Revert "Revert "Merge remote-tracking branch 'origin/main' into release-v1.7.1""

meilisearch/Cargo.toml

@@ -14,18 +14,18 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.7.0"
-actix-http = { version = "3.5.1", default-features = false, features = [
+actix-http = { version = "3.6.0", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
-    "rustls",
+    "rustls-0_21",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.4.1", default-features = false, features = [
+actix-web = { version = "4.5.1", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
     "cookies",
-    "rustls",
+    "rustls-0_21",
 ] }
 actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
 anyhow = { version = "1.0.79", features = ["backtrace"] }
@@ -52,7 +52,7 @@ index-scheduler = { path = "../index-scheduler" }
 indexmap = { version = "2.1.0", features = ["serde"] }
 is-terminal = "0.4.10"
 itertools = "0.11.0"
-jsonwebtoken = "8.3.0"
+jsonwebtoken = "9.2.0"
 lazy_static = "1.4.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
@@ -75,7 +75,7 @@ reqwest = { version = "0.11.23", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
-rustls = "0.20.8"
+rustls = "0.21.6"
 rustls-pemfile = "1.0.2"
 segment = { version = "0.2.3", optional = true }
 serde = { version = "1.0.195", features = ["derive"] }

meilisearch/src/main.rs

@@ -151,7 +151,7 @@ async fn run_http(
     .keep_alive(KeepAlive::Os);
 
     if let Some(config) = opt_clone.get_ssl_config()? {
-        http_server.bind_rustls(opt_clone.http_addr, config)?.run().await?;
+        http_server.bind_rustls_021(opt_clone.http_addr, config)?.run().await?;
     } else {
         http_server.bind(&opt_clone.http_addr)?.run().await?;
     }

meilisearch/src/option.rs

@@ -564,11 +564,11 @@ impl Opt {
                     }
                     if self.ssl_require_auth {
                         let verifier = AllowAnyAuthenticatedClient::new(client_auth_roots);
-                        config.with_client_cert_verifier(verifier)
+                        config.with_client_cert_verifier(Arc::from(verifier))
                     } else {
                         let verifier =
                             AllowAnyAnonymousOrAuthenticatedClient::new(client_auth_roots);
-                        config.with_client_cert_verifier(verifier)
+                        config.with_client_cert_verifier(Arc::from(verifier))
                     }
                 }
                 None => config.with_no_client_auth(),

meilisearch/src/routes/indexes/settings.rs

@@ -604,6 +604,7 @@ fn embedder_analytics(
                 EmbedderSource::OpenAi => sources.insert("openAi"),
                 EmbedderSource::HuggingFace => sources.insert("huggingFace"),
                 EmbedderSource::UserProvided => sources.insert("userProvided"),
+                EmbedderSource::Ollama => sources.insert("ollama"),
             };
         }
     };

meilisearch/src/search.rs

@@ -530,7 +530,7 @@ pub fn perform_search(
     // The attributes to retrieve are the ones explicitly marked as to retrieve (all by default),
     // but these attributes must be also be present
     // - in the fields_ids_map
-    // - in the the displayed attributes
+    // - in the displayed attributes
     let to_retrieve_ids: BTreeSet<_> = query
         .attributes_to_retrieve
         .as_ref()
@@ -671,27 +671,16 @@ pub fn perform_search(
 
             let sort_facet_values_by =
                 index.sort_facet_values_by(&rtxn).map_err(milli::Error::from)?;
-            let default_sort_facet_values_by =
-                sort_facet_values_by.get("*").copied().unwrap_or_default();
 
