Merge #5011

5011: Revamp analytics r=ManyTheFish a=irevoire

# Pull Request

## Related issue
Fixes https://github.com/meilisearch/meilisearch/issues/5009

## What does this PR do?
- Force every analytics to go through a trait that forces you to handle aggregation correcty
- Put the code to retrieve the `user-agent`, `timestamp` and `requests.total_received` in common between all aggregates, so there is no mistake
- Get rids of all the different channel for each kind of event in favor of an any map
- Ensure that we never [send empty event ever again](https://github.com/meilisearch/meilisearch/pull/5001)
- Merge all the sub-settings route into a global « Settings Updated » event.
- Fix: When using one of the three following feature, we were not sending any analytics IF they were set from the global route
  - /non-separator-tokens
  - /separator-tokens
  - /dictionary

Co-authored-by: Tamo <tamo@meilisearch.com>

Cargo.lock

@@ -3415,6 +3415,7 @@ dependencies = [
  "meilisearch-types",
  "mimalloc",
  "mime",
+ "mopa-maintained",
  "num_cpus",
  "obkv",
  "once_cell",
@@ -3681,6 +3682,12 @@ dependencies = [
  "syn 2.0.60",
 ]
 
+[[package]]
+name = "mopa-maintained"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79b7f3e22167862cc7c95b21a6f326c22e4bf40da59cbf000b368a310173ba11"
+
 [[package]]
 name = "mutually_exclusive_features"
 version = "0.0.3"

meilisearch/Cargo.toml

@@ -75,7 +75,7 @@ reqwest = { version = "0.12.5", features = [
 rustls = { version = "0.23.11", features = ["ring"], default-features = false }
 rustls-pki-types = { version = "1.7.0", features = ["alloc"] }
 rustls-pemfile = "2.1.2"
-segment = { version = "0.2.4", optional = true }
+segment = { version = "0.2.4" }
 serde = { version = "1.0.204", features = ["derive"] }
 serde_json = { version = "1.0.120", features = ["preserve_order"] }
 sha2 = "0.10.8"
@@ -104,6 +104,7 @@ tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
 tracing-actix-web = "0.7.11"
 build-info = { version = "1.7.0", path = "../build-info" }
 roaring = "0.10.2"
+mopa-maintained = "0.2.3"
 
 [dev-dependencies]
 actix-rt = "2.10.0"
@@ -131,8 +132,7 @@ tempfile = { version = "3.10.1", optional = true }
 zip = { version = "2.1.3", optional = true }
 
 [features]
-default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
+default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
-analytics = ["segment"]
 mini-dashboard = [
     "static-files",
     "anyhow",

meilisearch/src/analytics/mock_analytics.rs

@@ -1,109 +0,0 @@
-use std::any::Any;
-use std::sync::Arc;
-
-use actix_web::HttpRequest;
-use meilisearch_types::InstanceUid;
-use serde_json::Value;
-
-use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
-use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
-use crate::Opt;
-
-pub struct MockAnalytics {
-    instance_uid: Option<InstanceUid>,
-}
-
-#[derive(Default)]
-pub struct SearchAggregator;
-
-#[allow(dead_code)]
-impl SearchAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
-#[derive(Default)]
-pub struct SimilarAggregator;
-
-#[allow(dead_code)]
-impl SimilarAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
-#[derive(Default)]
-pub struct MultiSearchAggregator;
-
-#[allow(dead_code)]
-impl MultiSearchAggregator {
-    pub fn from_federated_search(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self) {}
-}
-
-#[derive(Default)]
-pub struct FacetSearchAggregator;
-
-#[allow(dead_code)]
-impl FacetSearchAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
-impl MockAnalytics {
-    #[allow(clippy::new_ret_no_self)]
-    pub fn new(opt: &Opt) -> Arc<dyn Analytics> {
-        let instance_uid = find_user_id(&opt.db_path);
-        Arc::new(Self { instance_uid })
-    }
-}
-
-impl Analytics for MockAnalytics {
-    fn instance_uid(&self) -> Option<&meilisearch_types::InstanceUid> {
-        self.instance_uid.as_ref()
-    }
-
-    // These methods are noop and should be optimized out
-    fn publish(&self, _event_name: String, _send: Value, _request: Option<&HttpRequest>) {}
-    fn get_search(&self, _aggregate: super::SearchAggregator) {}
-    fn post_search(&self, _aggregate: super::SearchAggregator) {}
-    fn get_similar(&self, _aggregate: super::SimilarAggregator) {}
-    fn post_similar(&self, _aggregate: super::SimilarAggregator) {}
-    fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
-    fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
-    fn add_documents(
-        &self,
-        _documents_query: &UpdateDocumentsQuery,
-        _index_creation: bool,
-        _request: &HttpRequest,
-    ) {
-    }
-    fn delete_documents(&self, _kind: DocumentDeletionKind, _request: &HttpRequest) {}
-    fn update_documents(
-        &self,
-        _documents_query: &UpdateDocumentsQuery,
-        _index_creation: bool,
-        _request: &HttpRequest,
-    ) {
-    }
-    fn update_documents_by_function(
-        &self,
-        _documents_query: &DocumentEditionByFunction,
-        _index_creation: bool,
-        _request: &HttpRequest,
-    ) {
-    }
-    fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-    fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-}

meilisearch/src/analytics/mod.rs

@@ -1,44 +1,45 @@
-mod mock_analytics;
+pub mod segment_analytics;
-#[cfg(feature = "analytics")]
-mod segment_analytics;
 
 use std::fs;
 use std::path::{Path, PathBuf};
 use std::str::FromStr;
+use std::sync::Arc;
 
 use actix_web::HttpRequest;
+use index_scheduler::IndexScheduler;
+use meilisearch_auth::AuthController;
 use meilisearch_types::InstanceUid;
-pub use mock_analytics::MockAnalytics;
+use mopa::mopafy;
 use once_cell::sync::Lazy;
 use platform_dirs::AppDirs;
-use serde_json::Value;
-
-use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
-
-// if the analytics feature is disabled
-// the `SegmentAnalytics` point to the mock instead of the real analytics
-#[cfg(not(feature = "analytics"))]
-pub type SegmentAnalytics = mock_analytics::MockAnalytics;
-#[cfg(not(feature = "analytics"))]
-pub type SearchAggregator = mock_analytics::SearchAggregator;
-#[cfg(not(feature = "analytics"))]
-pub type SimilarAggregator = mock_analytics::SimilarAggregator;
-#[cfg(not(feature = "analytics"))]
-pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(not(feature = "analytics"))]
-pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
 // if the feature analytics is enabled we use the real analytics
-#[cfg(feature = "analytics")]
 pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
-#[cfg(feature = "analytics")]
+
-pub type SearchAggregator = segment_analytics::SearchAggregator;
+use crate::Opt;
-#[cfg(feature = "analytics")]
+
-pub type SimilarAggregator = segment_analytics::SimilarAggregator;
+/// A macro used to quickly define events that don't aggregate or send anything besides an empty event with its name.
-#[cfg(feature = "analytics")]
+#[macro_export]
-pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
+macro_rules! empty_analytics {
-#[cfg(feature = "analytics")]
+    ($struct_name:ident, $event_name:literal) => {
-pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
+        #[derive(Default)]
+        struct $struct_name {}
+
+        impl $crate::analytics::Aggregate for $struct_name {
+            fn event_name(&self) -> &'static str {
+                $event_name
+            }
+
+            fn aggregate(self: Box<Self>, _other: Box<Self>) -> Box<Self> {
+                self
+            }
+
+            fn into_event(self: Box<Self>) -> serde_json::Value {
+                serde_json::json!({})
+            }
+        }
+    };
+}
 
 /// The Meilisearch config dir:
 /// `~/.config/Meilisearch` on *NIX or *BSD.
@@ -78,60 +79,88 @@ pub enum DocumentFetchKind {
     Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
 }
 
-pub trait Analytics: Sync + Send {
+/// To send an event to segment, your event must be able to aggregate itself with another event of the same type.
-    fn instance_uid(&self) -> Option<&InstanceUid>;
+pub trait Aggregate: 'static + mopa::Any + Send {
+    /// The name of the event that will be sent to segment.
+    fn event_name(&self) -> &'static str;
+
+    /// Will be called every time an event has been used twice before segment flushed its buffer.
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self>
+    where
+        Self: Sized;
+
+    /// Converts your structure to the final event that'll be sent to segment.
+    fn into_event(self: Box<Self>) -> serde_json::Value;
+}
+
+mopafy!(Aggregate);
+
+/// Helper trait to define multiple aggregates with the same content but a different name.
+/// Commonly used when you must aggregate a search with POST or with GET, for example.
+pub trait AggregateMethod: 'static + Default + Send {
+    fn event_name() -> &'static str;
+}
+
+/// A macro used to quickly define multiple aggregate method with their name
+/// Usage:
+/// ```rust
+/// use meilisearch::aggregate_methods;
+///
+/// aggregate_methods!(
+///     SearchGET => "Documents Searched GET",
+///     SearchPOST => "Documents Searched POST",
+/// );
+/// ```
+#[macro_export]
+macro_rules! aggregate_methods {
+    ($method:ident => $event_name:literal) => {
+        #[derive(Default)]
+        pub struct $method {}
+
+        impl $crate::analytics::AggregateMethod for $method {
+            fn event_name() -> &'static str {
+                $event_name
+            }
+        }
+    };
+    ($($method:ident => $event_name:literal,)+) => {
+        $(
+            aggregate_methods!($method => $event_name);
+        )+
+
+    };
+}
+
+#[derive(Clone)]
+pub struct Analytics {
+    segment: Option<Arc<SegmentAnalytics>>,
+}
+
+impl Analytics {
+    pub async fn new(
+        opt: &Opt,
+        index_scheduler: Arc<IndexScheduler>,
+        auth_controller: Arc<AuthController>,
+    ) -> Self {
+        if opt.no_analytics {
+            Self { segment: None }
+        } else {
+            Self { segment: SegmentAnalytics::new(opt, index_scheduler, auth_controller).await }
+        }
+    }
+
+    pub fn no_analytics() -> Self {
+        Self { segment: None }
+    }
+
+    pub fn instance_uid(&self) -> Option<&InstanceUid> {
+        self.segment.as_ref().map(|segment| segment.instance_uid.as_ref())
+    }
 
     /// The method used to publish most analytics that do not need to be batched every hours
-    fn publish(&self, event_name: String, send: Value, request: Option<&HttpRequest>);
+    pub fn publish<T: Aggregate>(&self, event: T, request: &HttpRequest) {
-
+        if let Some(ref segment) = self.segment {
-    /// This method should be called to aggregate a get search
+            let _ = segment.sender.try_send(segment_analytics::Message::new(event, request));
-    fn get_search(&self, aggregate: SearchAggregator);
+        }
-
+    }
-    /// This method should be called to aggregate a post search
-    fn post_search(&self, aggregate: SearchAggregator);
-
-    /// This method should be called to aggregate a get similar request
-    fn get_similar(&self, aggregate: SimilarAggregator);
-
-    /// This method should be called to aggregate a post similar request
-    fn post_similar(&self, aggregate: SimilarAggregator);
-
-    /// This method should be called to aggregate a post array of searches
-    fn post_multi_search(&self, aggregate: MultiSearchAggregator);
-
-    /// This method should be called to aggregate post facet values searches
-    fn post_facet_search(&self, aggregate: FacetSearchAggregator);
-
-    // this method should be called to aggregate an add documents request
-    fn add_documents(
-        &self,
-        documents_query: &UpdateDocumentsQuery,
-        index_creation: bool,
-        request: &HttpRequest,
-    );
-
-    // this method should be called to aggregate a fetch documents request
-    fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
-
-    // this method should be called to aggregate a fetch documents request
-    fn post_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
-
-    // this method should be called to aggregate a add documents request
-    fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest);
-
-    // this method should be called to batch an update documents request
-    fn update_documents(
-        &self,
-        documents_query: &UpdateDocumentsQuery,
-        index_creation: bool,
-        request: &HttpRequest,
-    );
-
-    // this method should be called to batch an update documents by function request
-    fn update_documents_by_function(
-        &self,
-        documents_query: &DocumentEditionByFunction,
-        index_creation: bool,
-        request: &HttpRequest,
-    );
 }

meilisearch/src/lib.rs

@@ -120,7 +120,7 @@ pub fn create_app(
     search_queue: Data<SearchQueue>,
     opt: Opt,
     logs: (LogRouteHandle, LogStderrHandle),
-    analytics: Arc<dyn Analytics>,
+    analytics: Data<Analytics>,
     enable_dashboard: bool,
 ) -> actix_web::App<
     impl ServiceFactory<
@@ -473,14 +473,14 @@ pub fn configure_data(
     search_queue: Data<SearchQueue>,
     opt: &Opt,
     (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
-    analytics: Arc<dyn Analytics>,
+    analytics: Data<Analytics>,
 ) {
     let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize;
     config
         .app_data(index_scheduler)
         .app_data(auth)
         .app_data(search_queue)
-        .app_data(web::Data::from(analytics))
+        .app_data(analytics)
         .app_data(web::Data::new(logs_route))
         .app_data(web::Data::new(logs_stderr))
         .app_data(web::Data::new(opt.clone()))

meilisearch/src/main.rs

@@ -124,19 +124,12 @@ async fn try_main() -> anyhow::Result<()> {
 
     let (index_scheduler, auth_controller) = setup_meilisearch(&opt)?;
 
