From 2d0cf7cbb42442de02022c2a453f3c5ceee52a8e Mon Sep 17 00:00:00 2001
From: TheAMM <the.actual.amm@gmail.com>
Date: Mon, 5 Jun 2017 17:29:00 +0300
Subject: [PATCH] [ES Schema change] Multi-field search display_name to match
 words over ngram limit

This fixes searching for "Machiavellianism", 16 chars ("Machiavellianis", 15 chars, worked previously).
Does not (seem to!) break anything, but requires a re-indexing of ES.
---
 es_mapping.yml | 19 ++++++++++++++++++-
 nyaa/search.py |  2 ++
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/es_mapping.yml b/es_mapping.yml
index 036db5b..4d4e39b 100644
--- a/es_mapping.yml
+++ b/es_mapping.yml
@@ -23,6 +23,17 @@ settings:
           - my_ngram
           - word_delimit
           - trim_zero
+      # For matching full words longer than the ngram limit (15 chars)
+      my_fullword_index_analyzer:
+        type: custom
+        tokenizer: standard
+        char_filter:
+          - my_char_filter
+        filter:
+          - lowercase
+          - word_delimit
+          # These should be enough, as my_index_analyzer will match the rest
+
     filter:
       my_ngram:
         type: edgeNGram
@@ -67,7 +78,13 @@ mappings:
         # the scene convention of stuff in brackets, plus stuff like k-on
         type: text
         analyzer: my_index_analyzer
-        fielddata: true
+        fielddata: true # Is this required?
+        fields:
+          # Multi-field for full-word matching (when going over ngram limits)
+          # Note: will have to be queried for, not automatic
+          fullword:
+            type: text
+            analyzer: my_fullword_index_analyzer
       created_time:
         type: date
         # Only in the ES index for generating magnet links
diff --git a/nyaa/search.py b/nyaa/search.py
index 83b9ebd..2614e24 100644
--- a/nyaa/search.py
+++ b/nyaa/search.py
@@ -109,6 +109,8 @@ def search_elastic(term='', user=None, sort='id', order='desc',
     # Apply search term
     if term:
         s = s.query('simple_query_string',
+                    # Query both fields, latter for words with >15 chars
+                    fields=['display_name', 'display_name.fullword'],
                     analyzer='my_search_analyzer',
                     default_operator="AND",
                     query=term)