Merge #1910

1910: After v0.24.0: import `stable` in `main` r=MarinPostma a=curquiza



Co-authored-by: Tamo <tamo@meilisearch.com>
Co-authored-by: many <maxime@meilisearch.com>
Co-authored-by: bors[bot] <26634292+bors[bot]@users.noreply.github.com>
Co-authored-by: Guillaume Mourier <guillaume@meilisearch.com>
Co-authored-by: Irevoire <tamo@meilisearch.com>
Co-authored-by: Clémentine Urquizar <clementine@meilisearch.com>

Cargo.lock

@@ -1804,8 +1804,8 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "0.20.0"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.20.0#5a6d22d4ec51dda0aba94b314e1b5a38af9400a2"
+version = "0.20.2"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.20.2#a2fc74f010116874c9be01d98a798d30ed718435"
 dependencies = [
  "bimap",
  "bincode",

meilisearch-error/src/lib.rs

@@ -53,7 +53,6 @@ pub enum Code {
     IndexAlreadyExists,
     IndexNotFound,
     InvalidIndexUid,
-    OpenIndex,
 
     // invalid state error
     InvalidState,
@@ -64,19 +63,21 @@ pub enum Code {
     MissingDocumentId,
     InvalidDocumentId,
 
-    Facet,
     Filter,
     Sort,
 
     BadParameter,
     BadRequest,
+    DatabaseSizeLimitReached,
     DocumentNotFound,
     Internal,
     InvalidGeoField,
     InvalidRankingRule,
+    InvalidStore,
     InvalidToken,
     MissingAuthorizationHeader,
-    NotFound,
+    NoSpaceLeftOnDevice,
+    DumpNotFound,
     TaskNotFound,
     PayloadTooLarge,
     RetrieveDocument,
@@ -100,25 +101,31 @@ impl Code {
         match self {
             // index related errors
             // create index is thrown on internal error while creating an index.
-            CreateIndex => ErrCode::internal("index_creation_failed", StatusCode::BAD_REQUEST),
+            CreateIndex => {
+                ErrCode::internal("index_creation_failed", StatusCode::INTERNAL_SERVER_ERROR)
+            }
             IndexAlreadyExists => ErrCode::invalid("index_already_exists", StatusCode::CONFLICT),
             // thrown when requesting an unexisting index
             IndexNotFound => ErrCode::invalid("index_not_found", StatusCode::NOT_FOUND),
             InvalidIndexUid => ErrCode::invalid("invalid_index_uid", StatusCode::BAD_REQUEST),
-            OpenIndex => {
-                ErrCode::internal("index_not_accessible", StatusCode::INTERNAL_SERVER_ERROR)
-            }
 
             // invalid state error
             InvalidState => ErrCode::internal("invalid_state", StatusCode::INTERNAL_SERVER_ERROR),
             // thrown when no primary key has been set
-            MissingPrimaryKey => ErrCode::invalid("missing_primary_key", StatusCode::BAD_REQUEST),
+            MissingPrimaryKey => {
+                ErrCode::invalid("primary_key_inference_failed", StatusCode::BAD_REQUEST)
+            }
             // error thrown when trying to set an already existing primary key
             PrimaryKeyAlreadyPresent => {
                 ErrCode::invalid("index_primary_key_already_exists", StatusCode::BAD_REQUEST)
             }
             // invalid ranking rule
-            InvalidRankingRule => ErrCode::invalid("invalid_request", StatusCode::BAD_REQUEST),
+            InvalidRankingRule => ErrCode::invalid("invalid_ranking_rule", StatusCode::BAD_REQUEST),
+
+            // invalid database
+            InvalidStore => {
+                ErrCode::internal("invalid_store_file", StatusCode::INTERNAL_SERVER_ERROR)
+            }
 
             // invalid document
             MaxFieldsLimitExceeded => {
@@ -127,8 +134,6 @@ impl Code {
             MissingDocumentId => ErrCode::invalid("missing_document_id", StatusCode::BAD_REQUEST),
             InvalidDocumentId => ErrCode::invalid("invalid_document_id", StatusCode::BAD_REQUEST),
 
-            // error related to facets
-            Facet => ErrCode::invalid("invalid_facet", StatusCode::BAD_REQUEST),
             // error related to filters
             Filter => ErrCode::invalid("invalid_filter", StatusCode::BAD_REQUEST),
             // error related to sorts
@@ -136,17 +141,22 @@ impl Code {
 
