Make Clippy happy

Cargo.lock

@@ -2730,6 +2730,7 @@ dependencies = [
  "geoutils",
  "grenad",
  "heed",
+ "indexmap",
  "insta",
  "itertools",
  "json-depth-checker",

index-scheduler/src/utils.rs

@@ -466,7 +466,7 @@ impl IndexScheduler {
                         }
                     }
                     Details::DocumentDeletionByFilter { deleted_documents, original_filter: _ } => {
-                        assert_eq!(kind.as_kind(), Kind::DocumentDeletion);
+                        assert_eq!(kind.as_kind(), Kind::DocumentDeletionByFilter);
                         let (index_uid, _) = if let KindWithContent::DocumentDeletionByFilter {
                             ref index_uid,
                             ref filter_expr,

meilisearch-types/src/error.rs

@@ -239,11 +239,8 @@ InvalidSearchMatchingStrategy         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchOffset                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
-InvalidFacetSearchQuery               , InvalidRequest       , BAD_REQUEST ;
-InvalidFacetSearchName                , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchFacet                    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
@@ -333,7 +330,6 @@ impl ErrorCode for milli::Error {
                     UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
                     UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
                     UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
-                    UserError::InvalidSearchFacet { .. } => Code::InvalidSearchFacet,
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::SortError(_) => Code::InvalidSearchSort,

meilisearch-types/src/tasks.rs

@@ -395,6 +395,7 @@ impl std::error::Error for ParseTaskStatusError {}
 pub enum Kind {
     DocumentAdditionOrUpdate,
     DocumentDeletion,
+    DocumentDeletionByFilter,
     SettingsUpdate,
     IndexCreation,
     IndexDeletion,
@@ -411,6 +412,7 @@ impl Kind {
         match self {
             Kind::DocumentAdditionOrUpdate
             | Kind::DocumentDeletion
+            | Kind::DocumentDeletionByFilter
             | Kind::SettingsUpdate
             | Kind::IndexCreation
             | Kind::IndexDeletion
@@ -428,6 +430,7 @@ impl Display for Kind {
         match self {
             Kind::DocumentAdditionOrUpdate => write!(f, "documentAdditionOrUpdate"),
             Kind::DocumentDeletion => write!(f, "documentDeletion"),
+            Kind::DocumentDeletionByFilter => write!(f, "documentDeletionByFilter"),
             Kind::SettingsUpdate => write!(f, "settingsUpdate"),
             Kind::IndexCreation => write!(f, "indexCreation"),
             Kind::IndexDeletion => write!(f, "indexDeletion"),

meilisearch/Cargo.toml

@@ -14,14 +14,27 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.6.4"
-actix-http = { version = "3.3.1", default-features = false, features = ["compress-brotli", "compress-gzip", "rustls"] }
-actix-web = { version = "4.3.1", default-features = false, features = ["macros", "compress-brotli", "compress-gzip", "cookies", "rustls"] }
+actix-http = { version = "3.3.1", default-features = false, features = [
+    "compress-brotli",
+    "compress-gzip",
+    "rustls",
+] }
+actix-web = { version = "4.3.1", default-features = false, features = [
+    "macros",
+    "compress-brotli",
+    "compress-gzip",
+    "cookies",
+    "rustls",
+] }
 actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
 anyhow = { version = "1.0.70", features = ["backtrace"] }
 async-stream = "0.3.5"
 async-trait = "0.1.68"
 bstr = "1.4.0"
-byte-unit = { version = "4.0.19", default-features = false, features = ["std", "serde"] }
+byte-unit = { version = "4.0.19", default-features = false, features = [
+    "std",
+    "serde",
+] }
 bytes = "1.4.0"
 clap = { version = "4.2.1", features = ["derive", "env"] }
 crossbeam-channel = "0.5.8"
@@ -56,7 +69,10 @@ prometheus = { version = "0.13.3", features = ["process"] }
 rand = "0.8.5"
 rayon = "1.7.0"
 regex = "1.7.3"
-reqwest = { version = "0.11.16", features = ["rustls-tls", "json"], default-features = false }
+reqwest = { version = "0.11.16", features = [
+    "rustls-tls",
+    "json",
+], default-features = false }
 rustls = "0.20.8"
 rustls-pemfile = "1.0.2"
 segment = { version = "0.2.2", optional = true }
@@ -70,7 +86,12 @@ sysinfo = "0.28.4"
 tar = "0.4.38"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.20", features = [
+    "serde-well-known",
+    "formatting",
+    "parsing",
+    "macros",
+] }
 tokio = { version = "1.27.0", features = ["full"] }
 tokio-stream = "0.1.12"
 toml = "0.7.3"
@@ -89,7 +110,7 @@ brotli = "3.3.4"
 insta = "1.29.0"
 manifest-dir-macros = "0.1.16"
 maplit = "1.0.2"
-meili-snap = {path = "../meili-snap"}
+meili-snap = { path = "../meili-snap" }
 temp-env = "0.3.3"
 urlencoding = "2.1.2"
 yaup = "0.2.1"
@@ -98,7 +119,10 @@ yaup = "0.2.1"
 anyhow = { version = "1.0.70", optional = true }
 cargo_toml = { version = "0.15.2", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.16", features = ["blocking", "rustls-tls"], default-features = false, optional = true }
+reqwest = { version = "0.11.16", features = [
+    "blocking",
+    "rustls-tls",
+], default-features = false, optional = true }
 sha-1 = { version = "0.10.1", optional = true }
 static-files = { version = "0.2.3", optional = true }
 tempfile = { version = "3.5.0", optional = true }
@@ -108,7 +132,17 @@ zip = { version = "0.6.4", optional = true }
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
-mini-dashboard = ["actix-web-static-files", "static-files", "anyhow", "cargo_toml", "hex", "reqwest", "sha-1", "tempfile", "zip"]
+mini-dashboard = [
+    "actix-web-static-files",
+    "static-files",
+    "anyhow",
+    "cargo_toml",
+    "hex",
+    "reqwest",
+    "sha-1",
+    "tempfile",
+    "zip",
+]
 chinese = ["meilisearch-types/chinese"]
 hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]

meilisearch/src/analytics/mock_analytics.rs

@@ -38,18 +38,6 @@ impl MultiSearchAggregator {
     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::default()
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
 impl MockAnalytics {
     #[allow(clippy::new_ret_no_self)]
     pub fn new(opt: &Opt) -> Arc<dyn Analytics> {
@@ -68,7 +56,6 @@ impl Analytics for MockAnalytics {
     fn get_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
-    fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
     fn add_documents(
         &self,
         _documents_query: &UpdateDocumentsQuery,

meilisearch/src/analytics/mod.rs

@@ -25,8 +25,6 @@ pub type SegmentAnalytics = mock_analytics::MockAnalytics;
 pub type SearchAggregator = mock_analytics::SearchAggregator;
 #[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(any(debug_assertions, not(feature = "analytics")))]
-pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
 // if we are in release mode and the feature analytics was enabled
 // we use the real analytics
@@ -36,8 +34,6 @@ pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
 pub type SearchAggregator = segment_analytics::SearchAggregator;
 #[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
-#[cfg(all(not(debug_assertions), feature = "analytics"))]
-pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
 