-    #[cfg(all(not(debug_assertions), feature = "analytics"))]
+    let analytics =
-    let analytics = if !opt.no_analytics {
+        analytics::Analytics::new(&opt, index_scheduler.clone(), auth_controller.clone()).await;
-        analytics::SegmentAnalytics::new(&opt, index_scheduler.clone(), auth_controller.clone())
-            .await
-    } else {
-        analytics::MockAnalytics::new(&opt)
-    };
-    #[cfg(any(debug_assertions, not(feature = "analytics")))]
-    let analytics = analytics::MockAnalytics::new(&opt);
 
     print_launch_resume(&opt, analytics.clone(), config_read_from);
 
-    run_http(index_scheduler, auth_controller, opt, log_handle, analytics).await?;
+    run_http(index_scheduler, auth_controller, opt, log_handle, Arc::new(analytics)).await?;
 
     Ok(())
 }
@@ -146,12 +139,13 @@ async fn run_http(
     auth_controller: Arc<AuthController>,
     opt: Opt,
     logs: (LogRouteHandle, LogStderrHandle),
-    analytics: Arc<dyn Analytics>,
+    analytics: Arc<Analytics>,
 ) -> anyhow::Result<()> {
     let enable_dashboard = &opt.env == "development";
     let opt_clone = opt.clone();
     let index_scheduler = Data::from(index_scheduler);
     let auth_controller = Data::from(auth_controller);
+    let analytics = Data::from(analytics);
     let search_queue = SearchQueue::new(
         opt.experimental_search_queue_size,
         available_parallelism()
@@ -187,11 +181,7 @@ async fn run_http(
     Ok(())
 }
 
-pub fn print_launch_resume(
+pub fn print_launch_resume(opt: &Opt, analytics: Analytics, config_read_from: Option<PathBuf>) {
-    opt: &Opt,
-    analytics: Arc<dyn Analytics>,
-    config_read_from: Option<PathBuf>,
-) {
     let build_info = build_info::BuildInfo::from_build();
 
     let protocol =
@@ -233,7 +223,6 @@ pub fn print_launch_resume(
         eprintln!("Prototype:\t\t{:?}", prototype);
     }
 
-    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     {
         if !opt.no_analytics {
             eprintln!(

meilisearch/src/option.rs

@@ -29,7 +29,6 @@ const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
 const MEILI_TASK_WEBHOOK_URL: &str = "MEILI_TASK_WEBHOOK_URL";
 const MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER: &str = "MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER";
-#[cfg(feature = "analytics")]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
 const MEILI_SSL_CERT_PATH: &str = "MEILI_SSL_CERT_PATH";
@@ -210,7 +209,6 @@ pub struct Opt {
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
     /// All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted
     /// at any time.
-    #[cfg(feature = "analytics")]
     #[serde(default)] // we can't send true
     #[clap(long, env = MEILI_NO_ANALYTICS)]
     pub no_analytics: bool,
@@ -425,7 +423,6 @@ pub struct Opt {
 
 impl Opt {
     /// Whether analytics should be enabled or not.
-    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     pub fn analytics(&self) -> bool {
         !self.no_analytics
     }
@@ -505,7 +502,6 @@ impl Opt {
             ignore_missing_dump: _,
             ignore_dump_if_db_exists: _,
             config_file_path: _,
-            #[cfg(feature = "analytics")]
             no_analytics,
             experimental_contains_filter,
             experimental_enable_metrics,
@@ -533,10 +529,7 @@ impl Opt {
             );
         }
 
-        #[cfg(feature = "analytics")]
-        {
         export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
-        }
         export_to_env_if_not_present(
             MEILI_HTTP_PAYLOAD_SIZE_LIMIT,
             http_payload_size_limit.to_string(),

meilisearch/src/routes/dump.rs

@@ -4,7 +4,6 @@ use index_scheduler::IndexScheduler;
 use meilisearch_auth::AuthController;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
 use tracing::debug;
 
 use crate::analytics::Analytics;
@@ -18,14 +17,16 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(create_dump))));
 }
 
+crate::empty_analytics!(DumpAnalytics, "Dump Created");
+
 pub async fn create_dump(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, Data<IndexScheduler>>,
     auth_controller: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, Data<AuthController>>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Dump Created".to_string(), json!({}), Some(&req));
+    analytics.publish(DumpAnalytics::default(), &req);
 
     let task = KindWithContent::DumpCreation {
         keys: auth_controller.list_keys()?,

meilisearch/src/routes/features.rs

@@ -6,10 +6,10 @@ use index_scheduler::IndexScheduler;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::keys::actions;
-use serde_json::json;
+use serde::Serialize;
 use tracing::debug;
 
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, Analytics};
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
@@ -17,7 +17,7 @@ use crate::extractors::sequential_extractor::SeqHandler;
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
         web::resource("")
-            .route(web::get().to(SeqHandler(get_features)))
+            .route(web::get().to(get_features))
             .route(web::patch().to(SeqHandler(patch_features))),
     );
 }
@@ -27,12 +27,9 @@ async fn get_features(
         ActionPolicy<{ actions::EXPERIMENTAL_FEATURES_GET }>,
         Data<IndexScheduler>,
     >,
-    req: HttpRequest,
-    analytics: Data<dyn Analytics>,
 ) -> HttpResponse {
     let features = index_scheduler.features();
 
-    analytics.publish("Experimental features Seen".to_string(), json!(null), Some(&req));
     let features = features.runtime_features();
     debug!(returns = ?features, "Get features");
     HttpResponse::Ok().json(features)
@@ -53,6 +50,35 @@ pub struct RuntimeTogglableFeatures {
     pub contains_filter: Option<bool>,
 }
 
+#[derive(Serialize)]
+pub struct PatchExperimentalFeatureAnalytics {
+    vector_store: bool,
+    metrics: bool,
+    logs_route: bool,
+    edit_documents_by_function: bool,
+    contains_filter: bool,
+}
+
+impl Aggregate for PatchExperimentalFeatureAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Experimental features Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            vector_store: new.vector_store,
+            metrics: new.metrics,
+            logs_route: new.logs_route,
+            edit_documents_by_function: new.edit_documents_by_function,
+            contains_filter: new.contains_filter,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 async fn patch_features(
     index_scheduler: GuardedData<
         ActionPolicy<{ actions::EXPERIMENTAL_FEATURES_UPDATE }>,
@@ -60,7 +86,7 @@ async fn patch_features(
     >,
     new_features: AwebJson<RuntimeTogglableFeatures, DeserrJsonError>,
     req: HttpRequest,
-    analytics: Data<dyn Analytics>,
+    analytics: Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let features = index_scheduler.features();
     debug!(parameters = ?new_features, "Patch features");
@@ -89,15 +115,14 @@ async fn patch_features(
     } = new_features;
 
     analytics.publish(
-        "Experimental features Updated".to_string(),
+        PatchExperimentalFeatureAnalytics {
-        json!({
+            vector_store,
-            "vector_store": vector_store,
+            metrics,
-            "metrics": metrics,
+            logs_route,
-            "logs_route": logs_route,
+            edit_documents_by_function,
-            "edit_documents_by_function": edit_documents_by_function,
+            contains_filter,
-            "contains_filter": contains_filter,
+        },
-        }),
+        &req,
-        Some(&req),
     );
     index_scheduler.put_runtime_features(new_features)?;
     debug!(returns = ?new_features, "Patch features");

meilisearch/src/routes/indexes/documents.rs

@@ -1,4 +1,6 @@
+use std::collections::HashSet;
 use std::io::ErrorKind;
+use std::marker::PhantomData;
 
 use actix_web::http::header::CONTENT_TYPE;
 use actix_web::web::Data;
@@ -23,14 +25,14 @@ use meilisearch_types::tasks::KindWithContent;
 use meilisearch_types::{milli, Document, Index};
 use mime::Mime;
 use once_cell::sync::Lazy;
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 use serde_json::Value;
 use tempfile::tempfile;
 use tokio::fs::File;
 use tokio::io::{AsyncSeekExt, AsyncWriteExt, BufWriter};
 use tracing::debug;
 
-use crate::analytics::{Analytics, DocumentDeletionKind, DocumentFetchKind};
+use crate::analytics::{Aggregate, AggregateMethod, Analytics};
 use crate::error::MeilisearchHttpError;
 use crate::error::PayloadError::ReceivePayload;
 use crate::extractors::authentication::policies::*;
@@ -41,7 +43,7 @@ use crate::routes::{
     get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
 };
 use crate::search::{parse_filter, RetrieveVectors};
-use crate::Opt;
+use crate::{aggregate_methods, Opt};
 
 static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
     vec!["application/json".to_string(), "application/x-ndjson".to_string(), "text/csv".to_string()]
@@ -100,12 +102,84 @@ pub struct GetDocument {
     retrieve_vectors: Param<bool>,
 }
 
+aggregate_methods!(
+    DocumentsGET => "Documents Fetched GET",
+    DocumentsPOST => "Documents Fetched POST",
+);
+
+#[derive(Serialize)]
+pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
+    // a call on ../documents/:doc_id
+    per_document_id: bool,
+    // if a filter was used
+    per_filter: bool,
+
+    #[serde(rename = "vector.retrieve_vectors")]
+    retrieve_vectors: bool,
+
+    // pagination
+    #[serde(rename = "pagination.max_limit")]
+    max_limit: usize,
+    #[serde(rename = "pagination.max_offset")]
+    max_offset: usize,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+#[derive(Copy, Clone, Debug, PartialEq, Eq)]
+pub enum DocumentFetchKind {
+    PerDocumentId { retrieve_vectors: bool },
+    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
+}
+
+impl<Method: AggregateMethod> DocumentsFetchAggregator<Method> {
+    pub fn from_query(query: &DocumentFetchKind) -> Self {
+        let (limit, offset, retrieve_vectors) = match query {
+            DocumentFetchKind::PerDocumentId { retrieve_vectors } => (1, 0, *retrieve_vectors),
+            DocumentFetchKind::Normal { limit, offset, retrieve_vectors, .. } => {
+                (*limit, *offset, *retrieve_vectors)
+            }
+        };
+
+        Self {
+            per_document_id: matches!(query, DocumentFetchKind::PerDocumentId { .. }),
+            per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
+            max_limit: limit,
+            max_offset: offset,
+            retrieve_vectors,
+
+            marker: PhantomData,
+        }
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for DocumentsFetchAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            per_document_id: self.per_document_id | new.per_document_id,
+            per_filter: self.per_filter | new.per_filter,
+            retrieve_vectors: self.retrieve_vectors | new.retrieve_vectors,
+            max_limit: self.max_limit.max(new.max_limit),
+            max_offset: self.max_offset.max(new.max_offset),
+            marker: PhantomData,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn get_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
     document_param: web::Path<DocumentParam>,
     params: AwebQueryParameter<GetDocument, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = document_param.into_inner();
     debug!(parameters = ?params, "Get document");
@@ -117,8 +191,15 @@ pub async fn get_document(
     let features = index_scheduler.features();
     let retrieve_vectors = RetrieveVectors::new(param_retrieve_vectors.0, features)?;
 
-    analytics.get_fetch_documents(
+    analytics.publish(
-        &DocumentFetchKind::PerDocumentId { retrieve_vectors: param_retrieve_vectors.0 },
+        DocumentsFetchAggregator::<DocumentsGET> {
+            retrieve_vectors: param_retrieve_vectors.0,
+            per_document_id: true,
+            per_filter: false,
+            max_limit: 0,
+            max_offset: 0,
+            marker: PhantomData,
+        },
         &req,
     );
 
@@ -129,17 +210,52 @@ pub async fn get_document(
     Ok(HttpResponse::Ok().json(document))
 }
 
+#[derive(Serialize)]
+pub struct DocumentsDeletionAggregator {
+    per_document_id: bool,
+    clear_all: bool,
+    per_batch: bool,
+    per_filter: bool,
+}
+
+impl Aggregate for DocumentsDeletionAggregator {
+    fn event_name(&self) -> &'static str {
+        "Documents Deleted"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            per_document_id: self.per_document_id | new.per_document_id,
+            clear_all: self.clear_all | new.clear_all,
+            per_batch: self.per_batch | new.per_batch,
+            per_filter: self.per_filter | new.per_filter,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn delete_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     path: web::Path<DocumentParam>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = path.into_inner();
     let index_uid = IndexUid::try_from(index_uid)?;
 
-    analytics.delete_documents(DocumentDeletionKind::PerDocumentId, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            per_document_id: true,
+            clear_all: false,
+            per_batch: false,
+            per_filter: false,
+        },
+        &req,
+    );
 
     let task = KindWithContent::DocumentDeletion {
         index_uid: index_uid.to_string(),
@@ -190,17 +306,19 @@ pub async fn documents_by_query_post(
     index_uid: web::Path<String>,
     body: AwebJson<BrowseQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let body = body.into_inner();
     debug!(parameters = ?body, "Get documents POST");
 
-    analytics.post_fetch_documents(
+    analytics.publish(
-        &DocumentFetchKind::Normal {
+        DocumentsFetchAggregator::<DocumentsPOST> {
-            with_filter: body.filter.is_some(),
+            per_filter: body.filter.is_some(),
-            limit: body.limit,
-            offset: body.offset,
             retrieve_vectors: body.retrieve_vectors,
+            max_limit: body.limit,
+            max_offset: body.offset,
+            per_document_id: false,
+            marker: PhantomData,
         },
         &req,
     );
@@ -213,7 +331,7 @@ pub async fn get_documents(
     index_uid: web::Path<String>,
     params: AwebQueryParameter<BrowseQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Get documents GET");
 
@@ -235,12 +353,14 @@ pub async fn get_documents(
         filter,
     };
 