             BadParameter => ErrCode::invalid("bad_parameter", StatusCode::BAD_REQUEST),
             BadRequest => ErrCode::invalid("bad_request", StatusCode::BAD_REQUEST),
+            DatabaseSizeLimitReached => ErrCode::internal(
+                "database_size_limit_reached",
+                StatusCode::INTERNAL_SERVER_ERROR,
+            ),
             DocumentNotFound => ErrCode::invalid("document_not_found", StatusCode::NOT_FOUND),
             Internal => ErrCode::internal("internal", StatusCode::INTERNAL_SERVER_ERROR),
-            InvalidGeoField => {
-                ErrCode::authentication("invalid_geo_field", StatusCode::BAD_REQUEST)
-            }
+            InvalidGeoField => ErrCode::invalid("invalid_geo_field", StatusCode::BAD_REQUEST),
             InvalidToken => ErrCode::authentication("invalid_api_key", StatusCode::FORBIDDEN),
             MissingAuthorizationHeader => {
                 ErrCode::authentication("missing_authorization_header", StatusCode::UNAUTHORIZED)
             }
             TaskNotFound => ErrCode::invalid("task_not_found", StatusCode::NOT_FOUND),
-            NotFound => ErrCode::invalid("not_found", StatusCode::NOT_FOUND),
+            DumpNotFound => ErrCode::invalid("dump_not_found", StatusCode::NOT_FOUND),
+            NoSpaceLeftOnDevice => {
+                ErrCode::internal("no_space_left_on_device", StatusCode::INTERNAL_SERVER_ERROR)
+            }
             PayloadTooLarge => ErrCode::invalid("payload_too_large", StatusCode::PAYLOAD_TOO_LARGE),
             RetrieveDocument => {
                 ErrCode::internal("unretrievable_document", StatusCode::BAD_REQUEST)
@@ -158,7 +168,7 @@ impl Code {
 
             // error related to dump
             DumpAlreadyInProgress => {
-                ErrCode::invalid("dump_already_in_progress", StatusCode::CONFLICT)
+                ErrCode::invalid("dump_already_processing", StatusCode::CONFLICT)
             }
             DumpProcessFailed => {
                 ErrCode::internal("dump_process_failed", StatusCode::INTERNAL_SERVER_ERROR)

meilisearch-http/Cargo.toml

@@ -98,5 +98,5 @@ default = ["analytics", "mini-dashboard"]
 tikv-jemallocator = "0.4.1"
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.1.4/build.zip"
-sha1 = "750e8a8e56cfa61fbf9ead14b08a5f17ad3f3d37"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.1.5/build.zip"
+sha1 = "1d955ea91b7691bd6fc207cb39866b82210783f0"

meilisearch-http/src/analytics/mock_analytics.rs

@@ -18,7 +18,7 @@ impl SearchAggregator {
         Self::default()
     }
 
-    pub fn finish(&mut self, _: &dyn Any) {}
+    pub fn succeed(&mut self, _: &dyn Any) {}
 }
 
 impl MockAnalytics {

meilisearch-http/src/analytics/segment_analytics.rs

@@ -1,4 +1,4 @@
-use std::collections::{HashMap, HashSet};
+use std::collections::{BinaryHeap, HashMap, HashSet};
 use std::fs;
 use std::path::Path;
 use std::sync::Arc;
@@ -38,7 +38,7 @@ fn write_user_id(db_path: &Path, user_id: &str) {
     }
 }
 
-const SEGMENT_API_KEY: &str = "vHi89WrNDckHSQssyUJqLvIyp2QFITSC";
+const SEGMENT_API_KEY: &str = "P3FWhhEsJiEDCuEHpmcN9DHcK4hVfBvb";
 
 pub fn extract_user_agents(request: &HttpRequest) -> Vec<String> {
     request
@@ -187,7 +187,7 @@ impl Segment {
                     "kernel_version": kernel_version,
                     "cores": sys.processors().len(),
                     "ram_size": sys.total_memory(),
-                    "disk_size": sys.disks().iter().map(|disk| disk.available_space()).max(),
+                    "disk_size": sys.disks().iter().map(|disk| disk.total_space()).max(),
                     "server_provider": std::env::var("MEILI_SERVER_PROVIDER").ok(),
             })
         });
@@ -254,9 +254,9 @@ impl Segment {
                 .await;
         }
         let get_search = std::mem::take(&mut self.get_search_aggregator)
-            .into_event(&self.user, "Document Searched GET");
+            .into_event(&self.user, "Documents Searched GET");
         let post_search = std::mem::take(&mut self.post_search_aggregator)
-            .into_event(&self.user, "Document Searched POST");
+            .into_event(&self.user, "Documents Searched POST");
         let add_documents = std::mem::take(&mut self.add_documents_aggregator)
             .into_event(&self.user, "Documents Added");
         let update_documents = std::mem::take(&mut self.update_documents_aggregator)
@@ -286,7 +286,7 @@ pub struct SearchAggregator {
     // requests
     total_received: usize,
     total_succeeded: usize,
-    time_spent: Vec<usize>,
+    time_spent: BinaryHeap<usize>,
 
     // sort
     sort_with_geo_point: bool,
@@ -364,7 +364,7 @@ impl SearchAggregator {
         ret
     }
 
-    pub fn finish(&mut self, result: &SearchResult) {
+    pub fn succeed(&mut self, result: &SearchResult) {
         self.total_succeeded += 1;
         self.time_spent.push(result.processing_time_ms as usize);
     }
@@ -398,17 +398,21 @@ impl SearchAggregator {
         self.max_offset = self.max_offset.max(other.max_offset);
     }
 