 /// The Meilisearch config dir:
 /// `~/.config/Meilisearch` on *NIX or *BSD.
@@ -92,9 +88,6 @@ pub trait Analytics: Sync + Send {
     /// 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 a add documents request
     fn add_documents(
         &self,

meilisearch/src/analytics/segment_analytics.rs

@@ -1,6 +1,5 @@
 use std::collections::{BinaryHeap, HashMap, HashSet};
 use std::fs;
-use std::mem::take;
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::time::{Duration, Instant};
@@ -30,13 +29,11 @@ use super::{
 use crate::analytics::Analytics;
 use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
-use crate::routes::indexes::facet_search::FacetSearchQuery;
 use crate::routes::tasks::TasksFilterQuery;
 use crate::routes::{create_all_stats, Stats};
 use crate::search::{
-    FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+    SearchQuery, SearchQueryWithIndex, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
 };
 use crate::Opt;
 
@@ -74,7 +71,6 @@ pub enum AnalyticsMsg {
     AggregateGetSearch(SearchAggregator),
     AggregatePostSearch(SearchAggregator),
     AggregatePostMultiSearch(MultiSearchAggregator),
-    AggregatePostFacetSearch(FacetSearchAggregator),
     AggregateAddDocuments(DocumentsAggregator),
     AggregateDeleteDocuments(DocumentsDeletionAggregator),
     AggregateUpdateDocuments(DocumentsAggregator),
@@ -143,7 +139,6 @@ impl SegmentAnalytics {
             batcher,
             post_search_aggregator: SearchAggregator::default(),
             post_multi_search_aggregator: MultiSearchAggregator::default(),
-            post_facet_search_aggregator: FacetSearchAggregator::default(),
             get_search_aggregator: SearchAggregator::default(),
             add_documents_aggregator: DocumentsAggregator::default(),
             delete_documents_aggregator: DocumentsDeletionAggregator::default(),
@@ -187,10 +182,6 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
     }
 
-    fn post_facet_search(&self, aggregate: FacetSearchAggregator) {
-        let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFacetSearch(aggregate));
-    }
-
     fn post_multi_search(&self, aggregate: MultiSearchAggregator) {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostMultiSearch(aggregate));
     }
@@ -363,7 +354,6 @@ pub struct Segment {
     get_search_aggregator: SearchAggregator,
     post_search_aggregator: SearchAggregator,
     post_multi_search_aggregator: MultiSearchAggregator,
-    post_facet_search_aggregator: FacetSearchAggregator,
     add_documents_aggregator: DocumentsAggregator,
     delete_documents_aggregator: DocumentsDeletionAggregator,
     update_documents_aggregator: DocumentsAggregator,
@@ -428,7 +418,6 @@ impl Segment {
                         Some(AnalyticsMsg::AggregateGetSearch(agreg)) => self.get_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostSearch(agreg)) => self.post_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostMultiSearch(agreg)) => self.post_multi_search_aggregator.aggregate(agreg),
-                        Some(AnalyticsMsg::AggregatePostFacetSearch(agreg)) => self.post_facet_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
@@ -472,72 +461,55 @@ impl Segment {
                 })
                 .await;
         }
+        let get_search = std::mem::take(&mut self.get_search_aggregator)
+            .into_event(&self.user, "Documents Searched GET");
+        let post_search = std::mem::take(&mut self.post_search_aggregator)
+            .into_event(&self.user, "Documents Searched POST");
+        let post_multi_search = std::mem::take(&mut self.post_multi_search_aggregator)
+            .into_event(&self.user, "Documents Searched by Multi-Search POST");
+        let add_documents = std::mem::take(&mut self.add_documents_aggregator)
+            .into_event(&self.user, "Documents Added");
+        let delete_documents = std::mem::take(&mut self.delete_documents_aggregator)
+            .into_event(&self.user, "Documents Deleted");
+        let update_documents = std::mem::take(&mut self.update_documents_aggregator)
+            .into_event(&self.user, "Documents Updated");
+        let get_fetch_documents = std::mem::take(&mut self.get_fetch_documents_aggregator)
+            .into_event(&self.user, "Documents Fetched GET");
+        let post_fetch_documents = std::mem::take(&mut self.post_fetch_documents_aggregator)
+            .into_event(&self.user, "Documents Fetched POST");
+        let get_tasks =
+            std::mem::take(&mut self.get_tasks_aggregator).into_event(&self.user, "Tasks Seen");
+        let health =
+            std::mem::take(&mut self.health_aggregator).into_event(&self.user, "Health Seen");
 
-        let Segment {
-            inbox: _,
-            opt: _,
-            batcher: _,
-            user,
-            get_search_aggregator,
-            post_search_aggregator,
-            post_multi_search_aggregator,
-            post_facet_search_aggregator,
-            add_documents_aggregator,
-            delete_documents_aggregator,
-            update_documents_aggregator,
-            get_fetch_documents_aggregator,
-            post_fetch_documents_aggregator,
-            get_tasks_aggregator,
-            health_aggregator,
-        } = self;
-
-        if let Some(get_search) =
-            take(get_search_aggregator).into_event(&user, "Documents Searched GET")
-        {
+        if let Some(get_search) = get_search {
             let _ = self.batcher.push(get_search).await;
         }
-        if let Some(post_search) =
-            take(post_search_aggregator).into_event(&user, "Documents Searched POST")
-        {
+        if let Some(post_search) = post_search {
             let _ = self.batcher.push(post_search).await;
         }
-        if let Some(post_multi_search) = take(post_multi_search_aggregator)
-            .into_event(&user, "Documents Searched by Multi-Search POST")
-        {
+        if let Some(post_multi_search) = post_multi_search {
             let _ = self.batcher.push(post_multi_search).await;
         }
-        if let Some(post_facet_search) = take(post_facet_search_aggregator)
-            .into_event(&user, "Documents Searched by Facet-Search POST")
-        {
-            let _ = self.batcher.push(post_facet_search).await;
-        }
-        if let Some(add_documents) =
-            take(add_documents_aggregator).into_event(&user, "Documents Added")
-        {
+        if let Some(add_documents) = add_documents {
             let _ = self.batcher.push(add_documents).await;
         }
-        if let Some(delete_documents) =
-            take(delete_documents_aggregator).into_event(&user, "Documents Deleted")
-        {
+        if let Some(delete_documents) = delete_documents {
             let _ = self.batcher.push(delete_documents).await;
         }
-        if let Some(update_documents) =
-            take(update_documents_aggregator).into_event(&user, "Documents Updated")
-        {
+        if let Some(update_documents) = update_documents {
             let _ = self.batcher.push(update_documents).await;
         }
-        if let Some(get_fetch_documents) =
-            take(get_fetch_documents_aggregator).into_event(&user, "Documents Fetched GET") {
+        if let Some(get_fetch_documents) = get_fetch_documents {
             let _ = self.batcher.push(get_fetch_documents).await;
         }
-        if let Some(post_fetch_documents) =
-            take(post_fetch_documents_aggregator).into_event(&user, "Documents Fetched POST") {
+        if let Some(post_fetch_documents) = post_fetch_documents {
             let _ = self.batcher.push(post_fetch_documents).await;
         }
-        if let Some(get_tasks) = take(get_tasks_aggregator).into_event(&user, "Tasks Seen") {
+        if let Some(get_tasks) = get_tasks {
             let _ = self.batcher.push(get_tasks).await;
         }
-        if let Some(health) = take(health_aggregator).into_event(&user, "Health Seen") {
+        if let Some(health) = health {
             let _ = self.batcher.push(health).await;
         }
         let _ = self.batcher.flush().await;
@@ -914,144 +886,6 @@ impl MultiSearchAggregator {
     }
 }
 