-    analytics.get_fetch_documents(
+    analytics.publish(
-        &DocumentFetchKind::Normal {
+        DocumentsFetchAggregator::<DocumentsGET> {
-            with_filter: query.filter.is_some(),
+            per_filter: query.filter.is_some(),
-            limit: query.limit,
-            offset: query.offset,
             retrieve_vectors: query.retrieve_vectors,
+            max_limit: query.limit,
+            max_offset: query.offset,
+            per_document_id: false,
+            marker: PhantomData,
         },
         &req,
     );
@@ -298,6 +418,39 @@ fn from_char_csv_delimiter(
     }
 }
 
+aggregate_methods!(
+    Replaced => "Documents Added",
+    Updated => "Documents Updated",
+);
+
+#[derive(Serialize)]
+pub struct DocumentsAggregator<T: AggregateMethod> {
+    payload_types: HashSet<String>,
+    primary_key: HashSet<String>,
+    index_creation: bool,
+    #[serde(skip)]
+    method: PhantomData<T>,
+}
+
+impl<Method: AggregateMethod> Aggregate for DocumentsAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            payload_types: self.payload_types.union(&new.payload_types).cloned().collect(),
+            primary_key: self.primary_key.union(&new.primary_key).cloned().collect(),
+            index_creation: self.index_creation | new.index_creation,
+            method: PhantomData,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(self).unwrap_or_default()
+    }
+}
+
 pub async fn replace_documents(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ADD }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
@@ -305,16 +458,32 @@ pub async fn replace_documents(
     body: Payload,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     debug!(parameters = ?params, "Replace documents");
     let params = params.into_inner();
 
-    analytics.add_documents(
+    let mut content_types = HashSet::new();
-        &params,
+    let content_type = req
-        index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+        .headers()
+        .get(CONTENT_TYPE)
+        .and_then(|s| s.to_str().ok())
+        .unwrap_or("unknown")
+        .to_string();
+    content_types.insert(content_type);
+    let mut primary_keys = HashSet::new();
+    if let Some(primary_key) = params.primary_key.clone() {
+        primary_keys.insert(primary_key);
+    }
+    analytics.publish(
+        DocumentsAggregator::<Replaced> {
+            payload_types: content_types,
+            primary_key: primary_keys,
+            index_creation: index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+            method: PhantomData,
+        },
         &req,
     );
 
@@ -346,16 +515,32 @@ pub async fn update_documents(
     body: Payload,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let params = params.into_inner();
     debug!(parameters = ?params, "Update documents");
 
-    analytics.add_documents(
+    let mut content_types = HashSet::new();
-        &params,
+    let content_type = req
-        index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+        .headers()
+        .get(CONTENT_TYPE)
+        .and_then(|s| s.to_str().ok())
+        .unwrap_or("unknown")
+        .to_string();
+    content_types.insert(content_type);
+    let mut primary_keys = HashSet::new();
+    if let Some(primary_key) = params.primary_key.clone() {
+        primary_keys.insert(primary_key);
+    }
+    analytics.publish(
+        DocumentsAggregator::<Updated> {
+            payload_types: content_types,
+            primary_key: primary_keys,
+            index_creation: index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+            method: PhantomData,
+        },
         &req,
     );
 
@@ -524,12 +709,20 @@ pub async fn delete_documents_batch(
     body: web::Json<Vec<Value>>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Delete documents by batch");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
-    analytics.delete_documents(DocumentDeletionKind::PerBatch, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            per_batch: true,
+            per_document_id: false,
+            clear_all: false,
+            per_filter: false,
+        },
+        &req,
+    );
 
     let ids = body
         .iter()
@@ -562,14 +755,22 @@ pub async fn delete_documents_by_filter(
     body: AwebJson<DocumentDeletionByFilter, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Delete documents by filter");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let index_uid = index_uid.into_inner();
     let filter = body.into_inner().filter;
 
-    analytics.delete_documents(DocumentDeletionKind::PerFilter, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            per_filter: true,
+            per_document_id: false,
+            clear_all: false,
+            per_batch: false,
+        },
+        &req,
+    );
 
     // we ensure the filter is well formed before enqueuing it
     crate::search::parse_filter(&filter, Code::InvalidDocumentFilter, index_scheduler.features())?
@@ -599,13 +800,41 @@ pub struct DocumentEditionByFunction {
     pub function: String,
 }
 
+#[derive(Serialize)]
+struct EditDocumentsByFunctionAggregator {
+    // Set to true if at least one request was filtered
+    filtered: bool,
+    // Set to true if at least one request contained a context
+    with_context: bool,
+
+    index_creation: bool,
+}
+
+impl Aggregate for EditDocumentsByFunctionAggregator {
+    fn event_name(&self) -> &'static str {
+        "Documents Edited By Function"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            filtered: self.filtered | new.filtered,
+            with_context: self.with_context | new.with_context,
+            index_creation: self.index_creation | new.index_creation,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn edit_documents_by_function(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ALL }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     params: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Edit documents by function");
 
@@ -617,9 +846,12 @@ pub async fn edit_documents_by_function(
     let index_uid = index_uid.into_inner();
     let params = params.into_inner();
 
-    analytics.update_documents_by_function(
+    analytics.publish(
-        &params,
+        EditDocumentsByFunctionAggregator {
-        index_scheduler.index(&index_uid).is_err(),
+            filtered: params.filter.is_some(),
+            with_context: params.context.is_some(),
+            index_creation: index_scheduler.index(&index_uid).is_err(),
+        },
         &req,
     );
 
@@ -670,10 +902,18 @@ pub async fn clear_all_documents(
     index_uid: web::Path<String>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-    analytics.delete_documents(DocumentDeletionKind::ClearAll, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            clear_all: true,
+            per_document_id: false,
+            per_batch: false,
+            per_filter: false,
+        },
+        &req,
+    );
 
     let task = KindWithContent::DocumentClear { index_uid: index_uid.to_string() };
     let uid = get_task_id(&req, &opt)?;

meilisearch/src/routes/indexes/facet_search.rs

@@ -1,3 +1,5 @@
+use std::collections::{BinaryHeap, HashSet};
+
 use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::AwebJson;
@@ -10,14 +12,15 @@ use meilisearch_types::locales::Locale;
 use serde_json::Value;
 use tracing::debug;
 
-use crate::analytics::{Analytics, FacetSearchAggregator};
+use crate::analytics::{Aggregate, Analytics};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::routes::indexes::search::search_kind;
 use crate::search::{
-    add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
+    add_search_rules, perform_facet_search, FacetSearchResult, HybridQuery, MatchingStrategy,
-    SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    RankingScoreThreshold, SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_SEARCH_OFFSET,
 };
 use crate::search_queue::SearchQueue;
 
@@ -53,20 +56,122 @@ pub struct FacetSearchQuery {
     pub locales: Option<Vec<Locale>>,
 }
 
+#[derive(Default)]
+pub struct FacetSearchAggregator {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // The set of all facetNames that were used
+    facet_names: HashSet<String>,
+
+    // As there been any other parameter than the facetName or facetQuery ones?
+    additional_search_parameters_provided: bool,
+}
+
+impl FacetSearchAggregator {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &FacetSearchQuery) -> Self {
+        let FacetSearchQuery {
+            facet_query: _,
+            facet_name,
+            vector,
+            q,
+            filter,
+            matching_strategy,
+            attributes_to_search_on,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = query;
+
+        Self {
+            total_received: 1,
+            facet_names: Some(facet_name.clone()).into_iter().collect(),
+            additional_search_parameters_provided: q.is_some()
+                || vector.is_some()
+                || filter.is_some()
+                || *matching_strategy != MatchingStrategy::default()
+                || attributes_to_search_on.is_some()
+                || hybrid.is_some()
+                || ranking_score_threshold.is_some()
+                || locales.is_some(),
+            ..Default::default()
+        }
+    }
+
+    pub fn succeed(&mut self, result: &FacetSearchResult) {
+        let FacetSearchResult { facet_hits: _, facet_query: _, processing_time_ms } = result;
+        self.total_succeeded = 1;
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl Aggregate for FacetSearchAggregator {
+    fn event_name(&self) -> &'static str {
+        "Facet Searched POST"
+    }
+
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        for time in new.time_spent {
+            self.time_spent.push(time);
+        }
+
+        Box::new(Self {
+            total_received: self.total_received.saturating_add(new.total_received),
+            total_succeeded: self.total_succeeded.saturating_add(new.total_succeeded),
+            time_spent: self.time_spent,
+            facet_names: self.facet_names.union(&new.facet_names).cloned().collect(),
+            additional_search_parameters_provided: self.additional_search_parameters_provided
+                | new.additional_search_parameters_provided,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            facet_names,
+            additional_search_parameters_provided,
+        } = *self;
+        // the index of the 99th percentage of value
+        let percentile_99th = 0.99 * (total_succeeded as f64 - 1.) + 1.;
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th as usize);
+
+        serde_json::json!({
+            "requests": {
+                "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "facets": {
+                "total_distinct_facet_count": facet_names.len(),
+                "additional_search_parameters_provided": additional_search_parameters_provided,
+            },
+        })
+    }
+}
+
 pub async fn search(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
     search_queue: Data<SearchQueue>,
     index_uid: web::Path<String>,
     params: AwebJson<FacetSearchQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.into_inner();
     debug!(parameters = ?query, "Facet search");
 
-    let mut aggregate = FacetSearchAggregator::from_query(&query, &req);
+    let mut aggregate = FacetSearchAggregator::from_query(&query);
 
     let facet_query = query.facet_query.clone();
     let facet_name = query.facet_name.clone();
@@ -100,7 +205,7 @@ pub async fn search(
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
-    analytics.post_facet_search(aggregate);
+    analytics.publish(aggregate, &req);
 
     let search_result = search_result?;
 

meilisearch/src/routes/indexes/mod.rs

@@ -1,3 +1,4 @@
+use std::collections::BTreeSet;
 use std::convert::Infallible;
 
 use actix_web::web::Data;
@@ -13,12 +14,11 @@ use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::{self, FieldDistribution, Index};
 use meilisearch_types::tasks::KindWithContent;
 use serde::Serialize;
-use serde_json::json;
 use time::OffsetDateTime;
 use tracing::debug;
 
 use super::{get_task_id, Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, Analytics};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
@@ -28,8 +28,11 @@ use crate::Opt;
 pub mod documents;
 pub mod facet_search;
 pub mod search;
+mod search_analytics;
 pub mod settings;
+mod settings_analytics;
 pub mod similar;
+mod similar_analytics;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -123,12 +126,31 @@ pub struct IndexCreateRequest {
     primary_key: Option<String>,
 }
 
+#[derive(Serialize)]
+struct IndexCreatedAggregate {
+    primary_key: BTreeSet<String>,
+}
+
+impl Aggregate for IndexCreatedAggregate {
+    fn event_name(&self) -> &'static str {
+        "Index Created"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self { primary_key: self.primary_key.union(&new.primary_key).cloned().collect() })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn create_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_CREATE }>, Data<IndexScheduler>>,
     body: AwebJson<IndexCreateRequest, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Create index");
     let IndexCreateRequest { primary_key, uid } = body.into_inner();
@@ -136,9 +158,8 @@ pub async fn create_index(
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&uid);
     if allow_index_creation {
         analytics.publish(
-            "Index Created".to_string(),
+            IndexCreatedAggregate { primary_key: primary_key.iter().cloned().collect() },
-            json!({ "primary_key": primary_key }),
+            &req,
-            Some(&req),
         );
 
         let task = KindWithContent::IndexCreation { index_uid: uid.to_string(), primary_key };
@@ -194,21 +215,38 @@ pub async fn get_index(
     Ok(HttpResponse::Ok().json(index_view))
 }
 
+#[derive(Serialize)]
+struct IndexUpdatedAggregate {
+    primary_key: BTreeSet<String>,
+}
+
+impl Aggregate for IndexUpdatedAggregate {
+    fn event_name(&self) -> &'static str {
+        "Index Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self { primary_key: self.primary_key.union(&new.primary_key).cloned().collect() })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
 pub async fn update_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_UPDATE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     body: AwebJson<UpdateIndexRequest, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Update index");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let body = body.into_inner();
     analytics.publish(
-        "Index Updated".to_string(),
+        IndexUpdatedAggregate { primary_key: body.primary_key.iter().cloned().collect() },
-        json!({ "primary_key": body.primary_key }),
+        &req,
-        Some(&req),
     );
 
     let task = KindWithContent::IndexUpdate {

meilisearch/src/routes/indexes/search.rs

@@ -13,12 +13,13 @@ use meilisearch_types::serde_cs::vec::CS;
 use serde_json::Value;
 use tracing::debug;
 
-use crate::analytics::{Analytics, SearchAggregator};
+use crate::analytics::Analytics;
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
+use crate::routes::indexes::search_analytics::{SearchAggregator, SearchGET, SearchPOST};
 use crate::search::{
     add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
     RetrieveVectors, SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH,
@@ -225,7 +226,7 @@ pub async fn search_with_url_query(
     index_uid: web::Path<String>,
     params: AwebQueryParameter<SearchQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Search get");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
@@ -237,7 +238,7 @@ pub async fn search_with_url_query(
         add_search_rules(&mut query.filter, search_rules);
     }
 
-    let mut aggregate = SearchAggregator::from_query(&query, &req);
+    let mut aggregate = SearchAggregator::<SearchGET>::from_query(&query);
 
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
@@ -254,7 +255,7 @@ pub async fn search_with_url_query(
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
-    analytics.get_search(aggregate);
+    analytics.publish(aggregate, &req);
 
     let search_result = search_result?;
 
@@ -268,7 +269,7 @@ pub async fn search_with_post(
     index_uid: web::Path<String>,
     params: AwebJson<SearchQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -280,7 +281,7 @@ pub async fn search_with_post(
         add_search_rules(&mut query.filter, search_rules);
     }
 
-    let mut aggregate = SearchAggregator::from_query(&query, &req);
+    let mut aggregate = SearchAggregator::<SearchPOST>::from_query(&query);
 
     let index = index_scheduler.index(&index_uid)?;
 