-    pub fn into_event(mut self, user: &User, event_name: &str) -> Option<Track> {
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
         if self.total_received == 0 {
             None
         } else {
+            // the index of the 99th percentage of value
             let percentile_99th = 0.99 * (self.total_succeeded as f64 - 1.) + 1.;
-            self.time_spent.drain(percentile_99th as usize..);
+            // we get all the values in a sorted manner
+            let time_spent = self.time_spent.into_sorted_vec();
+            // We are only intersted by the slowest value of the 99th fastest results
+            let time_spent = time_spent[percentile_99th as usize];
 
             let properties = json!({
                 "user-agent": self.user_agents,
                 "requests": {
-                    "99th_response_time":  format!("{:.2}", self.time_spent.iter().sum::<usize>() as f64 / self.time_spent.len() as f64),
+                    "99th_response_time":  format!("{:.2}", time_spent),
                     "total_succeeded": self.total_succeeded,
                     "total_failed": self.total_received.saturating_sub(self.total_succeeded), // just to be sure we never panics
                     "total_received": self.total_received,

meilisearch-http/src/extractors/authentication/error.rs

@@ -2,14 +2,14 @@ use meilisearch_error::{Code, ErrorCode};
 
 #[derive(Debug, thiserror::Error)]
 pub enum AuthenticationError {
-    #[error("You must have an authorization token")]
+    #[error("The X-MEILI-API-KEY header is missing.")]
     MissingAuthorizationHeader,
-    #[error("Invalid API key")]
+    #[error("The provided API key is invalid.")]
     InvalidToken(String),
     // Triggered on configuration error.
-    #[error("Irretrievable state")]
+    #[error("An internal error has occurred. `Irretrievable state`.")]
     IrretrievableState,
-    #[error("Unknown authentication policy")]
+    #[error("An internal error has occurred. `Unknown authentication policy`.")]
     UnknownPolicy,
 }
 

meilisearch-http/src/routes/indexes/search.rs

@@ -118,17 +118,18 @@ pub async fn search_with_url_query(
 
     let mut aggregate = SearchAggregator::from_query(&query, &req);
 
-    let search_result = meilisearch
-        .search(path.into_inner().index_uid, query)
-        .await?;
+    let search_result = meilisearch.search(path.into_inner().index_uid, query).await;
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.get_search(aggregate);
+
+    let search_result = search_result?;
 
     // Tests that the nb_hits is always set to false
     #[cfg(test)]
     assert!(!search_result.exhaustive_nb_hits);
 
-    aggregate.finish(&search_result);
-    analytics.get_search(aggregate);
-
     debug!("returns: {:?}", search_result);
     Ok(HttpResponse::Ok().json(search_result))
 }
@@ -145,17 +146,18 @@ pub async fn search_with_post(
 
     let mut aggregate = SearchAggregator::from_query(&query, &req);
 
-    let search_result = meilisearch
-        .search(path.into_inner().index_uid, query)
-        .await?;
+    let search_result = meilisearch.search(path.into_inner().index_uid, query).await;
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.post_search(aggregate);
+
+    let search_result = search_result?;
 
     // Tests that the nb_hits is always set to false
     #[cfg(test)]
     assert!(!search_result.exhaustive_nb_hits);
 
-    aggregate.finish(&search_result);
-    analytics.post_search(aggregate);
-
     debug!("returns: {:?}", search_result);
     Ok(HttpResponse::Ok().json(search_result))
 }

meilisearch-http/src/routes/mod.rs

@@ -97,8 +97,7 @@ pub struct FailedUpdateResult {
     pub update_id: u64,
     #[serde(rename = "type")]
     pub update_type: UpdateType,
-    #[serde(flatten)]
-    pub response: ResponseError,
+    pub error: ResponseError,
     pub duration: f64, // in seconds
     pub enqueued_at: DateTime<Utc>,
     pub processed_at: DateTime<Utc>,
@@ -190,12 +189,12 @@ impl From<UpdateStatus> for UpdateStatusResponse {
                 let update_id = failed.id();
                 let processed_at = failed.failed_at;
                 let enqueued_at = failed.from.from.enqueued_at;
-                let response = failed.into();
+                let error = failed.into();
 
                 let content = FailedUpdateResult {
                     update_id,
                     update_type,
-                    response,
+                    error,
                     duration,
                     enqueued_at,
                     processed_at,

meilisearch-http/tests/common/index.rs

@@ -7,6 +7,7 @@ use actix_web::http::StatusCode;
 use paste::paste;
 use serde_json::{json, Value};
 use tokio::time::sleep;
+use urlencoding::encode;
 
 use super::service::Service;
 