-#[derive(Default)]
-pub struct FacetSearchAggregator {
-    timestamp: Option<OffsetDateTime>,
-
-    // context
-    user_agents: HashSet<String>,
-
-    // 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 {
-    pub fn from_query(query: &FacetSearchQuery, request: &HttpRequest) -> Self {
-        let FacetSearchQuery {
-            facet_query: _,
-            facet_name,
-            q,
-            offset,
-            limit,
-            page,
-            hits_per_page,
-            attributes_to_retrieve,
-            attributes_to_crop,
-            crop_length,
-            attributes_to_highlight,
-            show_matches_position,
-            filter,
-            sort,
-            facets,
-            highlight_pre_tag,
-            highlight_post_tag,
-            crop_marker,
-            matching_strategy,
-        } = query;
-
-        let mut ret = Self::default();
-        ret.timestamp = Some(OffsetDateTime::now_utc());
-
-        ret.total_received = 1;
-        ret.user_agents = extract_user_agents(request).into_iter().collect();
-        ret.facet_names = Some(facet_name.clone()).into_iter().collect();
-
-        ret.additional_search_parameters_provided = q.is_some()
-            || *offset != DEFAULT_SEARCH_OFFSET()
-            || *limit != DEFAULT_SEARCH_LIMIT()
-            || page.is_some()
-            || hits_per_page.is_some()
-            || attributes_to_retrieve.is_some()
-            || attributes_to_crop.is_some()
-            || *crop_length != DEFAULT_CROP_LENGTH()
-            || attributes_to_highlight.is_some()
-            || *show_matches_position
-            || filter.is_some()
-            || sort.is_some()
-            || facets.is_some()
-            || *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG()
-            || *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG()
-            || *crop_marker != DEFAULT_CROP_MARKER()
-            || *matching_strategy != MatchingStrategy::default();
-
-        ret
-    }
-
-    pub fn succeed(&mut self, result: &FacetSearchResult) {
-        self.total_succeeded = self.total_succeeded.saturating_add(1);
-        self.time_spent.push(result.processing_time_ms as usize);
-    }
-
-    /// Aggregate one [SearchAggregator] into another.
-    pub fn aggregate(&mut self, mut other: Self) {
-        if self.timestamp.is_none() {
-            self.timestamp = other.timestamp;
-        }
-
-        // context
-        for user_agent in other.user_agents.into_iter() {
-            self.user_agents.insert(user_agent);
-        }
-
-        // request
-        self.total_received = self.total_received.saturating_add(other.total_received);
-        self.total_succeeded = self.total_succeeded.saturating_add(other.total_succeeded);
-        self.time_spent.append(&mut other.time_spent);
-
-        // facet_names
-        for facet_name in other.facet_names.into_iter() {
-            self.facet_names.insert(facet_name);
-        }
-
-        // additional_search_parameters_provided
-        self.additional_search_parameters_provided = self.additional_search_parameters_provided
-            | other.additional_search_parameters_provided;
-    }
-
-    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
-        if self.total_received == 0 {
-            None
-        } else {
-            // the index of the 99th percentage of value
-            let percentile_99th = 0.99 * (self.total_succeeded as f64 - 1.) + 1.;
-            // we get all the values in a sorted manner
-            let time_spent = self.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);
-
-            let properties = json!({
-                "user-agent": self.user_agents,
-                "requests": {
-                    "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
-                    "total_succeeded": self.total_succeeded,
-                    "total_failed": self.total_received.saturating_sub(self.total_succeeded), // just to be sure we never panics
-                    "total_received": self.total_received,
-                },
-                "facets": {
-                    "total_distinct_facet_count": self.facet_names.len(),
-                },
-                "additional_search_parameters_provided": self.additional_search_parameters_provided,
-            });
-
-            Some(Track {
-                timestamp: self.timestamp,
-                user: user.clone(),
-                event: event_name.to_string(),
-                properties,
-                ..Default::default()
-            })
-        }
-    }
-}
-
 #[derive(Default)]
 pub struct DocumentsAggregator {
     timestamp: Option<OffsetDateTime>,

meilisearch/src/routes/indexes/facet_search.rs

@@ -1,133 +0,0 @@
-use std::collections::{BTreeSet, HashSet};
-
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use deserr::actix_web::AwebJson;
-use index_scheduler::IndexScheduler;
-use log::debug;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::index_uid::IndexUid;
-use serde_json::Value;
-
-use crate::analytics::{Analytics, FacetSearchAggregator};
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::search::{
-    add_search_rules, perform_facet_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
-    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
-    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
-};
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(search)));
-}
-
-// TODO improve the error messages
-#[derive(Debug, Clone, Default, PartialEq, Eq, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
-pub struct FacetSearchQuery {
-    #[deserr(default, error = DeserrJsonError<InvalidFacetSearchQuery>)]
-    pub facet_query: Option<String>,
-    #[deserr(error = DeserrJsonError<InvalidFacetSearchName>)]
-    pub facet_name: String,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
-    pub q: Option<String>,
-    #[deserr(default = DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
-    pub offset: usize,
-    #[deserr(default = DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSearchLimit>)]
-    pub limit: usize,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchPage>)]
-    pub page: Option<usize>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchHitsPerPage>)]
-    pub hits_per_page: Option<usize>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToRetrieve>)]
-    pub attributes_to_retrieve: Option<BTreeSet<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToCrop>)]
-    pub attributes_to_crop: Option<Vec<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchCropLength>, default = DEFAULT_CROP_LENGTH())]
-    pub crop_length: usize,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToHighlight>)]
-    pub attributes_to_highlight: Option<HashSet<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchShowMatchesPosition>, default)]
-    pub show_matches_position: bool,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
-    pub filter: Option<Value>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchSort>)]
-    pub sort: Option<Vec<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchFacets>)]
-    pub facets: Option<Vec<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPreTag>, default = DEFAULT_HIGHLIGHT_PRE_TAG())]
-    pub highlight_pre_tag: String,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPostTag>, default = DEFAULT_HIGHLIGHT_POST_TAG())]
-    pub highlight_post_tag: String,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchCropMarker>, default = DEFAULT_CROP_MARKER())]
-    pub crop_marker: String,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
-    pub matching_strategy: MatchingStrategy,
-}
-
-pub async fn search(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    params: AwebJson<FacetSearchQuery, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let query = params.into_inner();
-    debug!("facet search called with params: {:?}", query);
-
-    let mut aggregate = FacetSearchAggregator::from_query(&query, &req);
-
-    let facet_query = query.facet_query.clone();
-    let facet_name = query.facet_name.clone();
-    let mut search_query = SearchQuery::from(query);
-
-    // Tenant token search_rules.
-    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut search_query, search_rules);
-    }
-
-    let index = index_scheduler.index(&index_uid)?;
-    let search_result = tokio::task::spawn_blocking(move || {
-        perform_facet_search(&index, search_query, facet_query, facet_name)
-    })
-    .await?;
-
-    if let Ok(ref search_result) = search_result {
-        aggregate.succeed(search_result);
-    }
-    analytics.post_facet_search(aggregate);
-
-    let search_result = search_result?;
-
-    debug!("returns: {:?}", search_result);
-    Ok(HttpResponse::Ok().json(search_result))
-}
-
-impl From<FacetSearchQuery> for SearchQuery {
-    fn from(value: FacetSearchQuery) -> Self {
-        SearchQuery {
-            q: value.q,
-            offset: value.offset,
-            limit: value.limit,
-            page: value.page,
-            hits_per_page: value.hits_per_page,
-            attributes_to_retrieve: value.attributes_to_retrieve,
-            attributes_to_crop: value.attributes_to_crop,
-            crop_length: value.crop_length,
-            attributes_to_highlight: value.attributes_to_highlight,
-            show_matches_position: value.show_matches_position,
-            filter: value.filter,
-            sort: value.sort,
-            facets: value.facets,
-            highlight_pre_tag: value.highlight_pre_tag,
-            highlight_post_tag: value.highlight_post_tag,
-            crop_marker: value.crop_marker,
-            matching_strategy: value.matching_strategy,
-        }
-    }
-}

meilisearch/src/routes/indexes/mod.rs

@@ -24,7 +24,6 @@ use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
 
 pub mod documents;
-pub mod facet_search;
 pub mod search;
 pub mod settings;
 