@@ -302,7 +303,7 @@ pub async fn search_with_post(
             MEILISEARCH_DEGRADED_SEARCH_REQUESTS.inc();
         }
     }
-    analytics.post_search(aggregate);
+    analytics.publish(aggregate, &req);
 
     let search_result = search_result?;
 

meilisearch/src/routes/indexes/search_analytics.rs

@@ -0,0 +1,485 @@
+use once_cell::sync::Lazy;
+use regex::Regex;
+use serde_json::{json, Value};
+use std::collections::{BTreeSet, BinaryHeap, HashMap};
+
+use meilisearch_types::locales::Locale;
+
+use crate::{
+    aggregate_methods,
+    analytics::{Aggregate, AggregateMethod},
+    search::{
+        SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+        DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+        DEFAULT_SEMANTIC_RATIO,
+    },
+};
+
+aggregate_methods!(
+    SearchGET => "Documents Searched GET",
+    SearchPOST => "Documents Searched POST",
+);
+
+#[derive(Default)]
+pub struct SearchAggregator<Method: AggregateMethod> {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    total_degraded: usize,
+    total_used_negative_operator: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // sort
+    sort_with_geo_point: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    sort_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    sort_total_number_of_criteria: usize,
+
+    // distinct
+    distinct: bool,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // attributes_to_search_on
+    // every time a search is done using attributes_to_search_on
+    attributes_to_search_on_total_number_of_uses: usize,
+
+    // q
+    // The maximum number of terms in a q request
+    max_terms_number: usize,
+
+    // vector
+    // The maximum number of floats in a vector request
+    max_vector_size: usize,
+    // Whether the semantic ratio passed to a hybrid search equals the default ratio.
+    semantic_ratio: bool,
+    hybrid: bool,
+    retrieve_vectors: bool,
+
+    // every time a search is done, we increment the counter linked to the used settings
+    matching_strategy: HashMap<String, usize>,
+
+    // List of the unique Locales passed as parameter
+    locales: BTreeSet<Locale>,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+    finite_pagination: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+    max_attributes_to_highlight: usize,
+    highlight_pre_tag: bool,
+    highlight_post_tag: bool,
+    max_attributes_to_crop: usize,
+    crop_marker: bool,
+    show_matches_position: bool,
+    crop_length: bool,
+
+    // facets
+    facets_sum_of_terms: usize,
+    facets_total_number_of_facets: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod> SearchAggregator<Method> {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SearchQuery) -> Self {
+        let SearchQuery {
+            q,
+            vector,
+            offset,
+            limit,
+            page,
+            hits_per_page,
+            attributes_to_retrieve: _,
+            retrieve_vectors,
+            attributes_to_crop: _,
+            crop_length,
+            attributes_to_highlight: _,
+            show_matches_position,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            sort,
+            distinct,
+            facets: _,
+            highlight_pre_tag,
+            highlight_post_tag,
+            crop_marker,
+            matching_strategy,
+            attributes_to_search_on,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = query;
+
+        let mut ret = Self::default();
+
+        ret.total_received = 1;
+
+        if let Some(ref sort) = sort {
+            ret.sort_total_number_of_criteria = 1;
+            ret.sort_with_geo_point = sort.iter().any(|s| s.contains("_geoPoint("));
+            ret.sort_sum_of_criteria_terms = sort.len();
+        }
+
+        ret.distinct = distinct.is_some();
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        // attributes_to_search_on
+        if attributes_to_search_on.is_some() {
+            ret.attributes_to_search_on_total_number_of_uses = 1;
+        }
+
+        if let Some(ref q) = q {
+            ret.max_terms_number = q.split_whitespace().count();
+        }
+
+        if let Some(ref vector) = vector {
+            ret.max_vector_size = vector.len();
+        }
+        ret.retrieve_vectors |= retrieve_vectors;
+
+        if query.is_finite_pagination() {
+            let limit = hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
+            ret.max_limit = limit;
+            ret.max_offset = page.unwrap_or(1).saturating_sub(1) * limit;
+            ret.finite_pagination = 1;
+        } else {
+            ret.max_limit = *limit;
+            ret.max_offset = *offset;
+            ret.finite_pagination = 0;
+        }
+
+        ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1);
+
+        if let Some(locales) = locales {
+            ret.locales = locales.iter().copied().collect();
+        }
+
+        ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
+        ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
+        ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
+        ret.crop_length = *crop_length != DEFAULT_CROP_LENGTH();
+        ret.show_matches_position = *show_matches_position;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        if let Some(hybrid) = hybrid {
+            ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
+            ret.hybrid = true;
+        }
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SearchResult) {
+        let SearchResult {
+            hits: _,
+            query: _,
+            processing_time_ms,
+            hits_info: _,
+            semantic_hit_count: _,
+            facet_distribution: _,
+            facet_stats: _,
+            degraded,
+            used_negative_operator,
+        } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+        if *degraded {
+            self.total_degraded = self.total_degraded.saturating_add(1);
+        }
+        if *used_negative_operator {
+            self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
+        }
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        let Self {
+            total_received,
+            total_succeeded,
+            mut time_spent,
+            sort_with_geo_point,
+            sort_sum_of_criteria_terms,
+            sort_total_number_of_criteria,
+            distinct,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            attributes_to_search_on_total_number_of_uses,
+            max_terms_number,
+            max_vector_size,
+            retrieve_vectors,
+            matching_strategy,
+            max_limit,
+            max_offset,
+            finite_pagination,
+            max_attributes_to_retrieve,
+            max_attributes_to_highlight,
+            highlight_pre_tag,
+            highlight_post_tag,
+            max_attributes_to_crop,
+            crop_marker,
+            show_matches_position,
+            crop_length,
+            facets_sum_of_terms,
+            facets_total_number_of_facets,
+            show_ranking_score,
+            show_ranking_score_details,
+            semantic_ratio,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
+            ranking_score_threshold,
+            mut locales,
+            marker: _,
+        } = *new;
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.total_degraded = self.total_degraded.saturating_add(total_degraded);
+        self.total_used_negative_operator =
+            self.total_used_negative_operator.saturating_add(total_used_negative_operator);
+        self.time_spent.append(&mut time_spent);
+
+        // sort
+        self.sort_with_geo_point |= sort_with_geo_point;
+        self.sort_sum_of_criteria_terms =
+            self.sort_sum_of_criteria_terms.saturating_add(sort_sum_of_criteria_terms);
+        self.sort_total_number_of_criteria =
+            self.sort_total_number_of_criteria.saturating_add(sort_total_number_of_criteria);
+
+        // distinct
+        self.distinct |= distinct;
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        // attributes_to_search_on
+        self.attributes_to_search_on_total_number_of_uses = self
+            .attributes_to_search_on_total_number_of_uses
+            .saturating_add(attributes_to_search_on_total_number_of_uses);
+
+        // q
+        self.max_terms_number = self.max_terms_number.max(max_terms_number);
+
+        // vector
+        self.max_vector_size = self.max_vector_size.max(max_vector_size);
+        self.retrieve_vectors |= retrieve_vectors;
+        self.semantic_ratio |= semantic_ratio;
+        self.hybrid |= hybrid;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+        self.finite_pagination += finite_pagination;
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+        self.max_attributes_to_highlight =
+            self.max_attributes_to_highlight.max(max_attributes_to_highlight);
+        self.highlight_pre_tag |= highlight_pre_tag;
+        self.highlight_post_tag |= highlight_post_tag;
+        self.max_attributes_to_crop = self.max_attributes_to_crop.max(max_attributes_to_crop);
+        self.crop_marker |= crop_marker;
+        self.show_matches_position |= show_matches_position;
+        self.crop_length |= crop_length;
+
+        // facets
+        self.facets_sum_of_terms = self.facets_sum_of_terms.saturating_add(facets_sum_of_terms);
+        self.facets_total_number_of_facets =
+            self.facets_total_number_of_facets.saturating_add(facets_total_number_of_facets);
+
+        // matching strategy
+        for (key, value) in matching_strategy.into_iter() {
+            let matching_strategy = self.matching_strategy.entry(key).or_insert(0);
+            *matching_strategy = matching_strategy.saturating_add(value);
+        }
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+
+        // locales
+        self.locales.append(&mut locales);
+
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            sort_with_geo_point,
+            sort_sum_of_criteria_terms,
+            sort_total_number_of_criteria,
+            distinct,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            attributes_to_search_on_total_number_of_uses,
+            max_terms_number,
+            max_vector_size,
+            retrieve_vectors,
+            matching_strategy,
+            max_limit,
+            max_offset,
+            finite_pagination,
+            max_attributes_to_retrieve,
+            max_attributes_to_highlight,
+            highlight_pre_tag,
+            highlight_post_tag,
+            max_attributes_to_crop,
+            crop_marker,
+            show_matches_position,
+            crop_length,
+            facets_sum_of_terms,
+            facets_total_number_of_facets,
+            show_ranking_score,
+            show_ranking_score_details,
+            semantic_ratio,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
+            ranking_score_threshold,
+            locales,
+            marker: _,
+        } = *self;
+
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // the index of the 99th percentage of value
+        let percentile_99th = time_spent.len() * 99 / 100;
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th);
+
+        json!({
+            "requests": {
+                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+                "total_degraded": total_degraded,
+                "total_used_negative_operator": total_used_negative_operator,
+            },
+            "sort": {
+                "with_geoPoint": sort_with_geo_point,
+                "avg_criteria_number": format!("{:.2}", sort_sum_of_criteria_terms as f64 / sort_total_number_of_criteria as f64),
+            },
+            "distinct": distinct,
+            "filter": {
+               "with_geoRadius": filter_with_geo_radius,
+               "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "attributes_to_search_on": {
+               "total_number_of_uses": attributes_to_search_on_total_number_of_uses,
+            },
+            "q": {
+               "max_terms_number": max_terms_number,
+            },
+            "vector": {
+                "max_vector_size": max_vector_size,
+                "retrieve_vectors": retrieve_vectors,
+            },
+            "hybrid": {
+                "enabled": hybrid,
+                "semantic_ratio": semantic_ratio,
+            },
+            "pagination": {
+               "max_limit": max_limit,
+               "max_offset": max_offset,
+               "most_used_navigation": if finite_pagination > (total_received / 2) { "exhaustive" } else { "estimated" },
+            },
+            "formatting": {
+                "max_attributes_to_retrieve": max_attributes_to_retrieve,
+                "max_attributes_to_highlight": max_attributes_to_highlight,
+                "highlight_pre_tag": highlight_pre_tag,
+                "highlight_post_tag": highlight_post_tag,
+                "max_attributes_to_crop": max_attributes_to_crop,
+                "crop_marker": crop_marker,
+                "show_matches_position": show_matches_position,
+                "crop_length": crop_length,
+            },
+            "facets": {
+                "avg_facets_number": format!("{:.2}", facets_sum_of_terms as f64 / facets_total_number_of_facets as f64),
+            },
+            "matching_strategy": {
+                "most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "locales": locales,
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+                "ranking_score_threshold": ranking_score_threshold,
+            },
+        })
+    }
+}

meilisearch/src/routes/indexes/settings.rs

@@ -1,15 +1,14 @@
+use super::settings_analytics::*;
 use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::AwebJson;
 use index_scheduler::IndexScheduler;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::ResponseError;
-use meilisearch_types::facet_values_sort::FacetValuesSort;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::update::Setting;
-use meilisearch_types::settings::{settings, RankingRuleView, SecretPolicy, Settings, Unchecked};
+use meilisearch_types::settings::{settings, SecretPolicy, Settings, Unchecked};
 use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
 use tracing::debug;
 
 use crate::analytics::Analytics;
@@ -20,7 +19,7 @@ use crate::Opt;
 
 #[macro_export]
 macro_rules! make_setting_route {
-    ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics_var:ident, $analytics:expr) => {
+    ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics:ident) => {
         pub mod $attr {
             use actix_web::web::Data;
             use actix_web::{web, HttpRequest, HttpResponse, Resource};
@@ -80,7 +79,7 @@ macro_rules! make_setting_route {
                 body: deserr::actix_web::AwebJson<Option<$type>, $err_ty>,
                 req: HttpRequest,
                 opt: web::Data<Opt>,
-                $analytics_var: web::Data<dyn Analytics>,
+                analytics: web::Data<Analytics>,
             ) -> std::result::Result<HttpResponse, ResponseError> {
                 let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -88,7 +87,10 @@ macro_rules! make_setting_route {
                 debug!(parameters = ?body, "Update settings");
 