@@ -14,12 +15,12 @@ macro_rules! make_settings_test_routes {
     ($($name:ident),+) => {
         $(paste! {
             pub async fn [<update_$name>](&self, value: Value) -> (Value, StatusCode) {
-                let url = format!("/indexes/{}/settings/{}", self.uid, stringify!($name).replace("_", "-"));
+                let url = format!("/indexes/{}/settings/{}", encode(self.uid.as_ref()).to_string(), stringify!($name).replace("_", "-"));
                 self.service.post(url, value).await
             }
 
             pub async fn [<get_$name>](&self) -> (Value, StatusCode) {
-                let url = format!("/indexes/{}/settings/{}", self.uid, stringify!($name).replace("_", "-"));
+                let url = format!("/indexes/{}/settings/{}", encode(self.uid.as_ref()).to_string(), stringify!($name).replace("_", "-"));
                 self.service.get(url).await
             }
         })*
@@ -34,12 +35,15 @@ pub struct Index<'a> {
 #[allow(dead_code)]
 impl Index<'_> {
     pub async fn get(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", self.uid);
+        let url = format!("/indexes/{}", encode(self.uid.as_ref()).to_string());
         self.service.get(url).await
     }
 
     pub async fn load_test_set(&self) -> u64 {
-        let url = format!("/indexes/{}/documents", self.uid);
+        let url = format!(
+            "/indexes/{}/documents",
+            encode(self.uid.as_ref()).to_string()
+        );
         let (response, code) = self
             .service
             .post_str(url, include_str!("../assets/test_set.json"))
@@ -62,13 +66,13 @@ impl Index<'_> {
         let body = json!({
             "primaryKey": primary_key,
         });
-        let url = format!("/indexes/{}", self.uid);
+        let url = format!("/indexes/{}", encode(self.uid.as_ref()).to_string());
 
         self.service.put(url, body).await
     }
 
     pub async fn delete(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", self.uid);
+        let url = format!("/indexes/{}", encode(self.uid.as_ref()).to_string());
         self.service.delete(url).await
     }
 
@@ -78,8 +82,15 @@ impl Index<'_> {
         primary_key: Option<&str>,
     ) -> (Value, StatusCode) {
         let url = match primary_key {
-            Some(key) => format!("/indexes/{}/documents?primaryKey={}", self.uid, key),
-            None => format!("/indexes/{}/documents", self.uid),
+            Some(key) => format!(
+                "/indexes/{}/documents?primaryKey={}",
+                encode(self.uid.as_ref()).to_string(),
+                key
+            ),
+            None => format!(
+                "/indexes/{}/documents",
+                encode(self.uid.as_ref()).to_string()
+            ),
         };
         self.service.post(url, documents).await
     }
@@ -90,15 +101,26 @@ impl Index<'_> {
         primary_key: Option<&str>,
     ) -> (Value, StatusCode) {
         let url = match primary_key {
-            Some(key) => format!("/indexes/{}/documents?primaryKey={}", self.uid, key),
-            None => format!("/indexes/{}/documents", self.uid),
+            Some(key) => format!(
+                "/indexes/{}/documents?primaryKey={}",
+                encode(self.uid.as_ref()).to_string(),
+                key
+            ),
+            None => format!(
+                "/indexes/{}/documents",
+                encode(self.uid.as_ref()).to_string()
+            ),
         };
         self.service.put(url, documents).await
     }
 
     pub async fn wait_update_id(&self, update_id: u64) -> Value {
         // try 10 times to get status, or panic to not wait forever
-        let url = format!("/indexes/{}/updates/{}", self.uid, update_id);
+        let url = format!(
+            "/indexes/{}/updates/{}",
+            encode(self.uid.as_ref()).to_string(),
+            update_id
+        );
         for _ in 0..10 {
             let (response, status_code) = self.service.get(&url).await;
             assert_eq!(status_code, 200, "response: {}", response);
@@ -113,12 +135,16 @@ impl Index<'_> {
     }
 
     pub async fn get_update(&self, update_id: u64) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/updates/{}", self.uid, update_id);
+        let url = format!(
+            "/indexes/{}/updates/{}",
+            encode(self.uid.as_ref()).to_string(),
+            update_id
+        );
         self.service.get(url).await
     }
 
     pub async fn list_updates(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/updates", self.uid);
+        let url = format!("/indexes/{}/updates", encode(self.uid.as_ref()).to_string());
         self.service.get(url).await
     }
 
@@ -127,12 +153,19 @@ impl Index<'_> {
         id: u64,
         _options: Option<GetDocumentOptions>,
     ) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/{}", self.uid, id);
+        let url = format!(
+            "/indexes/{}/documents/{}",
+            encode(self.uid.as_ref()).to_string(),
+            id
+        );
         self.service.get(url).await
     }
 
     pub async fn get_all_documents(&self, options: GetAllDocumentsOptions) -> (Value, StatusCode) {
-        let mut url = format!("/indexes/{}/documents?", self.uid);
+        let mut url = format!(
+            "/indexes/{}/documents?",
+            encode(self.uid.as_ref()).to_string()
+        );
         if let Some(limit) = options.limit {
             url.push_str(&format!("limit={}&", limit));
         }
@@ -152,39 +185,58 @@ impl Index<'_> {
     }
 
     pub async fn delete_document(&self, id: u64) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/{}", self.uid, id);
+        let url = format!(
+            "/indexes/{}/documents/{}",
+            encode(self.uid.as_ref()).to_string(),
+            id
+        );
         self.service.delete(url).await
     }
 