@@ -45,7 +44,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::resource("/stats").route(web::get().to(SeqHandler(get_index_stats))))
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
-            .service(web::scope("/facet-search").configure(facet_search::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }

meilisearch/src/routes/indexes/search.rs

@@ -16,9 +16,9 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::search::{
-    add_search_rules, perform_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
-    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
-    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+    add_search_rules, perform_search, FacetValuesSort, MatchingStrategy, SearchQuery,
+    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
 };
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
@@ -58,6 +58,8 @@ pub struct SearchQueryGet {
     show_matches_position: Param<bool>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchFacets>)]
     facets: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchFacets>)] // TODO
+    sort_facet_values_by: Option<FacetValuesSort>,
     #[deserr( default = DEFAULT_HIGHLIGHT_PRE_TAG(), error = DeserrQueryParamError<InvalidSearchHighlightPreTag>)]
     highlight_pre_tag: String,
     #[deserr( default = DEFAULT_HIGHLIGHT_POST_TAG(), error = DeserrQueryParamError<InvalidSearchHighlightPostTag>)]
@@ -92,6 +94,7 @@ impl From<SearchQueryGet> for SearchQuery {
             sort: other.sort.map(|attr| fix_sort_query_parameters(&attr)),
             show_matches_position: other.show_matches_position.0,
             facets: other.facets.map(|o| o.into_iter().collect()),
+            sort_facet_values_by: other.sort_facet_values_by,
             highlight_pre_tag: other.highlight_pre_tag,
             highlight_post_tag: other.highlight_post_tag,
             crop_marker: other.crop_marker,

meilisearch/src/routes/tasks.rs

@@ -730,7 +730,7 @@ mod tests {
             let err = deserr_query_params::<TaskDeletionOrCancelationQuery>(params).unwrap_err();
             snapshot!(meili_snap::json_string!(err), @r###"
             {
-              "message": "Invalid value in parameter `types`: `createIndex` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
+              "message": "Invalid value in parameter `types`: `createIndex` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `documentDeletionByFilter`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
               "code": "invalid_task_types",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_task_types"

meilisearch/src/search.rs

@@ -5,12 +5,12 @@ use std::time::Instant;
 
 use deserr::Deserr;
 use either::Either;
+use indexmap::IndexMap;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::milli::{FacetValueHit, SearchForFacetValues};
+use meilisearch_types::milli::OrderBy;
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::TokenizerBuilder;
@@ -62,6 +62,8 @@ pub struct SearchQuery {
     pub sort: Option<Vec<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchFacets>)]
     pub facets: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchFacets>)] // TODO
+    pub sort_facet_values_by: Option<FacetValuesSort>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPreTag>, default = DEFAULT_HIGHLIGHT_PRE_TAG())]
     pub highlight_pre_tag: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPostTag>, default = DEFAULT_HIGHLIGHT_POST_TAG())]
@@ -113,6 +115,8 @@ pub struct SearchQueryWithIndex {
     pub sort: Option<Vec<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchFacets>)]
     pub facets: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchFacets>)] // TODO
+    pub sort_facet_values_by: Option<FacetValuesSort>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPreTag>, default = DEFAULT_HIGHLIGHT_PRE_TAG())]
     pub highlight_pre_tag: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPostTag>, default = DEFAULT_HIGHLIGHT_POST_TAG())]
@@ -140,6 +144,7 @@ impl SearchQueryWithIndex {
             filter,
             sort,
             facets,
+            sort_facet_values_by,
             highlight_pre_tag,
             highlight_post_tag,
             crop_marker,
@@ -161,6 +166,7 @@ impl SearchQueryWithIndex {
                 filter,
                 sort,
                 facets,
+                sort_facet_values_by,
                 highlight_pre_tag,
                 highlight_post_tag,
                 crop_marker,
@@ -172,7 +178,7 @@ impl SearchQueryWithIndex {
     }
 }
 
-#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr)]
+#[derive(Debug, Clone, PartialEq, Eq, Deserr)]
 #[deserr(rename_all = camelCase)]
 pub enum MatchingStrategy {
     /// Remove query words from last to first
@@ -196,6 +202,26 @@ impl From<MatchingStrategy> for TermsMatchingStrategy {
     }
 }
 
+#[derive(Debug, Default, Clone, PartialEq, Eq, Deserr)]
+#[deserr(rename_all = camelCase)]
+pub enum FacetValuesSort {
+    /// Facet values are sorted in alphabetical order, ascending from A to Z.
+    #[default]
+    Alpha,
+    /// Facet values are sorted by decreasing count.
+    /// The count is the number of records containing this facet value in the results of the query.
+    Count,
+}
+
+impl From<FacetValuesSort> for OrderBy {
+    fn from(val: FacetValuesSort) -> Self {
+        match val {
+            FacetValuesSort::Alpha => OrderBy::Lexicographic,
+            FacetValuesSort::Count => OrderBy::Count,
+        }
+    }
+}
+
 #[derive(Debug, Clone, Serialize, PartialEq, Eq)]
 pub struct SearchHit {
     #[serde(flatten)]
@@ -215,7 +241,7 @@ pub struct SearchResult {
     #[serde(flatten)]
     pub hits_info: HitsInfo,
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub facet_distribution: Option<BTreeMap<String, BTreeMap<String, u64>>>,
+    pub facet_distribution: Option<BTreeMap<String, IndexMap<String, u64>>>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub facet_stats: Option<BTreeMap<String, FacetStats>>,
 }
@@ -243,14 +269,6 @@ pub struct FacetStats {
     pub max: f64,
 }
 
-#[derive(Serialize, Debug, Clone, PartialEq)]
-#[serde(rename_all = "camelCase")]
-pub struct FacetSearchResult {
-    pub hits: Vec<FacetValueHit>,
-    pub query: Option<String>,
-    pub processing_time_ms: u128,
-}
-
 /// Incorporate search rules in search query
 pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
     query.filter = match (query.filter.take(), rules.filter) {
@@ -271,12 +289,14 @@ pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
     }
 }
 
-fn prepare_search<'t>(
-    index: &'t Index,
-    rtxn: &'t RoTxn,
-    query: &'t SearchQuery,
-) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
-    let mut search = index.search(rtxn);
+pub fn perform_search(
+    index: &Index,
+    query: SearchQuery,
+) -> Result<SearchResult, MeilisearchHttpError> {
+    let before_search = Instant::now();
+    let rtxn = index.read_txn()?;
+
+    let mut search = index.search(&rtxn);
 
     if let Some(ref query) = query.q {
         search.query(query);
@@ -286,7 +306,7 @@ fn prepare_search<'t>(
     search.terms_matching_strategy(query.matching_strategy.into());
 
     let max_total_hits = index
-        .pagination_max_total_hits(rtxn)
+        .pagination_max_total_hits(&rtxn)
         .map_err(milli::Error::from)?
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
@@ -328,19 +348,6 @@ fn prepare_search<'t>(
         search.sort_criteria(sort);
     }
 