                 #[allow(clippy::redundant_closure_call)]
-                $analytics(&body, &req);
+                analytics.publish(
+                    $crate::routes::indexes::settings_analytics::$analytics::new(body.as_ref()).into_settings(),
+                    &req,
+                );
 
                 let new_settings = Settings {
                     $attr: match body {
@@ -160,21 +162,7 @@ make_setting_route!(
     >,
     filterable_attributes,
     "filterableAttributes",
-    analytics,
+    FilterableAttributesAnalytics
-    |setting: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "FilterableAttributes Updated".to_string(),
-            json!({
-                "filterable_attributes": {
-                    "total": setting.as_ref().map(|filter| filter.len()).unwrap_or(0),
-                    "has_geo": setting.as_ref().map(|filter| filter.contains("_geo")).unwrap_or(false),
-                }
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -186,21 +174,7 @@ make_setting_route!(
     >,
     sortable_attributes,
     "sortableAttributes",
-    analytics,
+    SortableAttributesAnalytics
-    |setting: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "SortableAttributes Updated".to_string(),
-            json!({
-                "sortable_attributes": {
-                    "total": setting.as_ref().map(|sort| sort.len()),
-                    "has_geo": setting.as_ref().map(|sort| sort.contains("_geo")),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -212,21 +186,7 @@ make_setting_route!(
     >,
     displayed_attributes,
     "displayedAttributes",
-    analytics,
+    DisplayedAttributesAnalytics
-    |displayed: &Option<Vec<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "DisplayedAttributes Updated".to_string(),
-            json!({
-                "displayed_attributes": {
-                    "total": displayed.as_ref().map(|displayed| displayed.len()),
-                    "with_wildcard": displayed.as_ref().map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -238,40 +198,7 @@ make_setting_route!(
     >,
     typo_tolerance,
     "typoTolerance",
-    analytics,
+    TypoToleranceAnalytics
-    |setting: &Option<meilisearch_types::settings::TypoSettings>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "TypoTolerance Updated".to_string(),
-            json!({
-                "typo_tolerance": {
-                    "enabled": setting.as_ref().map(|s| !matches!(s.enabled, Setting::Set(false))),
-                    "disable_on_attributes": setting
-                        .as_ref()
-                        .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
-                    "disable_on_words": setting
-                        .as_ref()
-                        .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
-                    "min_word_size_for_one_typo": setting
-                        .as_ref()
-                        .and_then(|s| s.min_word_size_for_typos
-                            .as_ref()
-                            .set()
-                            .map(|s| s.one_typo.set()))
-                        .flatten(),
-                    "min_word_size_for_two_typos": setting
-                        .as_ref()
-                        .and_then(|s| s.min_word_size_for_typos
-                            .as_ref()
-                            .set()
-                            .map(|s| s.two_typos.set()))
-                        .flatten(),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -283,21 +210,7 @@ make_setting_route!(
     >,
     searchable_attributes,
     "searchableAttributes",
-    analytics,
+    SearchableAttributesAnalytics
-    |setting: &Option<Vec<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "SearchableAttributes Updated".to_string(),
-            json!({
-                "searchable_attributes": {
-                    "total": setting.as_ref().map(|searchable| searchable.len()),
-                    "with_wildcard": setting.as_ref().map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -309,20 +222,7 @@ make_setting_route!(
     >,
     stop_words,
     "stopWords",
-    analytics,
+    StopWordsAnalytics
-    |stop_words: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "StopWords Updated".to_string(),
-            json!({
-                "stop_words": {
-                    "total": stop_words.as_ref().map(|stop_words| stop_words.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -334,20 +234,7 @@ make_setting_route!(
     >,
     non_separator_tokens,
     "nonSeparatorTokens",
-    analytics,
+    NonSeparatorTokensAnalytics
-    |non_separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "nonSeparatorTokens Updated".to_string(),
-            json!({
-                "non_separator_tokens": {
-                    "total": non_separator_tokens.as_ref().map(|non_separator_tokens| non_separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -359,20 +246,7 @@ make_setting_route!(
     >,
     separator_tokens,
     "separatorTokens",
-    analytics,
+    SeparatorTokensAnalytics
-    |separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "separatorTokens Updated".to_string(),
-            json!({
-                "separator_tokens": {
-                    "total": separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -384,20 +258,7 @@ make_setting_route!(
     >,
     dictionary,
     "dictionary",
-    analytics,
+    DictionaryAnalytics
-    |dictionary: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "dictionary Updated".to_string(),
-            json!({
-                "dictionary": {
-                    "total": dictionary.as_ref().map(|dictionary| dictionary.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -409,20 +270,7 @@ make_setting_route!(
     >,
     synonyms,
     "synonyms",
-    analytics,
+    SynonymsAnalytics
-    |synonyms: &Option<std::collections::BTreeMap<String, Vec<String>>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "Synonyms Updated".to_string(),
-            json!({
-                "synonyms": {
-                    "total": synonyms.as_ref().map(|synonyms| synonyms.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -434,19 +282,7 @@ make_setting_route!(
     >,
     distinct_attribute,
     "distinctAttribute",
-    analytics,
+    DistinctAttributeAnalytics
-    |distinct: &Option<String>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "DistinctAttribute Updated".to_string(),
-            json!({
-                "distinct_attribute": {
-                    "set": distinct.is_some(),
-                }
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -458,20 +294,7 @@ make_setting_route!(
     >,
     proximity_precision,
     "proximityPrecision",
-    analytics,
+    ProximityPrecisionAnalytics
-    |precision: &Option<meilisearch_types::settings::ProximityPrecisionView>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "ProximityPrecision Updated".to_string(),
-            json!({
-                "proximity_precision": {
-                    "set": precision.is_some(),
-                    "value": precision.unwrap_or_default(),
-                }
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -483,17 +306,7 @@ make_setting_route!(
     >,
     localized_attributes,
     "localizedAttributes",
-    analytics,
+    LocalesAnalytics
-    |rules: &Option<Vec<meilisearch_types::locales::LocalizedAttributesRuleView>>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "LocalizedAttributesRules Updated".to_string(),
-            json!({
-                "locales": rules.as_ref().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>())
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -505,26 +318,7 @@ make_setting_route!(
     >,
     ranking_rules,
     "rankingRules",
-    analytics,
+    RankingRulesAnalytics
-    |setting: &Option<Vec<meilisearch_types::settings::RankingRuleView>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "RankingRules Updated".to_string(),
-            json!({
-                "ranking_rules": {
-                    "words_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Words))),
-                    "typo_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Typo))),
-                    "proximity_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Proximity))),
-                    "attribute_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Attribute))),
-                    "sort_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Sort))),
-                    "exactness_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Exactness))),
-                    "values": setting.as_ref().map(|rr| rr.iter().filter(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Asc(_) | meilisearch_types::settings::RankingRuleView::Desc(_)) ).map(|x| x.to_string()).collect::<Vec<_>>().join(", ")),
-                }
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -536,25 +330,7 @@ make_setting_route!(
     >,
     faceting,
     "faceting",
-    analytics,
+    FacetingAnalytics
-    |setting: &Option<meilisearch_types::settings::FacetingSettings>, req: &HttpRequest| {
-        use serde_json::json;
-        use meilisearch_types::facet_values_sort::FacetValuesSort;
-
-        analytics.publish(
-            "Faceting Updated".to_string(),
-            json!({
-                "faceting": {
-                    "max_values_per_facet": setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
-                    "sort_facet_values_by_star_count": setting.as_ref().and_then(|s| {
-                        s.sort_facet_values_by.as_ref().set().map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
-                    }),
-                    "sort_facet_values_by_total": setting.as_ref().and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -566,20 +342,7 @@ make_setting_route!(
     >,
     pagination,
     "pagination",
-    analytics,
+    PaginationAnalytics
-    |setting: &Option<meilisearch_types::settings::PaginationSettings>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "Pagination Updated".to_string(),
-            json!({
-                "pagination": {
-                    "max_total_hits": setting.as_ref().and_then(|s| s.max_total_hits.set()),
-                },
-            }),
-            Some(req),
-        );
-    }
 );
 
 make_setting_route!(
@@ -591,74 +354,8 @@ make_setting_route!(
     >,
     embedders,
     "embedders",
-    analytics,
+    EmbeddersAnalytics
-    |setting: &Option<std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>>, req: &HttpRequest| {
-
-
-        analytics.publish(
-            "Embedders Updated".to_string(),
-            serde_json::json!({"embedders": crate::routes::indexes::settings::embedder_analytics(setting.as_ref())}),
-            Some(req),
 );
-    }
-);
-
-fn embedder_analytics(
-    setting: Option<
-        &std::collections::BTreeMap<
-            String,
-            Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>,
-        >,
-    >,
-) -> serde_json::Value {
-    let mut sources = std::collections::HashSet::new();
-
-    if let Some(s) = &setting {
-        for source in s
-            .values()
-            .filter_map(|config| config.clone().set())
-            .filter_map(|config| config.source.set())
-        {
-            use meilisearch_types::milli::vector::settings::EmbedderSource;
-            match source {
-                EmbedderSource::OpenAi => sources.insert("openAi"),
-                EmbedderSource::HuggingFace => sources.insert("huggingFace"),
-                EmbedderSource::UserProvided => sources.insert("userProvided"),
-                EmbedderSource::Ollama => sources.insert("ollama"),
-                EmbedderSource::Rest => sources.insert("rest"),
-            };
-        }
-    };
-
-    let document_template_used = setting.as_ref().map(|map| {
-        map.values()
-            .filter_map(|config| config.clone().set())
-            .any(|config| config.document_template.set().is_some())
-    });
-
-    let document_template_max_bytes = setting.as_ref().and_then(|map| {
-        map.values()
-            .filter_map(|config| config.clone().set())
-            .filter_map(|config| config.document_template_max_bytes.set())
-            .max()
-    });
-
-    let binary_quantization_used = setting.as_ref().map(|map| {
-        map.values()
-            .filter_map(|config| config.clone().set())
-            .any(|config| config.binary_quantized.set().is_some())
-    });
-
-    json!(
-        {
-            "total": setting.as_ref().map(|s| s.len()),
-            "sources": sources,
-            "document_template_used": document_template_used,
-            "document_template_max_bytes": document_template_max_bytes,
-            "binary_quantization_used": binary_quantization_used,
-        }
-    )
-}
 
 make_setting_route!(
     "/search-cutoff-ms",
@@ -669,14 +366,7 @@ make_setting_route!(
     >,
     search_cutoff_ms,
     "searchCutoffMs",
-    analytics,
+    SearchCutoffMsAnalytics
-    |setting: &Option<u64>, req: &HttpRequest| {
-        analytics.publish(
-            "Search Cutoff Updated".to_string(),
-            serde_json::json!({"search_cutoff_ms": setting }),
-            Some(req),
-        );
-    }
 );
 
 macro_rules! generate_configure {
@@ -720,7 +410,7 @@ pub async fn update_all(
     body: AwebJson<Settings<Unchecked>, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -729,104 +419,45 @@ pub async fn update_all(
     let new_settings = validate_settings(new_settings, &index_scheduler)?;
 
     analytics.publish(
-        "Settings Updated".to_string(),
+        SettingsAnalytics {
-        json!({
+            ranking_rules: RankingRulesAnalytics::new(new_settings.ranking_rules.as_ref().set()),
-           "ranking_rules": {
+            searchable_attributes: SearchableAttributesAnalytics::new(
-                "words_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Words))),
+                new_settings.searchable_attributes.as_ref().set(),
-                "typo_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Typo))),
+            ),
-                "proximity_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Proximity))),
+            displayed_attributes: DisplayedAttributesAnalytics::new(
-                "attribute_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Attribute))),
+                new_settings.displayed_attributes.as_ref().set(),
-                "sort_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Sort))),
+            ),
-                "exactness_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Exactness))),
+            sortable_attributes: SortableAttributesAnalytics::new(
-                "values": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().filter(|s| !matches!(s, RankingRuleView::Asc(_) | RankingRuleView::Desc(_)) ).map(|x| x.to_string()).collect::<Vec<_>>().join(", ")),
+                new_settings.sortable_attributes.as_ref().set(),
+            ),
+            filterable_attributes: FilterableAttributesAnalytics::new(
+                new_settings.filterable_attributes.as_ref().set(),
+            ),
+            distinct_attribute: DistinctAttributeAnalytics::new(
+                new_settings.distinct_attribute.as_ref().set(),
+            ),
+            proximity_precision: ProximityPrecisionAnalytics::new(
+                new_settings.proximity_precision.as_ref().set(),
+            ),
+            typo_tolerance: TypoToleranceAnalytics::new(new_settings.typo_tolerance.as_ref().set()),
+            faceting: FacetingAnalytics::new(new_settings.faceting.as_ref().set()),
+            pagination: PaginationAnalytics::new(new_settings.pagination.as_ref().set()),
+            stop_words: StopWordsAnalytics::new(new_settings.stop_words.as_ref().set()),
+            synonyms: SynonymsAnalytics::new(new_settings.synonyms.as_ref().set()),
+            embedders: EmbeddersAnalytics::new(new_settings.embedders.as_ref().set()),
+            search_cutoff_ms: SearchCutoffMsAnalytics::new(
+                new_settings.search_cutoff_ms.as_ref().set(),
+            ),
+            locales: LocalesAnalytics::new(new_settings.localized_attributes.as_ref().set()),
+            dictionary: DictionaryAnalytics::new(new_settings.dictionary.as_ref().set()),
+            separator_tokens: SeparatorTokensAnalytics::new(
+                new_settings.separator_tokens.as_ref().set(),
+            ),
+            non_separator_tokens: NonSeparatorTokensAnalytics::new(
+                new_settings.non_separator_tokens.as_ref().set(),
+            ),
         },
-            "searchable_attributes": {
+        &req,
-                "total": new_settings.searchable_attributes.as_ref().set().map(|searchable| searchable.len()),
-                "with_wildcard": new_settings.searchable_attributes.as_ref().set().map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
-            },
-            "displayed_attributes": {
-                "total": new_settings.displayed_attributes.as_ref().set().map(|displayed| displayed.len()),
-                "with_wildcard": new_settings.displayed_attributes.as_ref().set().map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
-            },
-           "sortable_attributes": {
-                "total": new_settings.sortable_attributes.as_ref().set().map(|sort| sort.len()),
-                "has_geo": new_settings.sortable_attributes.as_ref().set().map(|sort| sort.iter().any(|s| s == "_geo")),
-            },
-           "filterable_attributes": {
-                "total": new_settings.filterable_attributes.as_ref().set().map(|filter| filter.len()),
-                "has_geo": new_settings.filterable_attributes.as_ref().set().map(|filter| filter.iter().any(|s| s == "_geo")),
-            },
-            "distinct_attribute": {
-                "set": new_settings.distinct_attribute.as_ref().set().is_some()
-            },
-            "proximity_precision": {
-                "set": new_settings.proximity_precision.as_ref().set().is_some(),
-                "value": new_settings.proximity_precision.as_ref().set().copied().unwrap_or_default()
-            },
-            "typo_tolerance": {
-                "enabled": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.enabled.as_ref().set())
-                    .copied(),
-                "disable_on_attributes": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
-                "disable_on_words": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
-                "min_word_size_for_one_typo": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.min_word_size_for_typos
-                        .as_ref()
-                        .set()
-                        .map(|s| s.one_typo.set()))
-                    .flatten(),
-                "min_word_size_for_two_typos": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.min_word_size_for_typos
-                        .as_ref()
-                        .set()
-                        .map(|s| s.two_typos.set()))
-                    .flatten(),
-            },
-            "faceting": {
-                "max_values_per_facet": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.max_values_per_facet.as_ref().set()),
-                "sort_facet_values_by_star_count": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| {
-                        s.sort_facet_values_by.as_ref().set().map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
-                    }),
-                "sort_facet_values_by_total": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
-            },
-            "pagination": {
-                "max_total_hits": new_settings.pagination
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.max_total_hits.as_ref().set()),
-            },
-            "stop_words": {
-                "total": new_settings.stop_words.as_ref().set().map(|stop_words| stop_words.len()),
-            },
-            "synonyms": {
-                "total": new_settings.synonyms.as_ref().set().map(|synonyms| synonyms.len()),
-            },
-            "embedders": crate::routes::indexes::settings::embedder_analytics(new_settings.embedders.as_ref().set()),
-            "search_cutoff_ms": new_settings.search_cutoff_ms.as_ref().set(),
-            "locales": new_settings.localized_attributes.as_ref().set().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>()),
-        }),
-        Some(&req),
     );
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);