     pub async fn clear_all_documents(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents", self.uid);
+        let url = format!(
+            "/indexes/{}/documents",
+            encode(self.uid.as_ref()).to_string()
+        );
         self.service.delete(url).await
     }
 
     pub async fn delete_batch(&self, ids: Vec<u64>) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/delete-batch", self.uid);
+        let url = format!(
+            "/indexes/{}/documents/delete-batch",
+            encode(self.uid.as_ref()).to_string()
+        );
         self.service
             .post(url, serde_json::to_value(&ids).unwrap())
             .await
     }
 
     pub async fn settings(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", self.uid);
+        let url = format!(
+            "/indexes/{}/settings",
+            encode(self.uid.as_ref()).to_string()
+        );
         self.service.get(url).await
     }
 
     pub async fn update_settings(&self, settings: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", self.uid);
+        let url = format!(
+            "/indexes/{}/settings",
+            encode(self.uid.as_ref()).to_string()
+        );
         self.service.post(url, settings).await
     }
 
     pub async fn delete_settings(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", self.uid);
+        let url = format!(
+            "/indexes/{}/settings",
+            encode(self.uid.as_ref()).to_string()
+        );
         self.service.delete(url).await
     }
 
     pub async fn stats(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/stats", self.uid);
+        let url = format!("/indexes/{}/stats", encode(self.uid.as_ref()).to_string());
         self.service.get(url).await
     }
 
@@ -209,13 +261,17 @@ impl Index<'_> {
     }
 
     pub async fn search_post(&self, query: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/search", self.uid);
+        let url = format!("/indexes/{}/search", encode(self.uid.as_ref()).to_string());
         self.service.post(url, query).await
     }
 
     pub async fn search_get(&self, query: Value) -> (Value, StatusCode) {
         let params = serde_url_params::to_string(&query).unwrap();
-        let url = format!("/indexes/{}/search?{}", self.uid, params);
+        let url = format!(
+            "/indexes/{}/search?{}",
+            encode(self.uid.as_ref()).to_string(),
+            params
+        );
         self.service.get(url).await
     }
 

meilisearch-http/tests/common/server.rs

@@ -7,7 +7,6 @@ use meilisearch_lib::options::{IndexerOpts, MaxMemory};
 use once_cell::sync::Lazy;
 use serde_json::Value;
 use tempfile::TempDir;
-use urlencoding::encode;
 
 use meilisearch_http::option::Opt;
 
@@ -62,7 +61,7 @@ impl Server {
     /// Returns a view to an index. There is no guarantee that the index exists.
     pub fn index(&self, uid: impl AsRef<str>) -> Index<'_> {
         Index {
-            uid: encode(uid.as_ref()).to_string(),
+            uid: uid.as_ref().to_string(),
             service: &self.service,
         }
     }

meilisearch-http/tests/documents/add_documents.rs

@@ -812,13 +812,15 @@ async fn error_add_documents_bad_document_id() {
     let (response, code) = index.get_update(0).await;
     assert_eq!(code, 200);
     assert_eq!(response["status"], json!("failed"));
-    assert_eq!(response["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["code"], json!("invalid_document_id"));
-    assert_eq!(response["type"], json!("invalid_request"));
-    assert_eq!(
-        response["link"],
-        json!("https://docs.meilisearch.com/errors#invalid_document_id")
-    );
+
+    let expected_error = json!({
+        "message": "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 (_).",
+        "code": "invalid_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_document_id"
+    });
+
+    assert_eq!(response["error"], expected_error);
 }
 
 #[actix_rt::test]
@@ -837,13 +839,15 @@ async fn error_update_documents_bad_document_id() {
     let (response, code) = index.get_update(0).await;
     assert_eq!(code, 200);
     assert_eq!(response["status"], json!("failed"));
-    assert_eq!(response["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["code"], json!("invalid_document_id"));
-    assert_eq!(response["type"], json!("invalid_request"));
-    assert_eq!(
-        response["link"],
-        json!("https://docs.meilisearch.com/errors#invalid_document_id")
-    );
+
+    let expected_error = json!({
+        "message": "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 (_).",
+        "code": "invalid_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_document_id"
+    });
+
+    assert_eq!(response["error"], expected_error);
 }
 
 #[actix_rt::test]
@@ -862,16 +866,15 @@ async fn error_add_documents_missing_document_id() {
     let (response, code) = index.get_update(0).await;
     assert_eq!(code, 200);
     assert_eq!(response["status"], "failed");
-    assert_eq!(
-        response["message"],
-        json!(r#"Document doesn't have a `docid` attribute: `{"id":"11","content":"foobar"}`."#)
-    );
-    assert_eq!(response["code"], json!("missing_document_id"));
-    assert_eq!(response["type"], json!("invalid_request"));
-    assert_eq!(
-        response["link"],
-        json!("https://docs.meilisearch.com/errors#missing_document_id")
-    );
+
+    let expected_error = json!({
+        "message": r#"Document doesn't have a `docid` attribute: `{"id":"11","content":"foobar"}`."#,
+        "code": "missing_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#missing_document_id"
+    });
+
+    assert_eq!(response["error"], expected_error);
 }
 