-    Ok((search, is_finite_pagination, max_total_hits, offset))
-}
-
-pub fn perform_search(
-    index: &Index,
-    query: SearchQuery,
-) -> Result<SearchResult, MeilisearchHttpError> {
-    let before_search = Instant::now();
-    let rtxn = index.read_txn()?;
-
-    let (search, is_finite_pagination, max_total_hits, offset) =
-        prepare_search(index, &rtxn, &query)?;
-
     let milli::SearchResult { documents_ids, matching_words, candidates, .. } = search.execute()?;
 
     let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
@@ -472,7 +479,10 @@ pub fn perform_search(
             if fields.iter().all(|f| f != "*") {
                 facet_distribution.facets(fields);
             }
-            let distribution = facet_distribution.candidates(candidates).execute()?;
+            let distribution = facet_distribution
+                .candidates(candidates)
+                .order_by(query.sort_facet_values_by.map_or_else(Default::default, Into::into))
+                .execute()?;
             let stats = facet_distribution.compute_stats()?;
             (Some(distribution), Some(stats))
         }
@@ -494,30 +504,6 @@ pub fn perform_search(
     Ok(result)
 }
 
-pub fn perform_facet_search(
-    index: &Index,
-    search_query: SearchQuery,
-    facet_query: Option<String>,
-    facet_name: String,
-) -> Result<FacetSearchResult, MeilisearchHttpError> {
-    let before_search = Instant::now();
-    let rtxn = index.read_txn()?;
-
-    let (search, _, _, _) = prepare_search(index, &rtxn, &search_query)?;
-    let mut facet_search = SearchForFacetValues::new(facet_name, search);
-    if let Some(facet_query) = &facet_query {
-        facet_search.query(facet_query);
-    }
-
-    let hits = facet_search.execute()?;
-
-    Ok(FacetSearchResult {
-        hits,
-        query: facet_query,
-        processing_time_ms: before_search.elapsed().as_millis(),
-    })
-}
-
 fn insert_geo_distance(sorts: &[String], document: &mut Document) {
     lazy_static::lazy_static! {
         static ref GEO_REGEX: Regex =

meilisearch/tests/tasks/errors.rs

@@ -97,7 +97,7 @@ async fn task_bad_types() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `types`: `doggo` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
+      "message": "Invalid value in parameter `types`: `doggo` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `documentDeletionByFilter`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
       "code": "invalid_task_types",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_task_types"
@@ -108,7 +108,7 @@ async fn task_bad_types() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `types`: `doggo` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
+      "message": "Invalid value in parameter `types`: `doggo` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `documentDeletionByFilter`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
       "code": "invalid_task_types",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_task_types"
@@ -119,7 +119,7 @@ async fn task_bad_types() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `types`: `doggo` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
+      "message": "Invalid value in parameter `types`: `doggo` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `documentDeletionByFilter`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
       "code": "invalid_task_types",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_task_types"

milli/Cargo.toml

@@ -32,6 +32,7 @@ heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.6", default-f
     "lmdb",
     "sync-read-txn",
 ] }
+indexmap = { version = "1.9.3", features = ["serde"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 memmap2 = "0.5.10"

milli/src/error.rs

@@ -124,16 +124,6 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
         }
     )]
     InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
-    #[error("Attribute `{}` is not filterable. {}",
-        .field,
-        match .valid_fields.is_empty() {
-            true => "This index does not have configured filterable attributes.".to_string(),
-            false => format!("Available filterable attributes are: `{}`.",
-                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
-                ),
-        }
-    )]
-    InvalidSearchFacet { field: String, valid_fields: BTreeSet<String> },
     #[error("{}", HeedError::BadOpenOptions)]
     InvalidLmdbOpenOptions,
     #[error("You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.")]

milli/src/heed_codec/fst_set_codec.rs

@@ -1,23 +0,0 @@
-use std::borrow::Cow;
-
-use fst::Set;
-use heed::{BytesDecode, BytesEncode};
-
-/// A codec for values of type `Set<&[u8]>`.
-pub struct FstSetCodec;
-
-impl<'a> BytesEncode<'a> for FstSetCodec {
-    type EItem = Set<Vec<u8>>;
-
-    fn bytes_encode(item: &'a Self::EItem) -> Option<Cow<'a, [u8]>> {
-        Some(Cow::Borrowed(item.as_fst().as_bytes()))
-    }
-}
-
-impl<'a> BytesDecode<'a> for FstSetCodec {
-    type DItem = Set<&'a [u8]>;
-
-    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
-        Set::new(bytes).ok()
-    }
-}

milli/src/heed_codec/mod.rs

@@ -2,7 +2,6 @@ mod beu32_str_codec;
 mod byte_slice_ref;
 pub mod facet;
 mod field_id_word_count_codec;
-mod fst_set_codec;
 mod obkv_codec;
 mod roaring_bitmap;
 mod roaring_bitmap_length;
@@ -16,7 +15,6 @@ pub use str_ref::StrRefCodec;
 
 pub use self::beu32_str_codec::BEU32StrCodec;
 pub use self::field_id_word_count_codec::FieldIdWordCountCodec;
-pub use self::fst_set_codec::FstSetCodec;
 pub use self::obkv_codec::ObkvCodec;
 pub use self::roaring_bitmap::{BoRoaringBitmapCodec, CboRoaringBitmapCodec, RoaringBitmapCodec};
 pub use self::roaring_bitmap_length::{

milli/src/index.rs

@@ -19,7 +19,7 @@ use crate::heed_codec::facet::{
     FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
     FieldIdCodec, OrderedF64Codec,
 };
-use crate::heed_codec::{FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
+use crate::heed_codec::{ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
 use crate::{
     default_criteria, BEU32StrCodec, BoRoaringBitmapCodec, CboRoaringBitmapCodec, Criterion,
     DocumentId, ExternalDocumentsIds, FacetDistribution, FieldDistribution, FieldId,
@@ -85,7 +85,6 @@ pub mod db_name {
     pub const FACET_ID_IS_NULL_DOCIDS: &str = "facet-id-is-null-docids";
     pub const FACET_ID_IS_EMPTY_DOCIDS: &str = "facet-id-is-empty-docids";
     pub const FACET_ID_STRING_DOCIDS: &str = "facet-id-string-docids";
-    pub const FACET_ID_STRING_FST: &str = "facet-id-string-fst";
     pub const FIELD_ID_DOCID_FACET_F64S: &str = "field-id-docid-facet-f64s";
     pub const FIELD_ID_DOCID_FACET_STRINGS: &str = "field-id-docid-facet-strings";
     pub const DOCUMENTS: &str = "documents";
@@ -148,8 +147,6 @@ pub struct Index {
     pub facet_id_f64_docids: Database<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>,
     /// Maps the facet field id and ranges of strings with the docids that corresponds to them.
     pub facet_id_string_docids: Database<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>,
-    /// Maps the facet field id of the string facets with an FST containing all the facets values.
-    pub facet_id_string_fst: Database<OwnedType<BEU16>, FstSetCodec>,
 
     /// Maps the document id, the facet field id and the numbers.
     pub field_id_docid_facet_f64s: Database<FieldDocIdFacetF64Codec, Unit>,
@@ -169,7 +166,7 @@ impl Index {
     ) -> Result<Index> {
         use db_name::*;
 
