCount = 1;
+        int requiredSize = 3;
+        int shardSize = requiredSize + 2;
+        DocValueFormat format = DocValueFormat.RAW;
+        boolean showTermDocCountError = false;
+        long docCountError = -1;
+        long otherDocCount = 0;
+        List<DoubleTerms.Bucket> buckets = new ArrayList<>();
+        final int numBuckets = randomInt(shardSize);
+        Set<Double> terms = new HashSet<>();
+        for (int i = 0; i < numBuckets; ++i) {
+            double term = randomValueOtherThanMany(d -> terms.add(d) == false, random()::nextDouble);
+            int docCount = randomIntBetween(1, 100);
+            buckets.add(new DoubleTerms.Bucket(term, docCount, InternalAggregations.EMPTY,
+                    showTermDocCountError, docCountError, format));
+        }
+        return new DoubleTerms(name, order, requiredSize, minDocCount, pipelineAggregators,
+                metaData, format, shardSize, showTermDocCountError, otherDocCount, buckets, docCountError);
+    }
+
+    @Override
+    protected Reader<InternalTerms<?, ?>> instanceReader() {
+        return DoubleTerms::new;
+    }
+
+}
diff --git a/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/InternalTermsTestCase.java b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/InternalTermsTestCase.java
new file mode 100644
index 0000000000..03031633f7
--- /dev/null
+++ b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/InternalTermsTestCase.java
@@ -0,0 +1,82 @@
+/*
+ * Licensed to Elasticsearch under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.elasticsearch.search.aggregations.bucket.terms;
+
+import org.elasticsearch.search.aggregations.InternalAggregationTestCase;
+import org.elasticsearch.search.aggregations.pipeline.PipelineAggregator;
+
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Optional;
+import java.util.Map.Entry;
+import java.util.stream.Collectors;
+import java.util.stream.Stream;
+
+public abstract class InternalTermsTestCase extends InternalAggregationTestCase<InternalTerms<?,?>> {
+
+    @Override
+    protected InternalTerms<?, ?> createUnmappedInstance(
+            String name,
+            List<PipelineAggregator> pipelineAggregators,
+            Map<String, Object> metaData) {
+        InternalTerms<?, ?> testInstance = createTestInstance(name, pipelineAggregators, metaData);
+        return new UnmappedTerms(name, testInstance.order, testInstance.requiredSize, testInstance.minDocCount,
+                pipelineAggregators, metaData);
+    }
+
+    @Override
+    protected void assertReduced(InternalTerms<?, ?> reduced, List<InternalTerms<?, ?>> inputs) {
+        final int requiredSize = inputs.get(0).requiredSize;
+        Map<Object, Long> reducedCounts = toCounts(reduced.getBuckets().stream());
+        Map<Object, Long> totalCounts = toCounts(inputs.stream().map(Terms::getBuckets).flatMap(List::stream));
+
+        assertEquals(reducedCounts.size() == requiredSize,
+                totalCounts.size() >= requiredSize);
+
+        Map<Object, Long> expectedReducedCounts = new HashMap<>(totalCounts);
+        expectedReducedCounts.keySet().retainAll(reducedCounts.keySet());
+        assertEquals(expectedReducedCounts, reducedCounts);
+
+        final long minFinalcount = reduced.getBuckets().isEmpty()
+                ? -1
+                : reduced.getBuckets().get(reduced.getBuckets().size() - 1).getDocCount();
+        Map<Object, Long> evictedTerms = new HashMap<>(totalCounts);
+        evictedTerms.keySet().removeAll(reducedCounts.keySet());
+        Optional<Entry<Object, Long>> missingTerm = evictedTerms.entrySet().stream()
+                .filter(e -> e.getValue() > minFinalcount).findAny();
+        if (missingTerm.isPresent()) {
+            fail("Missed term: " + missingTerm + " from " + reducedCounts);
+        }
+
+        final long reducedTotalDocCount = reduced.getSumOfOtherDocCounts()
+                + reduced.getBuckets().stream().mapToLong(Terms.Bucket::getDocCount).sum();
+        final long expectedTotalDocCount = inputs.stream().map(Terms::getBuckets)
+                .flatMap(List::stream).mapToLong(Terms.Bucket::getDocCount).sum();
+        assertEquals(expectedTotalDocCount, reducedTotalDocCount);
+    }
+
+    private static Map<Object, Long> toCounts(Stream<? extends Terms.Bucket> buckets) {
+        return buckets.collect(Collectors.toMap(
+                Terms.Bucket::getKey,
+                Terms.Bucket::getDocCount,
+                Long::sum));
+    }
+}