 #[actix_rt::test]
@@ -890,16 +893,15 @@ async fn error_update_documents_missing_document_id() {
     let (response, code) = index.get_update(0).await;
     assert_eq!(code, 200);
     assert_eq!(response["status"], "failed");
-    assert_eq!(
-        response["message"],
-        r#"Document doesn't have a `docid` attribute: `{"id":"11","content":"foobar"}`."#
-    );
-    assert_eq!(response["code"], "missing_document_id");
-    assert_eq!(response["type"], "invalid_request");
-    assert_eq!(
-        response["link"],
-        "https://docs.meilisearch.com/errors#missing_document_id"
-    );
+
+    let expected_error = json!({
+        "message": r#"Document doesn't have a `docid` attribute: `{"id":"11","content":"foobar"}`."#,
+        "code": "missing_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#missing_document_id"
+    });
+
+    assert_eq!(response["error"], expected_error);
 }
 
 #[actix_rt::test]
@@ -927,45 +929,47 @@ async fn error_document_field_limit_reached() {
     assert_eq!(code, 200);
     // Documents without a primary key are not accepted.
     assert_eq!(response["status"], "failed");
-    assert_eq!(
-        response["message"],
-        "A document cannot contain more than 65,535 fields."
-    );
-    assert_eq!(response["code"], "document_fields_limit_reached");
-    assert_eq!(response["type"], "invalid_request");
-    assert_eq!(
-        response["link"],
-        "https://docs.meilisearch.com/errors#document_fields_limit_reached"
-    );
+
+    let expected_error = json!({
+        "message": "A document cannot contain more than 65,535 fields.",
+        "code": "document_fields_limit_reached",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#document_fields_limit_reached"
+    });
+
+    assert_eq!(response["error"], expected_error);
 }
 
 #[actix_rt::test]
-#[ignore] // // TODO: Fix in an other PR: this does not provoke any error.
 async fn error_add_documents_invalid_geo_field() {
     let server = Server::new().await;
     let index = server.index("test");
     index.create(Some("id")).await;
+    index
+        .update_settings(json!({"sortableAttributes": ["_geo"]}))
+        .await;
+
     let documents = json!([
         {
             "id": "11",
             "_geo": "foobar"
         }
     ]);
+
     index.add_documents(documents, None).await;
-    index.wait_update_id(0).await;
-    let (response, code) = index.get_update(0).await;
+    index.wait_update_id(1).await;
+    let (response, code) = index.get_update(1).await;
     assert_eq!(code, 200);
     assert_eq!(response["status"], "failed");
-    assert_eq!(
-        response["message"],
-        r#"The document with the id: `11` contains an invalid _geo field: :syntaxErrorHelper:REPLACE_ME."#
-    );
-    assert_eq!(response["code"], "invalid_geo_field");
-    assert_eq!(response["type"], "invalid_request");
-    assert_eq!(
-        response["link"],
-        "https://docs.meilisearch.com/errors#invalid_geo_field"
-    );
+
+    let expected_error = json!({
+        "message": r#"The document with the id: `11` contains an invalid _geo field: `foobar`."#,
+        "code": "invalid_geo_field",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_geo_field"
+    });
+
+    assert_eq!(response["error"], expected_error);
 }
 
 #[actix_rt::test]
@@ -993,3 +997,31 @@ async fn error_add_documents_payload_size() {
     assert_eq!(response, expected_response);
     assert_eq!(code, 413);
 }
+
+#[actix_rt::test]
+async fn error_primary_key_inference() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = json!([
+        {
+            "title": "11",
+            "desc": "foobar"
+        }
+    ]);
+
+    index.add_documents(documents, None).await;
+    index.wait_update_id(0).await;
+    let (response, code) = index.get_update(0).await;
+    assert_eq!(code, 200);
+    assert_eq!(response["status"], "failed");
+
+    let expected_error = json!({
+        "message": r#"The primary key inference process failed because the engine did not find any fields containing `id` substring in their name. If your document identifier does not contain any `id` substring, you can set the primary key of the index."#,
+        "code": "primary_key_inference_failed",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#primary_key_inference_failed"
+    });
+
+    assert_eq!(response["error"], expected_error);
+}

meilisearch-http/tests/index/create_index.rs

@@ -89,7 +89,6 @@ async fn error_create_existing_index() {
 }
 
 #[actix_rt::test]
-#[ignore] // TODO: Fix in an other PR: uid returned `test%20test%23%21` instead of `test test#!`
 async fn error_create_with_invalid_index_uid() {
     let server = Server::new().await;
     let index = server.index("test test#!");

meilisearch-http/tests/settings/get_settings.rs

@@ -63,7 +63,7 @@ async fn get_settings() {
 }
 
 #[actix_rt::test]
-async fn update_settings_unknown_field() {
+async fn error_update_settings_unknown_field() {
     let server = Server::new().await;
     let index = server.index("test");
     let (_response, code) = index.update_settings(json!({"foo": 12})).await;
@@ -95,10 +95,19 @@ async fn test_partial_update() {
 }
 
