From f31af836d990d08645ab48d462ad502a9f821750 Mon Sep 17 00:00:00 2001
From: TheAMM <the.actual.amm@gmail.com>
Date: Fri, 13 Apr 2018 14:37:01 +0300
Subject: [PATCH] Optimize Elasticsearch fullword field

Since the main display_name field ngrams words up to 15 characters,
anything to and under that will already be indexed - the fullword field
(which we have for words longer than 15 characters) needs to index only
words longer than that.
---
 es_mapping.yml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/es_mapping.yml b/es_mapping.yml
index 4d4e39b..6001305 100644
--- a/es_mapping.yml
+++ b/es_mapping.yml
@@ -32,13 +32,19 @@ settings:
         filter:
           - lowercase
           - word_delimit
-          # These should be enough, as my_index_analyzer will match the rest
+          # Skip tokens shorter than N characters,
+          # since they're already indexed in the main field
+          - fullword_min
 
     filter:
       my_ngram:
         type: edgeNGram
         min_gram: 1
         max_gram: 15
+      fullword_min:
+        type: length
+        # Remember to change this if you change the max_gram below!
+        min: 16
       resolution:
         type: pattern_capture
         patterns: ["(\\d+)[xX](\\d+)"]