meilisearch/src/routes/indexes/settings_analytics.rs

@@ -0,0 +1,621 @@
+//! All the structures used to make the analytics on the settings works.
+//! The signatures of the `new` functions are not very rust idiomatic because they must match the types received
+//! through the sub-settings route directly without any manipulation.
+//! This is why we often use a `Option<&Vec<_>>` instead of a `Option<&[_]>`.
+
+use meilisearch_types::locales::{Locale, LocalizedAttributesRuleView};
+use meilisearch_types::milli::update::Setting;
+use meilisearch_types::milli::vector::settings::EmbeddingSettings;
+use meilisearch_types::settings::{
+    FacetingSettings, PaginationSettings, ProximityPrecisionView, TypoSettings,
+};
+use meilisearch_types::{facet_values_sort::FacetValuesSort, settings::RankingRuleView};
+use serde::Serialize;
+use std::collections::{BTreeMap, BTreeSet, HashSet};
+
+use crate::analytics::Aggregate;
+
+#[derive(Serialize, Default)]
+pub struct SettingsAnalytics {
+    pub ranking_rules: RankingRulesAnalytics,
+    pub searchable_attributes: SearchableAttributesAnalytics,
+    pub displayed_attributes: DisplayedAttributesAnalytics,
+    pub sortable_attributes: SortableAttributesAnalytics,
+    pub filterable_attributes: FilterableAttributesAnalytics,
+    pub distinct_attribute: DistinctAttributeAnalytics,
+    pub proximity_precision: ProximityPrecisionAnalytics,
+    pub typo_tolerance: TypoToleranceAnalytics,
+    pub faceting: FacetingAnalytics,
+    pub pagination: PaginationAnalytics,
+    pub stop_words: StopWordsAnalytics,
+    pub synonyms: SynonymsAnalytics,
+    pub embedders: EmbeddersAnalytics,
+    pub search_cutoff_ms: SearchCutoffMsAnalytics,
+    pub locales: LocalesAnalytics,
+    pub dictionary: DictionaryAnalytics,
+    pub separator_tokens: SeparatorTokensAnalytics,
+    pub non_separator_tokens: NonSeparatorTokensAnalytics,
+}
+
+impl Aggregate for SettingsAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Settings Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            ranking_rules: RankingRulesAnalytics {
+                words_position: new
+                    .ranking_rules
+                    .words_position
+                    .or(self.ranking_rules.words_position),
+                typo_position: new.ranking_rules.typo_position.or(self.ranking_rules.typo_position),
+                proximity_position: new
+                    .ranking_rules
+                    .proximity_position
+                    .or(self.ranking_rules.proximity_position),
+                attribute_position: new
+                    .ranking_rules
+                    .attribute_position
+                    .or(self.ranking_rules.attribute_position),
+                sort_position: new.ranking_rules.sort_position.or(self.ranking_rules.sort_position),
+                exactness_position: new
+                    .ranking_rules
+                    .exactness_position
+                    .or(self.ranking_rules.exactness_position),
+                values: new.ranking_rules.values.or(self.ranking_rules.values),
+            },
+            searchable_attributes: SearchableAttributesAnalytics {
+                total: new.searchable_attributes.total.or(self.searchable_attributes.total),
+                with_wildcard: new
+                    .searchable_attributes
+                    .with_wildcard
+                    .or(self.searchable_attributes.with_wildcard),
+            },
+            displayed_attributes: DisplayedAttributesAnalytics {
+                total: new.displayed_attributes.total.or(self.displayed_attributes.total),
+                with_wildcard: new
+                    .displayed_attributes
+                    .with_wildcard
+                    .or(self.displayed_attributes.with_wildcard),
+            },
+            sortable_attributes: SortableAttributesAnalytics {
+                total: new.sortable_attributes.total.or(self.sortable_attributes.total),
+                has_geo: new.sortable_attributes.has_geo.or(self.sortable_attributes.has_geo),
+            },
+            filterable_attributes: FilterableAttributesAnalytics {
+                total: new.filterable_attributes.total.or(self.filterable_attributes.total),
+                has_geo: new.filterable_attributes.has_geo.or(self.filterable_attributes.has_geo),
+            },
+            distinct_attribute: DistinctAttributeAnalytics {
+                set: self.distinct_attribute.set | new.distinct_attribute.set,
+            },
+            proximity_precision: ProximityPrecisionAnalytics {
+                set: self.proximity_precision.set | new.proximity_precision.set,
+                value: new.proximity_precision.value.or(self.proximity_precision.value),
+            },
+            typo_tolerance: TypoToleranceAnalytics {
+                enabled: new.typo_tolerance.enabled.or(self.typo_tolerance.enabled),
+                disable_on_attributes: new
+                    .typo_tolerance
+                    .disable_on_attributes
+                    .or(self.typo_tolerance.disable_on_attributes),
+                disable_on_words: new
+                    .typo_tolerance
+                    .disable_on_words
+                    .or(self.typo_tolerance.disable_on_words),
+                min_word_size_for_one_typo: new
+                    .typo_tolerance
+                    .min_word_size_for_one_typo
+                    .or(self.typo_tolerance.min_word_size_for_one_typo),
+                min_word_size_for_two_typos: new
+                    .typo_tolerance
+                    .min_word_size_for_two_typos
+                    .or(self.typo_tolerance.min_word_size_for_two_typos),
+            },
+            faceting: FacetingAnalytics {
+                max_values_per_facet: new
+                    .faceting
+                    .max_values_per_facet
+                    .or(self.faceting.max_values_per_facet),
+                sort_facet_values_by_star_count: new
+                    .faceting
+                    .sort_facet_values_by_star_count
+                    .or(self.faceting.sort_facet_values_by_star_count),
+                sort_facet_values_by_total: new
+                    .faceting
+                    .sort_facet_values_by_total
+                    .or(self.faceting.sort_facet_values_by_total),
+            },
+            pagination: PaginationAnalytics {
+                max_total_hits: new.pagination.max_total_hits.or(self.pagination.max_total_hits),
+            },
+            stop_words: StopWordsAnalytics {
+                total: new.stop_words.total.or(self.stop_words.total),
+            },
+            synonyms: SynonymsAnalytics { total: new.synonyms.total.or(self.synonyms.total) },
+            embedders: EmbeddersAnalytics {
+                total: new.embedders.total.or(self.embedders.total),
+                sources: match (self.embedders.sources, new.embedders.sources) {
+                    (None, None) => None,
+                    (Some(sources), None) | (None, Some(sources)) => Some(sources),
+                    (Some(this), Some(other)) => Some(this.union(&other).cloned().collect()),
+                },
+                document_template_used: match (
+                    self.embedders.document_template_used,
+                    new.embedders.document_template_used,
+                ) {
+                    (None, None) => None,
+                    (Some(used), None) | (None, Some(used)) => Some(used),
+                    (Some(this), Some(other)) => Some(this | other),
+                },
+                document_template_max_bytes: match (
+                    self.embedders.document_template_max_bytes,
+                    new.embedders.document_template_max_bytes,
+                ) {
+                    (None, None) => None,
+                    (Some(bytes), None) | (None, Some(bytes)) => Some(bytes),
+                    (Some(this), Some(other)) => Some(this.max(other)),
+                },
+                binary_quantization_used: match (
+                    self.embedders.binary_quantization_used,
+                    new.embedders.binary_quantization_used,
+                ) {
+                    (None, None) => None,
+                    (Some(bq), None) | (None, Some(bq)) => Some(bq),
+                    (Some(this), Some(other)) => Some(this | other),
+                },
+            },
+            search_cutoff_ms: SearchCutoffMsAnalytics {
+                search_cutoff_ms: new
+                    .search_cutoff_ms
+                    .search_cutoff_ms
+                    .or(self.search_cutoff_ms.search_cutoff_ms),
+            },
+            locales: LocalesAnalytics { locales: new.locales.locales.or(self.locales.locales) },
+            dictionary: DictionaryAnalytics {
+                total: new.dictionary.total.or(self.dictionary.total),
+            },
+            separator_tokens: SeparatorTokensAnalytics {
+                total: new.non_separator_tokens.total.or(self.separator_tokens.total),
+            },
+            non_separator_tokens: NonSeparatorTokensAnalytics {
+                total: new.non_separator_tokens.total.or(self.non_separator_tokens.total),
+            },
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct RankingRulesAnalytics {
+    pub words_position: Option<usize>,
+    pub typo_position: Option<usize>,
+    pub proximity_position: Option<usize>,
+    pub attribute_position: Option<usize>,
+    pub sort_position: Option<usize>,
+    pub exactness_position: Option<usize>,
+    pub values: Option<String>,
+}
+
+impl RankingRulesAnalytics {
+    pub fn new(rr: Option<&Vec<RankingRuleView>>) -> Self {
+        RankingRulesAnalytics {
+            words_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Words))
+            }),
+            typo_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Typo))
+            }),
+            proximity_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Proximity)
+                })
+            }),
+            attribute_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Attribute)
+                })
+            }),
+            sort_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Sort))
+            }),
+            exactness_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Exactness)
+                })
+            }),
+            values: rr.as_ref().map(|rr| {
+                rr.iter()
+                    .filter(|s| {
+                        matches!(
+                            s,
+                            meilisearch_types::settings::RankingRuleView::Asc(_)
+                                | meilisearch_types::settings::RankingRuleView::Desc(_)
+                        )
+                    })
+                    .map(|x| x.to_string())
+                    .collect::<Vec<_>>()
+                    .join(", ")
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { ranking_rules: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SearchableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub with_wildcard: Option<bool>,
+}
+
+impl SearchableAttributesAnalytics {
+    pub fn new(setting: Option<&Vec<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|searchable| searchable.len()),
+            with_wildcard: setting
+                .as_ref()
+                .map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { searchable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DisplayedAttributesAnalytics {
+    pub total: Option<usize>,
+    pub with_wildcard: Option<bool>,
+}
+
+impl DisplayedAttributesAnalytics {
+    pub fn new(displayed: Option<&Vec<String>>) -> Self {
+        Self {
+            total: displayed.as_ref().map(|displayed| displayed.len()),
+            with_wildcard: displayed
+                .as_ref()
+                .map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { displayed_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SortableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub has_geo: Option<bool>,
+}
+
+impl SortableAttributesAnalytics {
+    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|sort| sort.len()),
+            has_geo: setting.as_ref().map(|sort| sort.contains("_geo")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { sortable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct FilterableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub has_geo: Option<bool>,
+}
+
+impl FilterableAttributesAnalytics {
+    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|filter| filter.len()),
+            has_geo: setting.as_ref().map(|filter| filter.contains("_geo")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { filterable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DistinctAttributeAnalytics {
+    pub set: bool,
+}
+
+impl DistinctAttributeAnalytics {
+    pub fn new(distinct: Option<&String>) -> Self {
+        Self { set: distinct.is_some() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { distinct_attribute: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct ProximityPrecisionAnalytics {
+    pub set: bool,
+    pub value: Option<ProximityPrecisionView>,
+}
+
+impl ProximityPrecisionAnalytics {
+    pub fn new(precision: Option<&ProximityPrecisionView>) -> Self {
+        Self { set: precision.is_some(), value: precision.cloned() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { proximity_precision: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct TypoToleranceAnalytics {
+    pub enabled: Option<bool>,
+    pub disable_on_attributes: Option<bool>,
+    pub disable_on_words: Option<bool>,
+    pub min_word_size_for_one_typo: Option<u8>,
+    pub min_word_size_for_two_typos: Option<u8>,
+}
+
+impl TypoToleranceAnalytics {
+    pub fn new(setting: Option<&TypoSettings>) -> Self {
+        Self {
+            enabled: setting.as_ref().map(|s| !matches!(s.enabled, Setting::Set(false))),
+            disable_on_attributes: setting
+                .as_ref()
+                .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
+            disable_on_words: setting
+                .as_ref()
+                .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
+            min_word_size_for_one_typo: setting
+                .as_ref()
+                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.one_typo.set()))
+                .flatten(),
+            min_word_size_for_two_typos: setting
+                .as_ref()
+                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.two_typos.set()))
+                .flatten(),
+        }
+    }
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { typo_tolerance: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct FacetingAnalytics {
+    pub max_values_per_facet: Option<usize>,
+    pub sort_facet_values_by_star_count: Option<bool>,
+    pub sort_facet_values_by_total: Option<usize>,
+}
+
+impl FacetingAnalytics {
+    pub fn new(setting: Option<&FacetingSettings>) -> Self {
+        Self {
+            max_values_per_facet: setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
+            sort_facet_values_by_star_count: setting.as_ref().and_then(|s| {
+                s.sort_facet_values_by
+                    .as_ref()
+                    .set()
+                    .map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
+            }),
+            sort_facet_values_by_total: setting
+                .as_ref()
+                .and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { faceting: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct PaginationAnalytics {
+    pub max_total_hits: Option<usize>,
+}
+
+impl PaginationAnalytics {
+    pub fn new(setting: Option<&PaginationSettings>) -> Self {
+        Self { max_total_hits: setting.as_ref().and_then(|s| s.max_total_hits.set()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { pagination: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct StopWordsAnalytics {
+    pub total: Option<usize>,
+}
+
+impl StopWordsAnalytics {
+    pub fn new(stop_words: Option<&BTreeSet<String>>) -> Self {
+        Self { total: stop_words.as_ref().map(|stop_words| stop_words.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { stop_words: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SynonymsAnalytics {
+    pub total: Option<usize>,
+}
+
+impl SynonymsAnalytics {
+    pub fn new(synonyms: Option<&BTreeMap<String, Vec<String>>>) -> Self {
+        Self { total: synonyms.as_ref().map(|synonyms| synonyms.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { synonyms: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct EmbeddersAnalytics {
+    // last
+    pub total: Option<usize>,
+    // Merge the sources
+    pub sources: Option<HashSet<String>>,
+    // |=
+    pub document_template_used: Option<bool>,
+    // max
+    pub document_template_max_bytes: Option<usize>,
+    // |=
+    pub binary_quantization_used: Option<bool>,
+}
+
+impl EmbeddersAnalytics {
+    pub fn new(setting: Option<&BTreeMap<String, Setting<EmbeddingSettings>>>) -> Self {
+        let mut sources = std::collections::HashSet::new();
+
+        if let Some(s) = &setting {
+            for source in s
+                .values()
+                .filter_map(|config| config.clone().set())
+                .filter_map(|config| config.source.set())
+            {
+                use meilisearch_types::milli::vector::settings::EmbedderSource;
+                match source {
+                    EmbedderSource::OpenAi => sources.insert("openAi".to_string()),
+                    EmbedderSource::HuggingFace => sources.insert("huggingFace".to_string()),
+                    EmbedderSource::UserProvided => sources.insert("userProvided".to_string()),
+                    EmbedderSource::Ollama => sources.insert("ollama".to_string()),
+                    EmbedderSource::Rest => sources.insert("rest".to_string()),
+                };
+            }
+        };
+
+        Self {
+            total: setting.as_ref().map(|s| s.len()),
+            sources: Some(sources),
+            document_template_used: setting.as_ref().map(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .any(|config| config.document_template.set().is_some())
+            }),
+            document_template_max_bytes: setting.as_ref().and_then(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .filter_map(|config| config.document_template_max_bytes.set())
+                    .max()
+            }),
+            binary_quantization_used: setting.as_ref().map(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .any(|config| config.binary_quantized.set().is_some())
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { embedders: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+#[serde(transparent)]
+pub struct SearchCutoffMsAnalytics {
+    pub search_cutoff_ms: Option<u64>,
+}
+
+impl SearchCutoffMsAnalytics {
+    pub fn new(setting: Option<&u64>) -> Self {
+        Self { search_cutoff_ms: setting.copied() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { search_cutoff_ms: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+#[serde(transparent)]
+pub struct LocalesAnalytics {
+    pub locales: Option<BTreeSet<Locale>>,
+}
+
+impl LocalesAnalytics {
+    pub fn new(rules: Option<&Vec<LocalizedAttributesRuleView>>) -> Self {
+        LocalesAnalytics {
+            locales: rules.as_ref().map(|rules| {
+                rules
+                    .iter()
+                    .flat_map(|rule| rule.locales.iter().cloned())
+                    .collect::<std::collections::BTreeSet<_>>()
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { locales: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DictionaryAnalytics {
+    pub total: Option<usize>,
+}
+
+impl DictionaryAnalytics {
+    pub fn new(dictionary: Option<&BTreeSet<String>>) -> Self {
+        Self { total: dictionary.as_ref().map(|dictionary| dictionary.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { dictionary: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SeparatorTokensAnalytics {
+    pub total: Option<usize>,
+}
+
+impl SeparatorTokensAnalytics {
+    pub fn new(separator_tokens: Option<&BTreeSet<String>>) -> Self {
+        Self { total: separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { separator_tokens: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct NonSeparatorTokensAnalytics {
+    pub total: Option<usize>,
+}
+
+impl NonSeparatorTokensAnalytics {
+    pub fn new(non_separator_tokens: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: non_separator_tokens
+                .as_ref()
+                .map(|non_separator_tokens| non_separator_tokens.len()),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { non_separator_tokens: self, ..Default::default() }
+    }
+}