 #[actix_rt::test]
-async fn delete_settings_unexisting_index() {
+async fn error_delete_settings_unexisting_index() {
     let server = Server::new().await;
     let index = server.index("test");
-    let (_response, code) = index.delete_settings().await;
+    let (response, code) = index.delete_settings().await;
+
+    let expected_response = json!({
+        "message": "Index `test` not found.",
+        "code": "index_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#index_not_found"
+    });
+
+    assert_eq!(response, expected_response);
     assert_eq!(code, 404);
 }
 
@@ -164,11 +173,20 @@ async fn update_setting_unexisting_index() {
 }
 
 #[actix_rt::test]
-async fn update_setting_unexisting_index_invalid_uid() {
+async fn error_update_setting_unexisting_index_invalid_uid() {
     let server = Server::new().await;
     let index = server.index("test##!  ");
     let (response, code) = index.update_settings(json!({})).await;
-    assert_eq!(code, 400, "{}", response);
+
+    let expected_response = json!({
+        "message": "`test##!  ` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+        "code": "invalid_index_uid",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
+    });
+
+    assert_eq!(response, expected_response);
+    assert_eq!(code, 400);
 }
 
 macro_rules! test_setting_routes {
@@ -246,3 +264,49 @@ test_setting_routes!(
     ranking_rules,
     synonyms
 );
+
+#[actix_rt::test]
+async fn error_set_invalid_ranking_rules() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    index.create(None).await;
+
+    let (_response, _code) = index
+        .update_settings(json!({ "rankingRules": [ "manyTheFish"]}))
+        .await;
+    index.wait_update_id(0).await;
+    let (response, code) = index.get_update(0).await;
+
+    assert_eq!(code, 200);
+    assert_eq!(response["status"], "failed");
+
+    let expected_error = json!({
+        "message": r#"`manyTheFish` ranking rule is invalid. Valid ranking rules are Words, Typo, Sort, Proximity, Attribute, Exactness and custom ranking rules."#,
+        "code": "invalid_ranking_rule",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_ranking_rule"
+    });
+
+    assert_eq!(response["error"], expected_error);
+}
+
+#[actix_rt::test]
+async fn set_and_reset_distinct_attribute_with_dedicated_route() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (_response, _code) = index.update_distinct_attribute(json!("test")).await;
+    index.wait_update_id(0).await;
+
+    let (response, _) = index.get_distinct_attribute().await;
+
+    assert_eq!(response, "test");
+
+    index.update_distinct_attribute(json!(null)).await;
+
+    index.wait_update_id(1).await;
+
+    let (response, _) = index.get_distinct_attribute().await;
+
+    assert_eq!(response, json!(null));
+}

meilisearch-lib/Cargo.toml

@@ -30,7 +30,7 @@ lazy_static = "1.4.0"
 log = "0.4.14"
 meilisearch-error = { path = "../meilisearch-error" }
 meilisearch-tokenizer = { git = "https://github.com/meilisearch/tokenizer.git", tag = "v0.2.5" }
-milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.20.0" }
+milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.20.2" }
 mime = "0.3.16"
 num_cpus = "1.13.0"
 once_cell = "1.8.0"

meilisearch-lib/src/document_formats.rs

@@ -25,7 +25,7 @@ impl fmt::Display for PayloadType {
 
 #[derive(thiserror::Error, Debug)]
 pub enum DocumentFormatError {
-    #[error("Internal error!: {0}")]
+    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn std::error::Error + Send + Sync + 'static>),
     #[error("The `{1}` payload provided is malformed. `{0}`.")]
     MalformedPayload(

meilisearch-lib/src/error.rs

@@ -36,11 +36,11 @@ impl ErrorCode for MilliError<'_> {
                 match error {
                     // TODO: wait for spec for new error codes.
                     UserError::SerdeJson(_)
-                    | UserError::MaxDatabaseSizeReached
-                    | UserError::InvalidStoreFile
-                    | UserError::NoSpaceLeftOnDevice
                     | UserError::DocumentLimitReached
                     | UserError::UnknownInternalDocumentId { .. } => Code::Internal,
+                    UserError::InvalidStoreFile => Code::InvalidStore,
+                    UserError::NoSpaceLeftOnDevice => Code::NoSpaceLeftOnDevice,
+                    UserError::MaxDatabaseSizeReached => Code::DatabaseSizeLimitReached,
                     UserError::AttributeLimitReached => Code::MaxFieldsLimitExceeded,
                     UserError::InvalidFilter(_) => Code::Filter,
                     UserError::MissingDocumentId { .. } => Code::MissingDocumentId,

meilisearch-lib/src/index/error.rs

@@ -9,7 +9,7 @@ pub type Result<T> = std::result::Result<T, IndexError>;
 
