Merge remaining sig_terms into terms (#57397) (#57687)

Merges the remaining implementation of `significant_terms` into `terms`
so that we can more easilly make them work properly without
`asMultiBucketAggregator` which *should* save memory and speed them up.

Relates #56487

Author: nik9000

rest-api-spec/src/main/resources/rest-api-spec/test/search.aggregation/20_terms.yml

@@ -779,7 +779,7 @@ setup:
         body: { "size" : 0, "aggs" : { "no_field_terms" : { "terms" : { "size": 1 } } } }
 
 ---
-"global ords profiler":
+"string profiler":
   - skip:
       version: " - 7.8.99"
       reason: debug information added in 7.9.0
@@ -831,6 +831,36 @@ setup:
   - match: { profile.shards.0.aggregations.0.children.0.type: MaxAggregator }
   - match: { profile.shards.0.aggregations.0.children.0.description: max_number }
 
+  - do:
+      search:
+        index: test_1
+        body:
+          profile: true
+          size: 0
+          aggs:
+            str_terms:
+              terms:
+                field: str
+                collect_mode: breadth_first
+                execution_hint: map
+              aggs:
+                max_number:
+                  max:
+                    field: number
+  - match: { aggregations.str_terms.buckets.0.key: sheep }
+  - match: { aggregations.str_terms.buckets.0.max_number.value: 3 }
+  - match: { aggregations.str_terms.buckets.1.key: cow }
+  - match: { aggregations.str_terms.buckets.1.max_number.value: 1 }
+  - match: { aggregations.str_terms.buckets.2.key: pig }
+  - match: { aggregations.str_terms.buckets.2.max_number.value: 1 }
+  - match: { profile.shards.0.aggregations.0.type: MapStringTermsAggregator }
+  - match: { profile.shards.0.aggregations.0.description: str_terms }
+  - match: { profile.shards.0.aggregations.0.breakdown.collect_count: 4 }
+  - match: { profile.shards.0.aggregations.0.debug.deferred_aggregators: [ max_number ] }
+  - match: { profile.shards.0.aggregations.0.debug.result_strategy: terms }
+  - match: { profile.shards.0.aggregations.0.children.0.type: MaxAggregator }
+  - match: { profile.shards.0.aggregations.0.children.0.description: max_number }
+
   - do:
       indices.create:
           index: test_3

server/src/main/java/org/elasticsearch/search/aggregations/bucket/terms/GlobalOrdinalsStringTermsAggregator.java

@@ -551,11 +551,12 @@ public void accept(long globalOrd, long bucketOrd, long docCount) throws IOExcep
             B[] topBuckets = buildBuckets(ordered.size());
             for (int i = ordered.size() - 1; i >= 0; --i) {
                 topBuckets[i] = convertTempBucketToRealBucket(ordered.pop());
+                otherDocCount[0] -= topBuckets[i].getDocCount();
             }
             buildSubAggs(topBuckets);
 
             return new InternalAggregation[] {
-                buildResult(topBuckets)
+                buildResult(topBuckets, otherDocCount[0])
             };
         }
 
@@ -608,7 +609,7 @@ public void accept(long globalOrd, long bucketOrd, long docCount) throws IOExcep
         /**
          * Turn the buckets into an aggregation result.
          */
-        abstract R buildResult(B[] topBuckets);
+        abstract R buildResult(B[] topBuckets, long otherDocCount);
 
         /**
          * Build an "empty" result. Only called if there isn't any data on this
@@ -621,8 +622,6 @@ public void accept(long globalOrd, long bucketOrd, long docCount) throws IOExcep
      * Builds results for the standard {@code terms} aggregation.
      */
     class StandardTermsResults extends ResultStrategy<StringTerms, StringTerms.Bucket, OrdBucket> {
-        private long otherDocCount;
-
         @Override
         String describe() {
             return "terms";
@@ -648,7 +647,6 @@ void updateBucket(OrdBucket spare, long globalOrd, long bucketOrd, long docCount
             spare.globalOrd = globalOrd;
             spare.bucketOrd = bucketOrd;
             spare.docCount = docCount;
-            otherDocCount += docCount;
         }
 
         @Override
@@ -660,7 +658,6 @@ StringTerms.Bucket convertTempBucketToRealBucket(OrdBucket temp) throws IOExcept
             BytesRef term = BytesRef.deepCopyOf(lookupGlobalOrd.apply(temp.globalOrd));
             StringTerms.Bucket result = new StringTerms.Bucket(term, temp.docCount, null, showTermDocCountError, 0, format);
             result.bucketOrd = temp.bucketOrd;
-            otherDocCount -= temp.docCount;
             result.docCountError = 0;
             return result;
         }
@@ -671,7 +668,7 @@ void buildSubAggs(StringTerms.Bucket[] topBuckets) throws IOException {
         }
 
         @Override
-        StringTerms buildResult(StringTerms.Bucket[] topBuckets) {
+        StringTerms buildResult(StringTerms.Bucket[] topBuckets, long otherDocCount) {
             return new StringTerms(name, order, bucketCountThresholds.getRequiredSize(), bucketCountThresholds.getMinDocCount(),
                 metadata(), format, bucketCountThresholds.getShardSize(), showTermDocCountError,
                 otherDocCount, Arrays.asList(topBuckets), 0);
@@ -707,7 +704,7 @@ class SignificantTermsResults extends ResultStrategy<
 
         @Override
         String describe() {
-            return "terms";
+            return "significant_terms";
         }
 
         @Override
@@ -763,7 +760,7 @@ void buildSubAggs(SignificantStringTerms.Bucket[] topBuckets) throws IOException
         }
 
         @Override
-        SignificantStringTerms buildResult(SignificantStringTerms.Bucket[] topBuckets) {
+        SignificantStringTerms buildResult(SignificantStringTerms.Bucket[] topBuckets, long otherDocCount) {
             return new SignificantStringTerms(name, bucketCountThresholds.getRequiredSize(), bucketCountThresholds.getMinDocCount(),
                 metadata(), format, subsetSize, termsAggFactory.getSupersetNumDocs(), significanceHeuristic, Arrays.asList(topBuckets));
         }