             if fields.iter().all(|f| f != "*") {
-                let fields: Vec<_> = fields
-                    .iter()
-                    .map(|n| {
-                        (
-                            n,
-                            sort_facet_values_by
-                                .get(n)
-                                .copied()
-                                .unwrap_or(default_sort_facet_values_by),
-                        )
-                    })
-                    .collect();
+                let fields: Vec<_> =
+                    fields.iter().map(|n| (n, sort_facet_values_by.get(n))).collect();
                 facet_distribution.facets(fields);
             }
+
             let distribution = facet_distribution
                 .candidates(candidates)
-                .default_order_by(default_sort_facet_values_by)
+                .default_order_by(sort_facet_values_by.get("*"))
                 .execute()?;
             let stats = facet_distribution.compute_stats()?;
             (Some(distribution), Some(stats))

meilisearch/tests/documents/add_documents.rs

@@ -1237,8 +1237,8 @@ async fn error_add_documents_missing_document_id() {
 }
 
 #[actix_rt::test]
-#[ignore] // // TODO: Fix in an other PR: this does not provoke any error.
-async fn error_document_field_limit_reached() {
+#[should_panic]
+async fn error_document_field_limit_reached_in_one_document() {
     let server = Server::new().await;
     let index = server.index("test");
 
@@ -1246,22 +1246,241 @@ async fn error_document_field_limit_reached() {
 
     let mut big_object = std::collections::HashMap::new();
     big_object.insert("id".to_owned(), "wow");
-    for i in 0..65535 {
+    for i in 0..(u16::MAX as usize + 1) {
         let key = i.to_string();
         big_object.insert(key, "I am a text!");
     }
 
     let documents = json!([big_object]);
 
-    let (_response, code) = index.update_documents(documents, Some("id")).await;
-    snapshot!(code, @"202");
+    let (response, code) = index.update_documents(documents, Some("id")).await;
+    snapshot!(code, @"500 Internal Server Error");
 
-    index.wait_task(0).await;
-    let (response, code) = index.get_task(0).await;
-    snapshot!(code, @"200");
+    let response = index.wait_task(response.uid()).await;
+    snapshot!(code, @"202 Accepted");
     // Documents without a primary key are not accepted.
-    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
-        @"");
+    snapshot!(response,
+        @r###"
+    {
+      "uid": 1,
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn error_document_field_limit_reached_over_multiple_documents() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    index.create(Some("id")).await;
+
+    let mut big_object = std::collections::HashMap::new();
+    big_object.insert("id".to_owned(), "wow");
+    for i in 0..(u16::MAX / 2) {
+        let key = i.to_string();
+        big_object.insert(key, "I am a text!");
+    }
+
+    let documents = json!([big_object]);
+
+    let (response, code) = index.update_documents(documents, Some("id")).await;
+    snapshot!(code, @"202 Accepted");
+
+    let response = index.wait_task(response.uid()).await;
+    snapshot!(code, @"202 Accepted");
+    snapshot!(response,
+        @r###"
+    {
+      "uid": 1,
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    let mut big_object = std::collections::HashMap::new();
+    big_object.insert("id".to_owned(), "waw");
+    for i in (u16::MAX as usize / 2)..(u16::MAX as usize + 1) {
+        let key = i.to_string();
+        big_object.insert(key, "I am a text!");
+    }
+
+    let documents = json!([big_object]);
+
+    let (response, code) = index.update_documents(documents, Some("id")).await;
+    snapshot!(code, @"202 Accepted");
+
+    let response = index.wait_task(response.uid()).await;
+    snapshot!(code, @"202 Accepted");
+    snapshot!(response,
+        @r###"
+    {
+      "uid": 2,
+      "indexUid": "test",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "A document cannot contain more than 65,535 fields.",
+        "code": "max_fields_limit_exceeded",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#max_fields_limit_exceeded"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn error_document_field_limit_reached_in_one_nested_document() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    index.create(Some("id")).await;
+
+    let mut nested = std::collections::HashMap::new();
+    for i in 0..(u16::MAX as usize + 1) {
+        let key = i.to_string();
+        nested.insert(key, "I am a text!");
+    }
+    let mut big_object = std::collections::HashMap::new();
+    big_object.insert("id".to_owned(), "wow");
+
+    let documents = json!([big_object]);
+
+    let (response, code) = index.update_documents(documents, Some("id")).await;
+    snapshot!(code, @"202 Accepted");
+
+    let response = index.wait_task(response.uid()).await;
+    snapshot!(code, @"202 Accepted");
+    // Documents without a primary key are not accepted.
+    snapshot!(response,
+        @r###"
+    {
+      "uid": 1,
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn error_document_field_limit_reached_over_multiple_documents_with_nested_fields() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    index.create(Some("id")).await;
+
+    let mut nested = std::collections::HashMap::new();
+    for i in 0..(u16::MAX / 2) {
+        let key = i.to_string();
+        nested.insert(key, "I am a text!");
+    }
+    let mut big_object = std::collections::HashMap::new();
+    big_object.insert("id".to_owned(), "wow");
+
+    let documents = json!([big_object]);
+
+    let (response, code) = index.update_documents(documents, Some("id")).await;
+    snapshot!(code, @"202 Accepted");
+
+    let response = index.wait_task(response.uid()).await;
+    snapshot!(code, @"202 Accepted");
+    snapshot!(response,
+        @r###"
+    {
+      "uid": 1,
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    let mut nested = std::collections::HashMap::new();
+    for i in 0..(u16::MAX / 2) {
+        let key = i.to_string();
+        nested.insert(key, "I am a text!");
+    }
+    let mut big_object = std::collections::HashMap::new();
+    big_object.insert("id".to_owned(), "wow");
+
+    let documents = json!([big_object]);
+
+    let (response, code) = index.update_documents(documents, Some("id")).await;
+    snapshot!(code, @"202 Accepted");
+
+    let response = index.wait_task(response.uid()).await;
+    snapshot!(code, @"202 Accepted");
+    snapshot!(response,
+        @r###"
+    {
+      "uid": 2,
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
 }
 