diff --git a/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/LongTermsTests.java b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/LongTermsTests.java
new file mode 100644
index 0000000000..ff95984bc3
--- /dev/null
+++ b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/LongTermsTests.java
@@ -0,0 +1,66 @@
+/*
+ * Licensed to Elasticsearch under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.elasticsearch.search.aggregations.bucket.terms;
+
+import org.elasticsearch.common.io.stream.Writeable.Reader;
+import org.elasticsearch.search.DocValueFormat;
+import org.elasticsearch.search.aggregations.InternalAggregations;
+import org.elasticsearch.search.aggregations.pipeline.PipelineAggregator;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+public class LongTermsTests extends InternalTermsTestCase {
+
+    @Override
+    protected InternalTerms<?, ?> createTestInstance(
+            String name,
+            List<PipelineAggregator> pipelineAggregators,
+            Map<String, Object> metaData) {
+        Terms.Order order = Terms.Order.count(false);
+        long minDocCount = 1;
+        int requiredSize = 3;
+        int shardSize = requiredSize + 2;
+        DocValueFormat format = DocValueFormat.RAW;
+        boolean showTermDocCountError = false;
+        long docCountError = -1;
+        long otherDocCount = 0;
+        List<LongTerms.Bucket> buckets = new ArrayList<>();
+        final int numBuckets = randomInt(shardSize);
+        Set<Long> terms = new HashSet<>();
+        for (int i = 0; i < numBuckets; ++i) {
+            long term = randomValueOtherThanMany(l -> terms.add(l) == false, random()::nextLong);
+            int docCount = randomIntBetween(1, 100);
+            buckets.add(new LongTerms.Bucket(term, docCount, InternalAggregations.EMPTY,
+                    showTermDocCountError, docCountError, format));
+        }
+        return new LongTerms(name, order, requiredSize, minDocCount, pipelineAggregators,
+                metaData, format, shardSize, showTermDocCountError, otherDocCount, buckets, docCountError);
+    }
+
+    @Override
+    protected Reader<InternalTerms<?, ?>> instanceReader() {
+        return LongTerms::new;
+    }
+
+}
diff --git a/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/StringTermsTests.java b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/StringTermsTests.java
new file mode 100644
index 0000000000..d20f546a54
--- /dev/null
+++ b/core/src/test/java/org/elasticsearch/search/aggregations/bucket/terms/StringTermsTests.java
@@ -0,0 +1,67 @@
+/*
+ * Licensed to Elasticsearch under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.elasticsearch.search.aggregations.bucket.terms;
+
+import org.apache.lucene.util.BytesRef;
+import org.elasticsearch.common.io.stream.Writeable.Reader;
+import org.elasticsearch.search.DocValueFormat;
+import org.elasticsearch.search.aggregations.InternalAggregations;
+import org.elasticsearch.search.aggregations.pipeline.PipelineAggregator;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+public class StringTermsTests extends InternalTermsTestCase {
+
+    @Override
+    protected InternalTerms<?, ?> createTestInstance(
+            String name,
+            List<PipelineAggregator> pipelineAggregators,
+            Map<String, Object> metaData) {
+        Terms.Order order = Terms.Order.count(false);
+        long minDocCount = 1;
+        int requiredSize = 3;
+        int shardSize = requiredSize + 2;
+        DocValueFormat format = DocValueFormat.RAW;
+        boolean showTermDocCountError = false;
+        long docCountError = -1;
+        long otherDocCount = 0;
+        List<StringTerms.Bucket> buckets = new ArrayList<>();
+        final int numBuckets = randomInt(shardSize);
+        Set<BytesRef> terms = new HashSet<>();
+        for (int i = 0; i < numBuckets; ++i) {
+            BytesRef term = randomValueOtherThanMany(b -> terms.add(b) == false, () -> new BytesRef(randomAsciiOfLength(10)));
+            int docCount = randomIntBetween(1, 100);
+            buckets.add(new StringTerms.Bucket(term, docCount, InternalAggregations.EMPTY,
+                    showTermDocCountError, docCountError, format));
+        }
+        return new StringTerms(name, order, requiredSize, minDocCount, pipelineAggregators,
+                metaData, format, shardSize, showTermDocCountError, otherDocCount, buckets, docCountError);
+    }
+
+    @Override
+    protected Reader<InternalTerms<?, ?>> instanceReader() {
+        return StringTerms::new;
+    }
+
+}