meilisearch/src/routes/indexes/similar.rs

@@ -13,9 +13,10 @@ use serde_json::Value;
 use tracing::debug;
 
 use super::ActionPolicy;
-use crate::analytics::{Analytics, SimilarAggregator};
+use crate::analytics::Analytics;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
+use crate::routes::indexes::similar_analytics::{SimilarAggregator, SimilarGET, SimilarPOST};
 use crate::search::{
     add_search_rules, perform_similar, RankingScoreThresholdSimilar, RetrieveVectors, SearchKind,
     SimilarQuery, SimilarResult, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
@@ -34,13 +35,13 @@ pub async fn similar_get(
     index_uid: web::Path<String>,
     params: AwebQueryParameter<SimilarQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.0.try_into()?;
 
-    let mut aggregate = SimilarAggregator::from_query(&query, &req);
+    let mut aggregate = SimilarAggregator::<SimilarGET>::from_query(&query);
 
     debug!(parameters = ?query, "Similar get");
 
@@ -49,7 +50,7 @@ pub async fn similar_get(
     if let Ok(similar) = &similar {
         aggregate.succeed(similar);
     }
-    analytics.get_similar(aggregate);
+    analytics.publish(aggregate, &req);
 
     let similar = similar?;
 
@@ -62,21 +63,21 @@ pub async fn similar_post(
     index_uid: web::Path<String>,
     params: AwebJson<SimilarQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.into_inner();
     debug!(parameters = ?query, "Similar post");
 
-    let mut aggregate = SimilarAggregator::from_query(&query, &req);
+    let mut aggregate = SimilarAggregator::<SimilarPOST>::from_query(&query);
 
     let similar = similar(index_scheduler, index_uid, query).await;
 
     if let Ok(similar) = &similar {
         aggregate.succeed(similar);
     }
-    analytics.post_similar(aggregate);
+    analytics.publish(aggregate, &req);
 
     let similar = similar?;
 

meilisearch/src/routes/indexes/similar_analytics.rs

@@ -0,0 +1,235 @@
+use std::collections::{BinaryHeap, HashMap};
+
+use once_cell::sync::Lazy;
+use regex::Regex;
+use serde_json::{json, Value};
+
+use crate::{
+    aggregate_methods,
+    analytics::{Aggregate, AggregateMethod},
+    search::{SimilarQuery, SimilarResult},
+};
+
+aggregate_methods!(
+    SimilarPOST => "Similar POST",
+    SimilarGET => "Similar GET",
+);
+
+#[derive(Default)]
+pub struct SimilarAggregator<Method: AggregateMethod> {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // Whether a non-default embedder was specified
+    retrieve_vectors: bool,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod> SimilarAggregator<Method> {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SimilarQuery) -> Self {
+        let SimilarQuery {
+            id: _,
+            embedder: _,
+            offset,
+            limit,
+            attributes_to_retrieve: _,
+            retrieve_vectors,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            ranking_score_threshold,
+        } = query;
+
+        let mut ret = Self::default();
+
+        ret.total_received = 1;
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        ret.max_limit = *limit;
+        ret.max_offset = *offset;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        ret.retrieve_vectors = *retrieve_vectors;
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SimilarResult) {
+        let SimilarResult { id: _, hits: _, processing_time_ms, hits_info: _ } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for SimilarAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    /// Aggregate one [SimilarAggregator] into another.
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        let Self {
+            total_received,
+            total_succeeded,
+            mut time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            ranking_score_threshold,
+            retrieve_vectors,
+            marker: _,
+        } = *new;
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.time_spent.append(&mut time_spent);
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        self.retrieve_vectors |= retrieve_vectors;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            ranking_score_threshold,
+            retrieve_vectors,
+            marker: _,
+        } = *self;
+
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // the index of the 99th percentage of value
+        let percentile_99th = time_spent.len() * 99 / 100;
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th);
+
+        json!({
+            "requests": {
+                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "filter": {
+               "with_geoRadius": filter_with_geo_radius,
+               "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "vector": {
+                "retrieve_vectors": retrieve_vectors,
+            },
+            "pagination": {
+               "max_limit": max_limit,
+               "max_offset": max_offset,
+            },
+            "formatting": {
+                "max_attributes_to_retrieve": max_attributes_to_retrieve,
+            },
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+                "ranking_score_threshold": ranking_score_threshold,
+            }
+        })
+    }
+}

meilisearch/src/routes/mod.rs

@@ -25,6 +25,7 @@ pub mod indexes;
 mod logs;
 mod metrics;
 mod multi_search;
+mod multi_search_analytics;
 mod snapshot;
 mod swap_indexes;
 pub mod tasks;

meilisearch/src/routes/multi_search.rs

@@ -9,7 +9,7 @@ use meilisearch_types::keys::actions;
 use serde::Serialize;
 use tracing::debug;
 
-use crate::analytics::{Analytics, MultiSearchAggregator};
+use crate::analytics::Analytics;
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
@@ -21,6 +21,8 @@ use crate::search::{
 };
 use crate::search_queue::SearchQueue;
 
+use super::multi_search_analytics::MultiSearchAggregator;
+
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(multi_search_with_post))));
 }
@@ -35,7 +37,7 @@ pub async fn multi_search_with_post(
     search_queue: Data<SearchQueue>,
     params: AwebJson<FederatedSearch, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     // Since we don't want to process half of the search requests and then get a permit refused
     // we're going to get one permit for the whole duration of the multi-search request.
@@ -43,7 +45,7 @@ pub async fn multi_search_with_post(
 
     let federated_search = params.into_inner();
 
-    let mut multi_aggregate = MultiSearchAggregator::from_federated_search(&federated_search, &req);
+    let mut multi_aggregate = MultiSearchAggregator::from_federated_search(&federated_search);
 
     let FederatedSearch { mut queries, federation } = federated_search;
 
@@ -87,7 +89,7 @@ pub async fn multi_search_with_post(
                 multi_aggregate.succeed();
             }
 
-            analytics.post_multi_search(multi_aggregate);
+            analytics.publish(multi_aggregate, &req);
             HttpResponse::Ok().json(search_result??)
         }
         None => {
@@ -149,7 +151,7 @@ pub async fn multi_search_with_post(
             if search_results.is_ok() {
                 multi_aggregate.succeed();
             }
-            analytics.post_multi_search(multi_aggregate);
+            analytics.publish(multi_aggregate, &req);
 
             let search_results = search_results.map_err(|(mut err, query_index)| {
                 // Add the query index that failed as context for the error message.