-        options.max_dbs(24);
+        options.max_dbs(23);
         unsafe { options.flag(Flags::MdbAlwaysFreePages) };
 
         let env = options.open(path)?;
@@ -200,13 +197,13 @@ impl Index {
         let facet_id_f64_docids = env.create_database(&mut wtxn, Some(FACET_ID_F64_DOCIDS))?;
         let facet_id_string_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_STRING_DOCIDS))?;
-        let facet_id_string_fst = env.create_database(&mut wtxn, Some(FACET_ID_STRING_FST))?;
         let facet_id_exists_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_EXISTS_DOCIDS))?;
         let facet_id_is_null_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_IS_NULL_DOCIDS))?;
         let facet_id_is_empty_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_IS_EMPTY_DOCIDS))?;
+
         let field_id_docid_facet_f64s =
             env.create_database(&mut wtxn, Some(FIELD_ID_DOCID_FACET_F64S))?;
         let field_id_docid_facet_strings =
@@ -235,7 +232,6 @@ impl Index {
             field_id_word_count_docids,
             facet_id_f64_docids,
             facet_id_string_docids,
-            facet_id_string_fst,
             facet_id_exists_docids,
             facet_id_is_null_docids,
             facet_id_is_empty_docids,

milli/src/lib.rs

@@ -99,9 +99,8 @@ pub use self::heed_codec::{
 };
 pub use self::index::Index;
 pub use self::search::{
-    FacetDistribution, FacetValueHit, Filter, FormatOptions, MatchBounds, MatcherBuilder,
-    MatchingWords, Search, SearchForFacetValues, SearchResult, TermsMatchingStrategy,
-    DEFAULT_VALUES_PER_FACET,
+    FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, OrderBy,
+    Search, SearchResult, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
 };
 
 pub type Result<T> = std::result::Result<T, error::Error>;

milli/src/search/facet/facet_distribution.rs

@@ -4,16 +4,18 @@ use std::{fmt, mem};
 
 use heed::types::ByteSlice;
 use heed::BytesDecode;
+use indexmap::IndexMap;
 use roaring::RoaringBitmap;
 
 use crate::error::UserError;
 use crate::facet::FacetType;
 use crate::heed_codec::facet::{
-    FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
-    OrderedF64Codec,
+    FacetGroupKeyCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec, OrderedF64Codec,
 };
 use crate::heed_codec::{ByteSliceRefCodec, StrRefCodec};
-use crate::search::facet::facet_distribution_iter;
+use crate::search::facet::facet_distribution_iter::{
+    count_iterate_over_facet_distribution, lexicographically_iterate_over_facet_distribution,
+};
 use crate::{FieldId, Index, Result};
 
 /// The default number of values by facets that will
@@ -24,10 +26,21 @@ pub const DEFAULT_VALUES_PER_FACET: usize = 100;
 /// the system to choose between one algorithm or another.
 const CANDIDATES_THRESHOLD: u64 = 3000;
 
+/// How should we fetch the facets?
+#[derive(Debug, Default, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
+pub enum OrderBy {
+    /// By lexicographic order...
+    #[default]
+    Lexicographic,
+    /// Or by number of docids in common?
+    Count,
+}
+
 pub struct FacetDistribution<'a> {
     facets: Option<HashSet<String>>,
     candidates: Option<RoaringBitmap>,
     max_values_per_facet: usize,
+    order_by: OrderBy,
     rtxn: &'a heed::RoTxn<'a>,
     index: &'a Index,
 }
@@ -38,6 +51,7 @@ impl<'a> FacetDistribution<'a> {
             facets: None,
             candidates: None,
             max_values_per_facet: DEFAULT_VALUES_PER_FACET,
+            order_by: OrderBy::default(),
             rtxn,
             index,
         }
@@ -53,6 +67,11 @@ impl<'a> FacetDistribution<'a> {
         self
     }
 
+    pub fn order_by(&mut self, order_by: OrderBy) -> &mut Self {
+        self.order_by = order_by;
+        self
+    }
+
     pub fn candidates(&mut self, candidates: RoaringBitmap) -> &mut Self {
         self.candidates = Some(candidates);
         self
@@ -65,7 +84,7 @@ impl<'a> FacetDistribution<'a> {
         field_id: FieldId,
         facet_type: FacetType,
         candidates: &RoaringBitmap,
-        distribution: &mut BTreeMap<String, u64>,
+        distribution: &mut IndexMap<String, u64>,
     ) -> heed::Result<()> {
         match facet_type {
             FacetType::Number => {
@@ -134,9 +153,15 @@ impl<'a> FacetDistribution<'a> {
         &self,
         field_id: FieldId,
         candidates: &RoaringBitmap,
-        distribution: &mut BTreeMap<String, u64>,
+        order_by: OrderBy,
+        distribution: &mut IndexMap<String, u64>,
     ) -> heed::Result<()> {
-        facet_distribution_iter::iterate_over_facet_distribution(
+        let search_function = match order_by {
+            OrderBy::Lexicographic => lexicographically_iterate_over_facet_distribution,
+            OrderBy::Count => count_iterate_over_facet_distribution,
+        };
+
+        search_function(
             self.rtxn,
             self.index
                 .facet_id_f64_docids
@@ -159,9 +184,15 @@ impl<'a> FacetDistribution<'a> {
         &self,
         field_id: FieldId,
         candidates: &RoaringBitmap,
-        distribution: &mut BTreeMap<String, u64>,
+        order_by: OrderBy,
+        distribution: &mut IndexMap<String, u64>,
     ) -> heed::Result<()> {
-        facet_distribution_iter::iterate_over_facet_distribution(
+        let search_function = match order_by {
+            OrderBy::Lexicographic => lexicographically_iterate_over_facet_distribution,
+            OrderBy::Count => count_iterate_over_facet_distribution,
+        };
+
+        search_function(
             self.rtxn,
             self.index
                 .facet_id_string_docids
@@ -189,93 +220,44 @@ impl<'a> FacetDistribution<'a> {
         )
     }
 
-    /// Placeholder search, a.k.a. no candidates were specified. We iterate throught the
-    /// facet values one by one and iterate on the facet level 0 for numbers.
-    fn facet_values_from_raw_facet_database(
-        &self,
-        field_id: FieldId,
-    ) -> heed::Result<BTreeMap<String, u64>> {
-        let mut distribution = BTreeMap::new();
-
-        let db = self.index.facet_id_f64_docids;
-        let mut prefix = vec![];
-        prefix.extend_from_slice(&field_id.to_be_bytes());
-        prefix.push(0); // read values from level 0 only
-
-        let iter = db
-            .as_polymorph()
-            .prefix_iter::<_, ByteSlice, ByteSlice>(self.rtxn, prefix.as_slice())?
-            .remap_types::<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>();
-
-        for result in iter {
-            let (key, value) = result?;
-            distribution.insert(key.left_bound.to_string(), value.bitmap.len());
-            if distribution.len() == self.max_values_per_facet {
-                break;
-            }
-        }
-
-        let iter = self
-            .index
-            .facet_id_string_docids
-            .as_polymorph()
-            .prefix_iter::<_, ByteSlice, ByteSlice>(self.rtxn, prefix.as_slice())?
-            .remap_types::<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>();
-
-        for result in iter {
-            let (key, value) = result?;
-
-            let docid = value.bitmap.iter().next().unwrap();
-            let key: (FieldId, _, &'a str) = (field_id, docid, key.left_bound);
-            let original_string =
-                self.index.field_id_docid_facet_strings.get(self.rtxn, &key)?.unwrap().to_owned();
-
-            distribution.insert(original_string, value.bitmap.len());
-            if distribution.len() == self.max_values_per_facet {
-                break;
-            }
-        }
-
-        Ok(distribution)
-    }
-
-    fn facet_values(&self, field_id: FieldId) -> heed::Result<BTreeMap<String, u64>> {
+    fn facet_values(&self, field_id: FieldId) -> heed::Result<IndexMap<String, u64>> {
         use FacetType::{Number, String};
 