 #[derive(Debug, thiserror::Error)]
 pub enum IndexError {
-    #[error("Internal error: {0}")]
+    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn Error + Send + Sync + 'static>),
     #[error("Document `{0}` not found.")]
     DocumentNotFound(String),

meilisearch-lib/src/index_controller/dump_actor/error.rs

@@ -7,11 +7,11 @@ pub type Result<T> = std::result::Result<T, DumpActorError>;
 
 #[derive(thiserror::Error, Debug)]
 pub enum DumpActorError {
-    #[error("Another dump is already in progress")]
+    #[error("A dump is already processing. You must wait until the current process is finished before requesting another dump.")]
     DumpAlreadyRunning,
     #[error("Dump `{0}` not found.")]
     DumpDoesNotExist(String),
-    #[error("Internal error: {0}")]
+    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn std::error::Error + Send + Sync + 'static>),
     #[error("{0}")]
     IndexResolver(#[from] IndexResolverError),
@@ -43,7 +43,7 @@ impl ErrorCode for DumpActorError {
     fn error_code(&self) -> Code {
         match self {
             DumpActorError::DumpAlreadyRunning => Code::DumpAlreadyInProgress,
-            DumpActorError::DumpDoesNotExist(_) => Code::NotFound,
+            DumpActorError::DumpDoesNotExist(_) => Code::DumpNotFound,
             DumpActorError::Internal(_) => Code::Internal,
             DumpActorError::IndexResolver(e) => e.error_code(),
             DumpActorError::UpdateLoop(e) => e.error_code(),

meilisearch-lib/src/index_controller/dump_actor/loaders/v2.rs

@@ -361,14 +361,13 @@ mod compat {
             "index_already_exists" => Code::IndexAlreadyExists,
             "index_not_found" => Code::IndexNotFound,
             "invalid_index_uid" => Code::InvalidIndexUid,
-            "index_not_accessible" => Code::OpenIndex,
             "invalid_state" => Code::InvalidState,
             "missing_primary_key" => Code::MissingPrimaryKey,
             "primary_key_already_present" => Code::PrimaryKeyAlreadyPresent,
             "invalid_request" => Code::InvalidRankingRule,
             "max_fields_limit_exceeded" => Code::MaxFieldsLimitExceeded,
             "missing_document_id" => Code::MissingDocumentId,
-            "invalid_facet" => Code::Facet,
+            "invalid_facet" => Code::Filter,
             "invalid_filter" => Code::Filter,
             "invalid_sort" => Code::Sort,
             "bad_parameter" => Code::BadParameter,
@@ -378,7 +377,6 @@ mod compat {
             "invalid_geo_field" => Code::InvalidGeoField,
             "invalid_token" => Code::InvalidToken,
             "missing_authorization_header" => Code::MissingAuthorizationHeader,
-            "not_found" => Code::NotFound,
             "payload_too_large" => Code::PayloadTooLarge,
             "unretrievable_document" => Code::RetrieveDocument,
             "search_error" => Code::SearchDocuments,

meilisearch-lib/src/index_controller/error.rs

@@ -24,7 +24,7 @@ pub enum IndexControllerError {
     DumpActor(#[from] DumpActorError),
     #[error("{0}")]
     IndexError(#[from] IndexError),
-    #[error("Internal error: {0}")]
+    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn Error + Send + Sync + 'static>),
 }
 

meilisearch-lib/src/index_controller/index_resolver/error.rs

@@ -19,9 +19,9 @@ pub enum IndexResolverError {
     UnexistingIndex(String),
     #[error("A primary key is already present. It's impossible to update it")]
     ExistingPrimaryKey,
-    #[error("Internal Error: `{0}`")]
+    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn std::error::Error + Send + Sync + 'static>),
-    #[error("Internal Error: Index uuid `{0}` is already assigned.")]
+    #[error("The creation of the `{0}` index has failed due to `Index uuid is already assigned`.")]
     UuidAlreadyExists(Uuid),
     #[error("{0}")]
     Milli(#[from] milli::Error),
@@ -60,7 +60,7 @@ impl ErrorCode for IndexResolverError {
             IndexResolverError::UnexistingIndex(_) => Code::IndexNotFound,
             IndexResolverError::ExistingPrimaryKey => Code::PrimaryKeyAlreadyPresent,
             IndexResolverError::Internal(_) => Code::Internal,
-            IndexResolverError::UuidAlreadyExists(_) => Code::Internal,
+            IndexResolverError::UuidAlreadyExists(_) => Code::CreateIndex,
             IndexResolverError::Milli(e) => MilliError(e).error_code(),
             IndexResolverError::BadlyFormatted(_) => Code::InvalidIndexUid,
         }

meilisearch-lib/src/index_controller/updates/error.rs

@@ -16,7 +16,7 @@ pub type Result<T> = std::result::Result<T, UpdateLoopError>;
 pub enum UpdateLoopError {
     #[error("Task `{0}` not found.")]
     UnexistingUpdate(u64),
-    #[error("Internal error: {0}")]
+    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn Error + Send + Sync + 'static>),
     #[error(
         "update store was shut down due to a fatal error, please check your logs for more info."