From d57026cd969e5b41621d6f4a592bd98b994eb0fd Mon Sep 17 00:00:00 2001
From: ManyTheFish <many@meilisearch.com>
Date: Tue, 25 Jul 2023 15:01:42 +0200
Subject: [PATCH] Support synonyms sinergies

---
 .../tests/settings/tokenizer_customization.rs | 263 ++++++++++++++++++
 milli/src/update/settings.rs                  |  66 ++++-
 2 files changed, 314 insertions(+), 15 deletions(-)

diff --git a/meilisearch/tests/settings/tokenizer_customization.rs b/meilisearch/tests/settings/tokenizer_customization.rs
index 75bea560b..62a1440b2 100644
--- a/meilisearch/tests/settings/tokenizer_customization.rs
+++ b/meilisearch/tests/settings/tokenizer_customization.rs
@@ -194,3 +194,266 @@ async fn set_and_search() {
         })
         .await;
 }
+
+#[actix_rt::test]
+async fn advanced_synergies() {
+    let documents = json!([
+        {
+            "id": 1,
+            "content": "J.R.R. Tolkien",
+        },
+        {
+            "id": 2,
+            "content": "J. R. R. Tolkien",
+        },
+        {
+            "id": 3,
+            "content": "jrr Tolkien",
+        },
+        {
+            "id": 4,
+            "content": "J.K. Rowlings",
+        },
+        {
+            "id": 5,
+            "content": "J. K. Rowlings",
+        },
+        {
+            "id": 6,
+            "content": "jk Rowlings",
+        },
+    ]);
+
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    index.add_documents(documents, None).await;
+    index.wait_task(0).await;
+
+    let (_response, _code) = index
+        .update_settings(json!({
+            "dictionary": ["J.R.R.", "J. R. R.", "J.K.", "J. K."],
+            "synonyms": {
+                "J.R.R.": ["jrr", "J. R. R."],
+                "J. R. R.": ["jrr", "J.R.R."],
+                "jrr": ["J.R.R.", "J. R. R."],
+                "J.K.": ["jk", "J. K."],
+                "J. K.": ["jk", "J.K."],
+                "jk": ["J.K.", "J. K."],
+            }
+        }))
+        .await;
+    index.wait_task(1).await;
+
+    index
+        .search(json!({"q": "J.R.R.", "attributesToHighlight": ["content"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "content": "J.R.R. Tolkien",
+                "_formatted": {
+                  "id": "1",
+                  "content": "<em>J.R.R.</em> Tolkien"
+                }
+              },
+              {
+                "id": 2,
+                "content": "J. R. R. Tolkien",
+                "_formatted": {
+                  "id": "2",
+                  "content": "<em>J. R. R.</em> Tolkien"
+                }
+              },
+              {
+                "id": 3,
+                "content": "jrr Tolkien",
+                "_formatted": {
+                  "id": "3",
+                  "content": "<em>jrr</em> Tolkien"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "jrr", "attributesToHighlight": ["content"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 3,
+                "content": "jrr Tolkien",
+                "_formatted": {
+                  "id": "3",
+                  "content": "<em>jrr</em> Tolkien"
+                }
+              },
+              {
+                "id": 1,
+                "content": "J.R.R. Tolkien",
+                "_formatted": {
+                  "id": "1",
+                  "content": "<em>J.R.R.</em> Tolkien"
+                }
+              },
+              {
+                "id": 2,
+                "content": "J. R. R. Tolkien",
+                "_formatted": {
+                  "id": "2",
+                  "content": "<em>J. R. R.</em> Tolkien"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "J. R. R.", "attributesToHighlight": ["content"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 2,
+                "content": "J. R. R. Tolkien",
+                "_formatted": {
+                  "id": "2",
+                  "content": "<em>J. R. R.</em> Tolkien"
+                }
+              },
+              {
+                "id": 1,
+                "content": "J.R.R. Tolkien",
+                "_formatted": {
+                  "id": "1",
+                  "content": "<em>J.R.R.</em> Tolkien"
+                }
+              },
+              {
+                "id": 3,
+                "content": "jrr Tolkien",
+                "_formatted": {
+                  "id": "3",
+                  "content": "<em>jrr</em> Tolkien"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "jk", "attributesToHighlight": ["content"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 6,
+                "content": "jk Rowlings",
+                "_formatted": {
+                  "id": "6",
+                  "content": "<em>jk</em> Rowlings"
+                }
+              },
+              {
+                "id": 4,
+                "content": "J.K. Rowlings",
+                "_formatted": {
+                  "id": "4",
+                  "content": "<em>J.K.</em> Rowlings"
+                }
+              },
+              {
+                "id": 5,
+                "content": "J. K. Rowlings",
+                "_formatted": {
+                  "id": "5",
+                  "content": "<em>J. K.</em> Rowlings"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "J.K.", "attributesToHighlight": ["content"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 4,
+                "content": "J.K. Rowlings",
+                "_formatted": {
+                  "id": "4",
+                  "content": "<em>J.K.</em> Rowlings"
+                }
+              },
+              {
+                "id": 5,
+                "content": "J. K. Rowlings",
+                "_formatted": {
+                  "id": "5",
+                  "content": "<em>J. K.</em> Rowlings"
+                }
+              },
+              {
+                "id": 6,
+                "content": "jk Rowlings",
+                "_formatted": {
+                  "id": "6",
+                  "content": "<em>jk</em> Rowlings"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "J. K.", "attributesToHighlight": ["content"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 5,
+                "content": "J. K. Rowlings",
+                "_formatted": {
+                  "id": "5",
+                  "content": "<em>J. K.</em> Rowlings"
+                }
+              },
+              {
+                "id": 4,
+                "content": "J.K. Rowlings",
+                "_formatted": {
+                  "id": "4",
+                  "content": "<em>J.K.</em> Rowlings"
+                }
+              },
+              {
+                "id": 6,
+                "content": "jk Rowlings",
+                "_formatted": {
+                  "id": "6",
+                  "content": "<em>jk</em> Rowlings"
+                }
+              },
+              {
+                "id": 2,
+                "content": "J. R. R. Tolkien",
+                "_formatted": {
+                  "id": "2",
+                  "content": "<em>J. R.</em> R. Tolkien"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
diff --git a/milli/src/update/settings.rs b/milli/src/update/settings.rs
index bdae5d7b4..8f5a71f1d 100644
--- a/milli/src/update/settings.rs
+++ b/milli/src/update/settings.rs
@@ -491,57 +491,78 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
     }
 