-        match self.candidates {
-            Some(ref candidates) => {
+        let mut distribution = IndexMap::new();
+        match (self.order_by, &self.candidates) {
+            (OrderBy::Lexicographic, Some(cnd)) if cnd.len() <= CANDIDATES_THRESHOLD => {
                 // Classic search, candidates were specified, we must return facet values only related
                 // to those candidates. We also enter here for facet strings for performance reasons.
-                let mut distribution = BTreeMap::new();
-                if candidates.len() <= CANDIDATES_THRESHOLD {
-                    self.facet_distribution_from_documents(
-                        field_id,
-                        Number,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                    self.facet_distribution_from_documents(
-                        field_id,
-                        String,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                } else {
-                    self.facet_numbers_distribution_from_facet_levels(
-                        field_id,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                    self.facet_strings_distribution_from_facet_levels(
-                        field_id,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                }
-                Ok(distribution)
+                self.facet_distribution_from_documents(field_id, Number, cnd, &mut distribution)?;
+                self.facet_distribution_from_documents(field_id, String, cnd, &mut distribution)?;
             }
-            None => self.facet_values_from_raw_facet_database(field_id),
-        }
+            _ => {
+                let universe;
+                let candidates;
+                match &self.candidates {
+                    Some(cnd) => candidates = cnd,
+                    None => {
+                        universe = self.index.documents_ids(self.rtxn)?;
+                        candidates = &universe;
+                    }
+                }
+
+                self.facet_numbers_distribution_from_facet_levels(
+                    field_id,
+                    candidates,
+                    self.order_by,
+                    &mut distribution,
+                )?;
+                self.facet_strings_distribution_from_facet_levels(
+                    field_id,
+                    candidates,
+                    self.order_by,
+                    &mut distribution,
+                )?;
+            }
+        };
+
+        Ok(distribution)
     }
 
     pub fn compute_stats(&self) -> Result<BTreeMap<String, (f64, f64)>> {
@@ -337,7 +319,7 @@ impl<'a> FacetDistribution<'a> {
         Ok(distribution)
     }
 
-    pub fn execute(&self) -> Result<BTreeMap<String, BTreeMap<String, u64>>> {
+    pub fn execute(&self) -> Result<BTreeMap<String, IndexMap<String, u64>>> {
         let fields_ids_map = self.index.fields_ids_map(self.rtxn)?;
         let filterable_fields = self.index.filterable_fields(self.rtxn)?;
 
@@ -374,13 +356,20 @@ impl<'a> FacetDistribution<'a> {
 
 impl fmt::Debug for FacetDistribution<'_> {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        let FacetDistribution { facets, candidates, max_values_per_facet, rtxn: _, index: _ } =
-            self;
+        let FacetDistribution {
+            facets,
+            candidates,
+            max_values_per_facet,
+            order_by,
+            rtxn: _,
+            index: _,
+        } = self;
 
         f.debug_struct("FacetDistribution")
             .field("facets", facets)
             .field("candidates", candidates)
             .field("max_values_per_facet", max_values_per_facet)
+            .field("order_by", order_by)
             .finish()
     }
 }

milli/src/search/facet/facet_distribution_iter.rs

@@ -1,3 +1,5 @@
+use std::cmp::Reverse;
+use std::collections::BinaryHeap;
 use std::ops::ControlFlow;
 
 use heed::Result;
@@ -19,7 +21,7 @@ use crate::DocumentId;
 ///
 /// The return value of the closure is a `ControlFlow<()>` which indicates whether we should
 /// keep iterating over the different facet values or stop.
-pub fn iterate_over_facet_distribution<'t, CB>(
+pub fn lexicographically_iterate_over_facet_distribution<'t, CB>(
     rtxn: &'t heed::RoTxn<'t>,
     db: heed::Database<FacetGroupKeyCodec<ByteSliceRefCodec>, FacetGroupValueCodec>,
     field_id: u16,
@@ -29,7 +31,7 @@ pub fn iterate_over_facet_distribution<'t, CB>(
 where
     CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
 {
-    let mut fd = FacetDistribution { rtxn, db, field_id, callback };
+    let mut fd = LexicographicFacetDistribution { rtxn, db, field_id, callback };
     let highest_level = get_highest_level(
         rtxn,
         db.remap_key_type::<FacetGroupKeyCodec<ByteSliceRefCodec>>(),
@@ -44,7 +46,99 @@ where
     }
 }
 
-struct FacetDistribution<'t, CB>
+pub fn count_iterate_over_facet_distribution<'t, CB>(
+    rtxn: &'t heed::RoTxn<'t>,
+    db: heed::Database<FacetGroupKeyCodec<ByteSliceRefCodec>, FacetGroupValueCodec>,
+    field_id: u16,
+    candidates: &RoaringBitmap,
+    mut callback: CB,
+) -> Result<()>
+where
+    CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
+{
+    #[derive(Debug, PartialOrd, Ord, PartialEq, Eq)]
+    struct LevelEntry<'t> {
+        /// The number of candidates in this entry.
+        count: u64,
+        /// The key level of the entry.
+        level: Reverse<u8>,
+        /// The left bound key.
+        left_bound: &'t [u8],
+        /// The number of keys we must look for after `left_bound`.
+        group_size: u8,
+        /// Any docid in the set of matching documents. Used to find the original facet string.
+        any_docid: u32,
+    }
+
+    // Represents the list of keys that we must explore.
+    let mut heap = BinaryHeap::new();
+    let highest_level = get_highest_level(
+        rtxn,
+        db.remap_key_type::<FacetGroupKeyCodec<ByteSliceRefCodec>>(),
+        field_id,
+    )?;
+
+    if let Some(first_bound) = get_first_facet_value::<ByteSliceRefCodec>(rtxn, db, field_id)? {
+        // We first fill the heap with values from the highest level
+        let starting_key =
+            FacetGroupKey { field_id, level: highest_level, left_bound: first_bound };
+        for el in db.range(rtxn, &(&starting_key..)).unwrap().take(usize::MAX) {
+            let (key, value) = el.unwrap();
+            // The range is unbounded on the right and the group size for the highest level is MAX,
+            // so we need to check that we are not iterating over the next field id
+            if key.field_id != field_id {
+                break;
+            }
+            let intersection = value.bitmap & candidates;
+            let count = intersection.len();
+            if count != 0 {
+                heap.push(LevelEntry {
+                    count,
+                    level: Reverse(key.level),
+                    left_bound: key.left_bound,
+                    group_size: value.size,
+                    any_docid: intersection.min().unwrap(),
+                });
+            }
+        }
+
+        while let Some(LevelEntry { count, level, left_bound, group_size, any_docid }) = heap.pop()
+        {
+            if let Reverse(0) = level {
+                match (callback)(left_bound, count, any_docid)? {
+                    ControlFlow::Continue(_) => (),
+                    ControlFlow::Break(_) => return Ok(()),
+                }
+            } else {
+                let starting_key = FacetGroupKey { field_id, level: level.0 - 1, left_bound };
+                for el in db.range(rtxn, &(&starting_key..)).unwrap().take(group_size as usize) {
+                    let (key, value) = el.unwrap();
+                    // The range is unbounded on the right and the group size for the highest level is MAX,
+                    // so we need to check that we are not iterating over the next field id
+                    if key.field_id != field_id {
+                        break;
+                    }
+                    let intersection = value.bitmap & candidates;
+                    let count = intersection.len();
+                    if count != 0 {
+                        heap.push(LevelEntry {
+                            count,
+                            level: Reverse(key.level),
+                            left_bound: key.left_bound,
+                            group_size: value.size,
+                            any_docid: intersection.min().unwrap(),
+                        });
+                    }
+                }
+            }
+        }
+    }
+
+    Ok(())
+}
+
+/// Iterate over the facets values by lexicographic order.
+struct LexicographicFacetDistribution<'t, CB>
 where
     CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
 {
@@ -54,7 +148,7 @@ where
     callback: CB,
 }
 