meilisearch/src/routes/multi_search_analytics.rs

@@ -0,0 +1,170 @@
+use std::collections::HashSet;
+
+use serde_json::json;
+
+use crate::{
+    analytics::Aggregate,
+    search::{FederatedSearch, SearchQueryWithIndex},
+};
+
+#[derive(Default)]
+pub struct MultiSearchAggregator {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+
+    // sum of the number of distinct indexes in each single request, use with total_received to compute an avg
+    total_distinct_index_count: usize,
+    // number of queries with a single index, use with total_received to compute a proportion
+    total_single_index: usize,
+
+    // sum of the number of search queries in the requests, use with total_received to compute an average
+    total_search_count: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+
+    // federation
+    use_federation: bool,
+}
+
+impl MultiSearchAggregator {
+    pub fn from_federated_search(federated_search: &FederatedSearch) -> Self {
+        let use_federation = federated_search.federation.is_some();
+
+        let distinct_indexes: HashSet<_> = federated_search
+            .queries
+            .iter()
+            .map(|query| {
+                let query = &query;
+                // make sure we get a compilation error if a field gets added to / removed from SearchQueryWithIndex
+                let SearchQueryWithIndex {
+                    index_uid,
+                    federation_options: _,
+                    q: _,
+                    vector: _,
+                    offset: _,
+                    limit: _,
+                    page: _,
+                    hits_per_page: _,
+                    attributes_to_retrieve: _,
+                    retrieve_vectors: _,
+                    attributes_to_crop: _,
+                    crop_length: _,
+                    attributes_to_highlight: _,
+                    show_ranking_score: _,
+                    show_ranking_score_details: _,
+                    show_matches_position: _,
+                    filter: _,
+                    sort: _,
+                    distinct: _,
+                    facets: _,
+                    highlight_pre_tag: _,
+                    highlight_post_tag: _,
+                    crop_marker: _,
+                    matching_strategy: _,
+                    attributes_to_search_on: _,
+                    hybrid: _,
+                    ranking_score_threshold: _,
+                    locales: _,
+                } = query;
+
+                index_uid.as_str()
+            })
+            .collect();
+
+        let show_ranking_score =
+            federated_search.queries.iter().any(|query| query.show_ranking_score);
+        let show_ranking_score_details =
+            federated_search.queries.iter().any(|query| query.show_ranking_score_details);
+
+        Self {
+            total_received: 1,
+            total_succeeded: 0,
+            total_distinct_index_count: distinct_indexes.len(),
+            total_single_index: if distinct_indexes.len() == 1 { 1 } else { 0 },
+            total_search_count: federated_search.queries.len(),
+            show_ranking_score,
+            show_ranking_score_details,
+            use_federation,
+        }
+    }
+
+    pub fn succeed(&mut self) {
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+    }
+}
+
+impl Aggregate for MultiSearchAggregator {
+    fn event_name(&self) -> &'static str {
+        "Documents Searched by Multi-Search POST"
+    }
+
+    /// Aggregate one [MultiSearchAggregator] into another.
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        // write the aggregate in a way that will cause a compilation error if a field is added.
+
+        // get ownership of self, replacing it by a default value.
+        let this = *self;
+
+        let total_received = this.total_received.saturating_add(new.total_received);
+        let total_succeeded = this.total_succeeded.saturating_add(new.total_succeeded);
+        let total_distinct_index_count =
+            this.total_distinct_index_count.saturating_add(new.total_distinct_index_count);
+        let total_single_index = this.total_single_index.saturating_add(new.total_single_index);
+        let total_search_count = this.total_search_count.saturating_add(new.total_search_count);
+        let show_ranking_score = this.show_ranking_score || new.show_ranking_score;
+        let show_ranking_score_details =
+            this.show_ranking_score_details || new.show_ranking_score_details;
+        let use_federation = this.use_federation || new.use_federation;
+
+        Box::new(Self {
+            total_received,
+            total_succeeded,
+            total_distinct_index_count,
+            total_single_index,
+            total_search_count,
+            show_ranking_score,
+            show_ranking_score_details,
+            use_federation,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            total_distinct_index_count,
+            total_single_index,
+            total_search_count,
+            show_ranking_score,
+            show_ranking_score_details,
+            use_federation,
+        } = *self;
+
+        json!({
+            "requests": {
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "indexes": {
+                "total_single_index": total_single_index,
+                "total_distinct_index_count": total_distinct_index_count,
+                "avg_distinct_index_count": (total_distinct_index_count as f64) / (total_received as f64), // not 0 else returned early
+            },
+            "searches": {
+                "total_search_count": total_search_count,
+                "avg_search_count": (total_search_count as f64) / (total_received as f64),
+            },
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+            },
+            "federation": {
+                "use_federation": use_federation,
+            }
+        })
+    }
+}

meilisearch/src/routes/snapshot.rs

@@ -3,7 +3,6 @@ use actix_web::{web, HttpRequest, HttpResponse};
 use index_scheduler::IndexScheduler;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
 use tracing::debug;
 
 use crate::analytics::Analytics;
@@ -17,13 +16,15 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(create_snapshot))));
 }
 
+crate::empty_analytics!(SnapshotAnalytics, "Snapshot Created");
+
 pub async fn create_snapshot(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SNAPSHOTS_CREATE }>, Data<IndexScheduler>>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Snapshot Created".to_string(), json!({}), Some(&req));
+    analytics.publish(SnapshotAnalytics::default(), &req);
 
     let task = KindWithContent::SnapshotCreation;
     let uid = get_task_id(&req, &opt)?;

meilisearch/src/routes/swap_indexes.rs

@@ -8,10 +8,10 @@ use meilisearch_types::error::deserr_codes::InvalidSwapIndexes;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::tasks::{IndexSwap, KindWithContent};
-use serde_json::json;
+use serde::Serialize;
 
 use super::{get_task_id, is_dry_run, SummarizedTaskView};
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, Analytics};
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
@@ -29,21 +29,36 @@ pub struct SwapIndexesPayload {
     indexes: Vec<IndexUid>,
 }
 
+#[derive(Serialize)]
+struct IndexSwappedAnalytics {
+    swap_operation_number: usize,
+}
+
+impl Aggregate for IndexSwappedAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Indexes Swapped"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            swap_operation_number: self.swap_operation_number.max(new.swap_operation_number),
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn swap_indexes(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_SWAP }>, Data<IndexScheduler>>,
     params: AwebJson<Vec<SwapIndexesPayload>, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let params = params.into_inner();
-    analytics.publish(
+    analytics.publish(IndexSwappedAnalytics { swap_operation_number: params.len() }, &req);
-        "Indexes Swapped".to_string(),
-        json!({
-            "swap_operation_number": params.len(),
-        }),
-        Some(&req),
-    );
     let filters = index_scheduler.filters();
 
     let mut swaps = vec![];

meilisearch/src/routes/tasks.rs

@@ -12,18 +12,17 @@ use meilisearch_types::star_or::{OptionStarOr, OptionStarOrList};
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status};
 use serde::Serialize;
-use serde_json::json;
 use time::format_description::well_known::Rfc3339;
 use time::macros::format_description;
 use time::{Date, Duration, OffsetDateTime, Time};
 use tokio::task;
 
 use super::{get_task_id, is_dry_run, SummarizedTaskView};
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, AggregateMethod, Analytics};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::Opt;
+use crate::{aggregate_methods, Opt};
 
 const DEFAULT_LIMIT: u32 = 20;
 
@@ -158,12 +157,69 @@ impl TaskDeletionOrCancelationQuery {
     }
 }
 
+aggregate_methods!(
+    CancelTasks => "Tasks Canceled",
+    DeleteTasks => "Tasks Deleted",
+);
+
+#[derive(Serialize)]
+struct TaskFilterAnalytics<Method: AggregateMethod> {
+    filtered_by_uid: bool,
+    filtered_by_index_uid: bool,
+    filtered_by_type: bool,
+    filtered_by_status: bool,
+    filtered_by_canceled_by: bool,
+    filtered_by_before_enqueued_at: bool,
+    filtered_by_after_enqueued_at: bool,
+    filtered_by_before_started_at: bool,
+    filtered_by_after_started_at: bool,
+    filtered_by_before_finished_at: bool,
+    filtered_by_after_finished_at: bool,
+
+    #[serde(skip)]
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod + 'static> Aggregate for TaskFilterAnalytics<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            filtered_by_uid: self.filtered_by_uid | new.filtered_by_uid,
+            filtered_by_index_uid: self.filtered_by_index_uid | new.filtered_by_index_uid,
+            filtered_by_type: self.filtered_by_type | new.filtered_by_type,
+            filtered_by_status: self.filtered_by_status | new.filtered_by_status,
+            filtered_by_canceled_by: self.filtered_by_canceled_by | new.filtered_by_canceled_by,
+            filtered_by_before_enqueued_at: self.filtered_by_before_enqueued_at
+                | new.filtered_by_before_enqueued_at,
+            filtered_by_after_enqueued_at: self.filtered_by_after_enqueued_at
+                | new.filtered_by_after_enqueued_at,
+            filtered_by_before_started_at: self.filtered_by_before_started_at
+                | new.filtered_by_before_started_at,
+            filtered_by_after_started_at: self.filtered_by_after_started_at
+                | new.filtered_by_after_started_at,
+            filtered_by_before_finished_at: self.filtered_by_before_finished_at
+                | new.filtered_by_before_finished_at,
+            filtered_by_after_finished_at: self.filtered_by_after_finished_at
+                | new.filtered_by_after_finished_at,
+
+            marker: std::marker::PhantomData,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 async fn cancel_tasks(
     index_scheduler: GuardedData<ActionPolicy<{ actions::TASKS_CANCEL }>, Data<IndexScheduler>>,
     params: AwebQueryParameter<TaskDeletionOrCancelationQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let params = params.into_inner();
 
@@ -172,21 +228,22 @@ async fn cancel_tasks(
     }
 
     analytics.publish(
-        "Tasks Canceled".to_string(),
+        TaskFilterAnalytics::<CancelTasks> {
-        json!({
+            filtered_by_uid: params.uids.is_some(),
-            "filtered_by_uid": params.uids.is_some(),
+            filtered_by_index_uid: params.index_uids.is_some(),
-            "filtered_by_index_uid": params.index_uids.is_some(),
+            filtered_by_type: params.types.is_some(),
-            "filtered_by_type": params.types.is_some(),
+            filtered_by_status: params.statuses.is_some(),
-            "filtered_by_status": params.statuses.is_some(),
+            filtered_by_canceled_by: params.canceled_by.is_some(),
-            "filtered_by_canceled_by": params.canceled_by.is_some(),
+            filtered_by_before_enqueued_at: params.before_enqueued_at.is_some(),
-            "filtered_by_before_enqueued_at": params.before_enqueued_at.is_some(),
+            filtered_by_after_enqueued_at: params.after_enqueued_at.is_some(),
-            "filtered_by_after_enqueued_at": params.after_enqueued_at.is_some(),
+            filtered_by_before_started_at: params.before_started_at.is_some(),
-            "filtered_by_before_started_at": params.before_started_at.is_some(),
+            filtered_by_after_started_at: params.after_started_at.is_some(),
-            "filtered_by_after_started_at": params.after_started_at.is_some(),
+            filtered_by_before_finished_at: params.before_finished_at.is_some(),
-            "filtered_by_before_finished_at": params.before_finished_at.is_some(),
+            filtered_by_after_finished_at: params.after_finished_at.is_some(),
-            "filtered_by_after_finished_at": params.after_finished_at.is_some(),
+
-        }),
+            marker: std::marker::PhantomData,
-        Some(&req),
+        },
+        &req,
     );
 
     let query = params.into_query();
@@ -214,7 +271,7 @@ async fn delete_tasks(
     params: AwebQueryParameter<TaskDeletionOrCancelationQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let params = params.into_inner();
 
@@ -223,22 +280,24 @@ async fn delete_tasks(
     }
 
     analytics.publish(
-        "Tasks Deleted".to_string(),
+        TaskFilterAnalytics::<DeleteTasks> {
-        json!({
+            filtered_by_uid: params.uids.is_some(),
-            "filtered_by_uid": params.uids.is_some(),
+            filtered_by_index_uid: params.index_uids.is_some(),
-            "filtered_by_index_uid": params.index_uids.is_some(),
+            filtered_by_type: params.types.is_some(),
-            "filtered_by_type": params.types.is_some(),
+            filtered_by_status: params.statuses.is_some(),
-            "filtered_by_status": params.statuses.is_some(),
+            filtered_by_canceled_by: params.canceled_by.is_some(),
-            "filtered_by_canceled_by": params.canceled_by.is_some(),
+            filtered_by_before_enqueued_at: params.before_enqueued_at.is_some(),
-            "filtered_by_before_enqueued_at": params.before_enqueued_at.is_some(),
+            filtered_by_after_enqueued_at: params.after_enqueued_at.is_some(),
-            "filtered_by_after_enqueued_at": params.after_enqueued_at.is_some(),
+            filtered_by_before_started_at: params.before_started_at.is_some(),
-            "filtered_by_before_started_at": params.before_started_at.is_some(),
+            filtered_by_after_started_at: params.after_started_at.is_some(),
-            "filtered_by_after_started_at": params.after_started_at.is_some(),
+            filtered_by_before_finished_at: params.before_finished_at.is_some(),
-            "filtered_by_before_finished_at": params.before_finished_at.is_some(),
+            filtered_by_after_finished_at: params.after_finished_at.is_some(),
-            "filtered_by_after_finished_at": params.after_finished_at.is_some(),
+
-        }),
+            marker: std::marker::PhantomData,
-        Some(&req),
+        },
+        &req,
     );
+
     let query = params.into_query();
 
     let (tasks, _) = index_scheduler.get_task_ids_from_authorized_indexes(

meilisearch/tests/common/server.rs

@@ -381,7 +381,6 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
         db_path: dir.as_ref().join("db"),
         dump_dir: dir.as_ref().join("dumps"),
         env: "development".to_owned(),
-        #[cfg(feature = "analytics")]
         no_analytics: true,
         max_index_size: Byte::from_u64_with_unit(100, Unit::MiB).unwrap(),
         max_task_db_size: Byte::from_u64_with_unit(1, Unit::GiB).unwrap(),

meilisearch/tests/common/service.rs

@@ -9,8 +9,9 @@ use actix_web::test;
 use actix_web::test::TestRequest;
 use actix_web::web::Data;
 use index_scheduler::IndexScheduler;
+use meilisearch::analytics::Analytics;
 use meilisearch::search_queue::SearchQueue;
-use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
+use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
 use meilisearch_auth::AuthController;
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::Layer;
@@ -141,7 +142,7 @@ impl Service {
             Data::new(search_queue),
             self.options.clone(),
             (route_layer_handle, stderr_layer_handle),
-            analytics::MockAnalytics::new(&self.options),
+            Data::new(Analytics::no_analytics()),
             true,
         ))
         .await

meilisearch/tests/logs/mod.rs

@@ -7,8 +7,9 @@ use std::str::FromStr;
 use actix_web::http::header::ContentType;
 use actix_web::web::Data;
 use meili_snap::snapshot;
+use meilisearch::analytics::Analytics;
 use meilisearch::search_queue::SearchQueue;
-use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
+use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::layer::SubscriberExt;
 use tracing_subscriber::Layer;
@@ -54,7 +55,7 @@ async fn basic_test_log_stream_route() {
         Data::new(search_queue),
         server.service.options.clone(),
         (route_layer_handle, stderr_layer_handle),
-        analytics::MockAnalytics::new(&server.service.options),
+        Data::new(Analytics::no_analytics()),
         true,
     ))
     .await;