Merge #2408

2408: Upgrade milli v0.28 r=ManyTheFish a=ManyTheFish

- Add smart crop
- Add test on _matches_infos
- Fix some test

Co-authored-by: ManyTheFish <many@meilisearch.com>

Cargo.lock

@@ -1092,8 +1092,8 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "0.26.4"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.26.5#1f6dc31e2f8ee02cdda255a856d15f253daf17ec"
+version = "0.28.0"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.28.0#19dac01c5ca81543b751f66ad51fcff61608d969"
 dependencies = [
  "nom",
  "nom_locate",
@@ -1119,8 +1119,8 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "0.26.4"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.26.5#1f6dc31e2f8ee02cdda255a856d15f253daf17ec"
+version = "0.28.0"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.28.0#19dac01c5ca81543b751f66ad51fcff61608d969"
 dependencies = [
  "serde_json",
 ]
@@ -1622,8 +1622,8 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "0.26.4"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.26.5#1f6dc31e2f8ee02cdda255a856d15f253daf17ec"
+version = "0.28.0"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.28.0#19dac01c5ca81543b751f66ad51fcff61608d969"
 dependencies = [
  "serde_json",
 ]
@@ -2151,8 +2151,8 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "0.26.4"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.26.5#1f6dc31e2f8ee02cdda255a856d15f253daf17ec"
+version = "0.28.0"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.28.0#19dac01c5ca81543b751f66ad51fcff61608d969"
 dependencies = [
  "bimap",
  "bincode",
@@ -2189,6 +2189,7 @@ dependencies = [
  "smallvec",
  "smartstring",
  "tempfile",
+ "thiserror",
  "time 0.3.9",
  "uuid",
 ]
@@ -3360,18 +3361,18 @@ checksum = "b1141d4d61095b28419e22cb0bbf02755f5e54e0526f97f1e3d1d160e60885fb"
 
 [[package]]
 name = "thiserror"
-version = "1.0.30"
+version = "1.0.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "854babe52e4df1653706b98fcfc05843010039b406875930a70e4d9644e5c417"
+checksum = "bd829fe32373d27f76265620b5309d0340cb8550f523c1dda251d6298069069a"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.30"
+version = "1.0.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa32fd3f627f367fe16f893e2597ae3c05020f8bba2666a4e6ea73d377e5714b"
+checksum = "0396bc89e626244658bef819e22d0cc459e795a5ebe878e6ec336d1674a8d79a"
 dependencies = [
  "proc-macro2 1.0.37",
  "quote 1.0.17",

meilisearch-auth/Cargo.toml

@@ -6,7 +6,7 @@ edition = "2021"
 [dependencies]
 enum-iterator = "0.7.0"
 meilisearch-error = { path = "../meilisearch-error" }
-milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.26.5" }
+milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.28.0" }
 rand = "0.8.4"
 serde = { version = "1.0.136", features = ["derive"] }
 serde_json = { version = "1.0.79", features = ["preserve_order"] }

meilisearch-http/tests/documents/add_documents.rs

@@ -868,7 +868,12 @@ async fn error_add_documents_bad_document_id() {
     let (response, code) = index.get_task(1).await;
     assert_eq!(code, 200);
     assert_eq!(response["status"], json!("failed"));
-    assert_eq!(response["error"]["message"], json!("Document identifier `foo & bar` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."));
+    assert_eq!(
+        response["error"]["message"],
+        json!(
+            r#"Document identifier `"foo & bar"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."#
+        )
+    );
     assert_eq!(response["error"]["code"], json!("invalid_document_id"));
     assert_eq!(response["error"]["type"], json!("invalid_request"));
     assert_eq!(
@@ -891,7 +896,12 @@ async fn error_update_documents_bad_document_id() {
     index.update_documents(documents, None).await;
     let response = index.wait_task(1).await;
     assert_eq!(response["status"], json!("failed"));
-    assert_eq!(response["error"]["message"], json!("Document identifier `foo & bar` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."));
+    assert_eq!(
+        response["error"]["message"],
+        json!(
+            r#"Document identifier `"foo & bar"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."#
+        )
+    );
     assert_eq!(response["error"]["code"], json!("invalid_document_id"));
     assert_eq!(response["error"]["type"], json!("invalid_request"));
     assert_eq!(

meilisearch-http/tests/search/formatted.rs

@@ -16,7 +16,7 @@ async fn formatted_contain_wildcard() {
     index.wait_task(1).await;
 
     let (response, code) = index
-        .search_post(json!({ "q": "pesti", "attributesToRetrieve": ["father", "mother"], "attributesToHighlight": ["father", "mother", "*"], "attributesToCrop": ["doggos"] }))
+        .search_post(json!({ "q": "pesti", "attributesToRetrieve": ["father", "mother"], "attributesToHighlight": ["father", "mother", "*"], "attributesToCrop": ["doggos"], "matches": true }))
         .await;
     assert_eq!(code, 200, "{}", response);
     assert_eq!(
@@ -25,7 +25,8 @@ async fn formatted_contain_wildcard() {
             "_formatted": {
                 "id": "852",
                 "cattos": "<em>pesti</em>",
-            }
+            },
+            "_matchesInfo": {"cattos": [{"start": 0, "length": 5}]},
         })
     );
 
@@ -43,7 +44,7 @@ async fn formatted_contain_wildcard() {
 
     let (response, code) = index
         .search_post(
-            json!({ "q": "pesti", "attributesToRetrieve": ["*"], "attributesToHighlight": ["id"] }),
+            json!({ "q": "pesti", "attributesToRetrieve": ["*"], "attributesToHighlight": ["id"], "matches": true }),
         )
         .await;
     assert_eq!(code, 200, "{}", response);
@@ -55,7 +56,8 @@ async fn formatted_contain_wildcard() {
             "_formatted": {
                 "id": "852",
                 "cattos": "pesti",
-            }
+            },
+            "_matchesInfo": {"cattos": [{"start": 0, "length": 5}]},
         })
     );
 
@@ -141,6 +143,27 @@ async fn format_nested() {
         })
     );
 
+    let (response, code) = index
+        .search_post(
+            json!({ "q": "bobby", "attributesToRetrieve": ["doggos.name"], "matches": true }),
+        )
+        .await;
+    assert_eq!(code, 200, "{}", response);
+    assert_eq!(
+        response["hits"][0],
+        json!({
+            "doggos": [
+                {
+                    "name": "bobby",
+                },
+                {
+                    "name": "buddy",
+                },
+            ],
+            "_matchesInfo": {"doggos.name": [{"start": 0, "length": 5}]},
+        })
+    );
+
     let (response, code) = index
         .search_post(json!({ "q": "pesti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.name"] }))
         .await;

meilisearch-lib/Cargo.toml

@@ -30,7 +30,7 @@ lazy_static = "1.4.0"
 log = "0.4.14"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-error = { path = "../meilisearch-error" }
-milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.26.5" }
+milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.28.0" }
 mime = "0.3.16"
 num_cpus = "1.13.1"
 obkv = "0.2.0"