From 06b2a587affa0ff4c06a4aff81724f96c8b1e719 Mon Sep 17 00:00:00 2001
From: many <maxime@meilisearch.com>
Date: Tue, 12 Jan 2021 13:53:32 +0100
Subject: [PATCH] normalize synonyms during indexation

---
 .../src/update/settings_update.rs             | 19 ++++-
 meilisearch-http/tests/search_settings.rs     | 83 +++++++++++++++++++
 2 files changed, 100 insertions(+), 2 deletions(-)

diff --git a/meilisearch-core/src/update/settings_update.rs b/meilisearch-core/src/update/settings_update.rs
index 7b82c1c6e..205ef216a 100644
--- a/meilisearch-core/src/update/settings_update.rs
+++ b/meilisearch-core/src/update/settings_update.rs
@@ -1,9 +1,10 @@
-use std::collections::{BTreeMap, BTreeSet};
+use std::{borrow::Cow, collections::{BTreeMap, BTreeSet}};
 
 use heed::Result as ZResult;
 use fst::{set::OpBuilder, SetBuilder};
 use sdset::SetBuf;
 use meilisearch_schema::Schema;
+use meilisearch_tokenizer::analyzer::{Analyzer, AnalyzerConfig};
 
 use crate::database::{MainT, UpdateT};
 use crate::settings::{UpdateState, SettingsUpdate, RankingRule};
@@ -289,13 +290,27 @@ pub fn apply_synonyms_update(
 
     let main_store = index.main;
     let synonyms_store = index.synonyms;
+    let stop_words = index.main.stop_words_fst(writer)?.map_data(Cow::into_owned)?;
+    let analyzer = Analyzer::new(AnalyzerConfig::default_with_stopwords(&stop_words));
+
+    fn normalize<T: AsRef<[u8]>>(analyzer: &Analyzer<T>, text: &str) -> String {
+        analyzer.analyze(&text)
+            .tokens()
+            .fold(String::new(), |mut s, t| {
+                s.push_str(&t.word);
+                s
+            })
+    }
 
     let mut synonyms_builder = SetBuilder::memory();
     synonyms_store.clear(writer)?;
-    for (word, alternatives) in synonyms.clone() {
+    for (word, alternatives) in synonyms {
+        let word = normalize(&analyzer, &word);
+
         synonyms_builder.insert(&word)?;
 
         let alternatives = {
+            let alternatives = alternatives.iter().map(|text| normalize(&analyzer, &text)).collect();
             let alternatives = SetBuf::from_dirty(alternatives);
             let mut alternatives_builder = SetBuilder::memory();
             alternatives_builder.extend_iter(alternatives)?;
diff --git a/meilisearch-http/tests/search_settings.rs b/meilisearch-http/tests/search_settings.rs
index 46417498d..97d27023a 100644
--- a/meilisearch-http/tests/search_settings.rs
+++ b/meilisearch-http/tests/search_settings.rs
@@ -167,6 +167,89 @@ async fn search_with_settings_stop_words() {
 async fn search_with_settings_synonyms() {
     let mut server = common::Server::test_server().await;
 
+    let config = json!({
+      "rankingRules": [
+        "typo",
+        "words",
+        "proximity",
+        "attribute",
+        "wordsPosition",
+        "desc(age)",
+        "exactness",
+        "desc(balance)"
+      ],
+      "distinctAttribute": null,
+      "searchableAttributes": [
+        "name",
+        "age",
+        "color",
+        "gender",
+        "email",
+        "address",
+        "about"
+      ],
+      "displayedAttributes": [
+        "name",
+        "age",
+        "gender",
+        "color",
+        "email",
+        "phone",
+        "address",
+        "balance"
+      ],
+      "stopWords": null,
+      "synonyms": {
+          "Application": [
+              "Exercitation"
+          ]
+      },
+    });
+
+    server.update_all_settings(config).await;
+
+    let query = "q=application&limit=3";
+    let expect = json!([
+      {
+        "balance": "$1,921.58",
+        "age": 31,
+        "color": "Green",
+        "name": "Harper Carson",
+        "gender": "male",
+        "email": "harpercarson@chorizon.com",
+        "phone": "+1 (912) 430-3243",
+        "address": "883 Dennett Place, Knowlton, New Mexico, 9219"
+      },
+      {
+        "balance": "$1,706.13",
+        "age": 27,
+        "color": "Green",
+        "name": "Cherry Orr",
+        "gender": "female",
+        "email": "cherryorr@chorizon.com",
+        "phone": "+1 (995) 479-3174",
+        "address": "442 Beverly Road, Ventress, New Mexico, 3361"
+      },
+      {
+        "balance": "$1,476.39",
+        "age": 28,
+        "color": "brown",
+        "name": "Maureen Dale",
+        "gender": "female",
+        "email": "maureendale@chorizon.com",
+        "phone": "+1 (984) 538-3684",
+        "address": "817 Newton Street, Bannock, Wyoming, 1468"
+      }
+    ]);
+
+    let (response, _status_code) = server.search_get(query).await;
+    assert_json_eq!(expect, response["hits"].clone(), ordered: false);
+}
+
+#[actix_rt::test]
+async fn search_with_settings_normalized_synonyms() {
+    let mut server = common::Server::test_server().await;
+
     let config = json!({
       "rankingRules": [
         "typo",