 #[actix_rt::test]

meilisearch/tests/search/facet_search.rs

@@ -123,6 +123,28 @@ async fn simple_facet_search_with_max_values() {
     assert_eq!(dbg!(response)["facetHits"].as_array().unwrap().len(), 1);
 }
 
+#[actix_rt::test]
+async fn simple_facet_search_by_count_with_max_values() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = DOCUMENTS.clone();
+    index
+        .update_settings_faceting(
+            json!({ "maxValuesPerFacet": 1, "sortFacetValuesBy": { "*": "count" } }),
+        )
+        .await;
+    index.update_settings_filterable_attributes(json!(["genres"])).await;
+    index.add_documents(documents, None).await;
+    index.wait_task(2).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
+
+    assert_eq!(code, 200, "{}", response);
+    assert_eq!(dbg!(response)["facetHits"].as_array().unwrap().len(), 1);
+}
+
 #[actix_rt::test]
 async fn non_filterable_facet_search_error() {
     let server = Server::new().await;
@@ -157,3 +179,24 @@ async fn facet_search_dont_support_words() {
     assert_eq!(code, 200, "{}", response);
     assert_eq!(response["facetHits"].as_array().unwrap().len(), 0);
 }
+
+#[actix_rt::test]
+async fn simple_facet_search_with_sort_by_count() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = DOCUMENTS.clone();
+    index.update_settings_faceting(json!({ "sortFacetValuesBy": { "*": "count" } })).await;
+    index.update_settings_filterable_attributes(json!(["genres"])).await;
+    index.add_documents(documents, None).await;
+    index.wait_task(2).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
+
+    assert_eq!(code, 200, "{}", response);
+    let hits = response["facetHits"].as_array().unwrap();
+    assert_eq!(hits.len(), 2);
+    assert_eq!(hits[0], json!({ "value": "Action", "count": 3 }));
+    assert_eq!(hits[1], json!({ "value": "Adventure", "count": 2 }));
+}