From 57d4839af6a2e218b3ddb7e4d5f7c4c537866745 Mon Sep 17 00:00:00 2001
From: Patrick Leary <patrick.r.leary@gmail.com>
Date: Thu, 7 Jul 2022 12:27:19 -0400
Subject: [PATCH] attempt to fix observer species count accuracy for small
 sizes #335

---
 lib/controllers/v1/observations_controller.js | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/lib/controllers/v1/observations_controller.js b/lib/controllers/v1/observations_controller.js
index c8b4c2e1..fad98c92 100644
--- a/lib/controllers/v1/observations_controller.js
+++ b/lib/controllers/v1/observations_controller.js
@@ -1219,6 +1219,11 @@ ObservationsController.observationsSpeciesObserverCounts = async req => {
         }
       }
     };
+    // attempting to account for inaccurate counts for queries with a small size
+    // see https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-terms-aggregation.html#search-aggregations-bucket-terms-aggregation-shard-size
+    if ( ( ( aggSize * 1.5 ) + 10 ) < 50 ) {
+      countQuery.aggs.user_taxa.terms.shard_size = 50;
+    }
   }
   countQuery.per_page = 0;
   countQuery.skip_total_hits = true;