     fn update_non_separator_tokens(&mut self) -> Result<bool> {
-        match self.non_separator_tokens {
+        let changes = match self.non_separator_tokens {
             Setting::Set(ref non_separator_tokens) => {
                 let current = self.index.non_separator_tokens(self.wtxn)?;
 
                 // Does the new list differ from the previous one?
                 if current.map_or(true, |current| &current != non_separator_tokens) {
                     self.index.put_non_separator_tokens(self.wtxn, non_separator_tokens)?;
-                    Ok(true)
+                    true
                 } else {
-                    Ok(false)
+                    false
                 }
             }
-            Setting::Reset => Ok(self.index.delete_non_separator_tokens(self.wtxn)?),
-            Setting::NotSet => Ok(false),
+            Setting::Reset => self.index.delete_non_separator_tokens(self.wtxn)?,
+            Setting::NotSet => false,
+        };
+
+        // the synonyms must be updated if non separator tokens have been updated.
+        if changes {
+            self.update_synonyms()?;
         }
+
+        Ok(changes)
     }
 
     fn update_separator_tokens(&mut self) -> Result<bool> {
-        match self.separator_tokens {
+        let changes = match self.separator_tokens {
             Setting::Set(ref separator_tokens) => {
                 let current = self.index.separator_tokens(self.wtxn)?;
 
                 // Does the new list differ from the previous one?
                 if current.map_or(true, |current| &current != separator_tokens) {
                     self.index.put_separator_tokens(self.wtxn, separator_tokens)?;
-                    Ok(true)
+                    true
                 } else {
-                    Ok(false)
+                    false
                 }
             }
-            Setting::Reset => Ok(self.index.delete_separator_tokens(self.wtxn)?),
-            Setting::NotSet => Ok(false),
+            Setting::Reset => self.index.delete_separator_tokens(self.wtxn)?,
+            Setting::NotSet => false,
+        };
+
+        // the synonyms must be updated if separator tokens have been updated.
+        if changes {
+            self.update_synonyms()?;
         }
+
+        Ok(changes)
     }
 
     fn update_dictionary(&mut self) -> Result<bool> {
-        match self.dictionary {
+        let changes = match self.dictionary {
             Setting::Set(ref dictionary) => {
                 let current = self.index.dictionary(self.wtxn)?;
 
                 // Does the new list differ from the previous one?
                 if current.map_or(true, |current| &current != dictionary) {
                     self.index.put_dictionary(self.wtxn, dictionary)?;
-                    Ok(true)
+                    true
                 } else {
-                    Ok(false)
+                    false
                 }
             }
-            Setting::Reset => Ok(self.index.delete_dictionary(self.wtxn)?),
-            Setting::NotSet => Ok(false),
+            Setting::Reset => self.index.delete_dictionary(self.wtxn)?,
+            Setting::NotSet => false,
+        };
+
+        // the synonyms must be updated if dictionary has been updated.
+        if changes {
+            self.update_synonyms()?;
         }
+
+        Ok(changes)
     }
 
     fn update_synonyms(&mut self) -> Result<bool> {
@@ -565,6 +586,21 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
                 if let Some(ref stop_words) = stop_words {
                     builder.stop_words(stop_words);
                 }
+
+                let separators = self.index.allowed_separators(self.wtxn)?;
+                let separators: Option<Vec<_>> =
+                    separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
+                if let Some(ref separators) = separators {
+                    builder.separators(separators);
+                }
+
+                let dictionary = self.index.dictionary(self.wtxn)?;
+                let dictionary: Option<Vec<_>> =
+                    dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
+                if let Some(ref dictionary) = dictionary {
+                    builder.words_dict(dictionary);
+                }
+
                 let tokenizer = builder.build();
 
                 let mut new_synonyms = HashMap::new();