-impl<'t, CB> FacetDistribution<'t, CB>
+impl<'t, CB> LexicographicFacetDistribution<'t, CB>
 where
     CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
 {
@@ -86,6 +180,7 @@ where
         }
         Ok(ControlFlow::Continue(()))
     }
+
     fn iterate(
         &mut self,
         candidates: &RoaringBitmap,
@@ -116,7 +211,7 @@ where
                     value.size as usize,
                 )?;
                 match cf {
-                    ControlFlow::Continue(_) => {}
+                    ControlFlow::Continue(_) => (),
                     ControlFlow::Break(_) => return Ok(ControlFlow::Break(())),
                 }
             }
@@ -132,7 +227,7 @@ mod tests {
     use heed::BytesDecode;
     use roaring::RoaringBitmap;
 
-    use super::iterate_over_facet_distribution;
+    use super::lexicographically_iterate_over_facet_distribution;
     use crate::heed_codec::facet::OrderedF64Codec;
     use crate::milli_snap;
     use crate::search::facet::tests::{get_random_looking_index, get_simple_index};
@@ -144,7 +239,7 @@ mod tests {
             let txn = index.env.read_txn().unwrap();
             let candidates = (0..=255).collect::<RoaringBitmap>();
             let mut results = String::new();
-            iterate_over_facet_distribution(
+            lexicographically_iterate_over_facet_distribution(
                 &txn,
                 index.content,
                 0,
@@ -161,6 +256,7 @@ mod tests {
             txn.commit().unwrap();
         }
     }
+
     #[test]
     fn filter_distribution_all_stop_early() {
         let indexes = [get_simple_index(), get_random_looking_index()];
@@ -169,7 +265,7 @@ mod tests {
             let candidates = (0..=255).collect::<RoaringBitmap>();
             let mut results = String::new();
             let mut nbr_facets = 0;
-            iterate_over_facet_distribution(
+            lexicographically_iterate_over_facet_distribution(
                 &txn,
                 index.content,
                 0,

milli/src/search/facet/mod.rs

@@ -4,7 +4,7 @@ use heed::types::{ByteSlice, DecodeIgnore};
 use heed::{BytesDecode, RoTxn};
 use roaring::RoaringBitmap;
 
-pub use self::facet_distribution::{FacetDistribution, DEFAULT_VALUES_PER_FACET};
+pub use self::facet_distribution::{FacetDistribution, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::filter::{BadGeoError, Filter};
 use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec, OrderedF64Codec};
 use crate::heed_codec::ByteSliceRefCodec;

milli/src/search/mod.rs

@@ -1,20 +1,14 @@
 use std::fmt;
 
-use fst::automaton::{Automaton, Str};
-use fst::{IntoStreamer, Streamer};
 use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
-use log::error;
 use once_cell::sync::Lazy;
 use roaring::bitmap::RoaringBitmap;
 
-pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET};
+pub use self::facet::{FacetDistribution, Filter, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::new::matches::{FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWords};
 use self::new::PartialSearchResult;
-use crate::error::UserError;
-use crate::heed_codec::facet::{FacetGroupKey, FacetGroupValue};
 use crate::{
-    execute_search, AscDesc, DefaultSearchLogger, DocumentId, FieldIdMapMissingEntry, Index,
-    Result, SearchContext, BEU16,
+    execute_search, AscDesc, DefaultSearchLogger, DocumentId, Index, Result, SearchContext,
 };
 
 // Building these factories is not free.
@@ -22,9 +16,6 @@ static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true));
 static LEVDIST1: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(1, true));
 static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true));
 
-/// The maximum number of facets returned by the facet search route.
-const MAX_NUMBER_OF_FACETS: usize = 100;
-
 pub mod facet;
 mod fst_utils;
 pub mod new;
@@ -208,174 +199,6 @@ pub fn build_dfa(word: &str, typos: u8, is_prefix: bool) -> DFA {
     }
 }
 
-pub struct SearchForFacetValues<'a> {
-    query: Option<String>,
-    facet: String,
-    search_query: Search<'a>,
-}
-
-impl<'a> SearchForFacetValues<'a> {
-    pub fn new(facet: String, search_query: Search<'a>) -> SearchForFacetValues<'a> {
-        SearchForFacetValues { query: None, facet, search_query }
-    }
-
-    pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
-        self.query = Some(query.into());
-        self
-    }
-
-    pub fn execute(&self) -> Result<Vec<FacetValueHit>> {
-        let index = self.search_query.index;
-        let rtxn = self.search_query.rtxn;
-
-        let filterable_fields = index.filterable_fields(rtxn)?;
-        if !filterable_fields.contains(&self.facet) {
-            return Err(UserError::InvalidSearchFacet {
-                field: self.facet.clone(),
-                valid_fields: filterable_fields.into_iter().collect(),
-            }
-            .into());
-        }
-
-        let fields_ids_map = index.fields_ids_map(rtxn)?;
-        let fid = match fields_ids_map.id(&self.facet) {
-            Some(fid) => fid,
-            None => {
-                return Err(FieldIdMapMissingEntry::FieldName {
-                    field_name: self.facet.clone(),
-                    process: "search for facet values",
-                }
-                .into());
-            }
-        };
-
-        let fst = match self.search_query.index.facet_id_string_fst.get(rtxn, &BEU16::new(fid))? {
-            Some(fst) => fst,
-            None => return Ok(vec![]),
-        };
-
-        let search_candidates = self.search_query.execute()?.candidates;
-
-        match self.query.as_ref() {
-            Some(query) => {
-                let authorize_typos = self.search_query.index.authorize_typos(rtxn)?;
-                let field_authorizes_typos =
-                    !self.search_query.index.exact_attributes_ids(rtxn)?.contains(&fid);
-
-                if authorize_typos && field_authorizes_typos {
-                    let mut results = vec![];
-
-                    let exact_words_fst = self.search_query.index.exact_words(rtxn)?;
-                    if exact_words_fst.map_or(false, |fst| fst.contains(query)) {
-                        let key =
-                            FacetGroupKey { field_id: fid, level: 0, left_bound: query.as_ref() };
-                        if let Some(FacetGroupValue { bitmap, .. }) =
-                            index.facet_id_string_docids.get(rtxn, &key)?
-                        {
-                            let count = search_candidates.intersection_len(&bitmap);
-                            if count != 0 {
-                                results.push(FacetValueHit { value: query.to_string(), count });
-                            }
-                        }
-                    } else {
-                        let one_typo = self.search_query.index.min_word_len_one_typo(rtxn)?;
-                        let two_typos = self.search_query.index.min_word_len_two_typos(rtxn)?;
-
-                        let is_prefix = true;
-                        let automaton = if query.len() < one_typo as usize {
-                            build_dfa(query, 0, is_prefix)
-                        } else if query.len() < two_typos as usize {
-                            build_dfa(query, 1, is_prefix)
-                        } else {
-                            build_dfa(query, 2, is_prefix)
-                        };
-
-                        let mut stream = fst.search(automaton).into_stream();
-                        let mut length = 0;
-                        while let Some(facet_value) = stream.next() {
-                            let value = std::str::from_utf8(facet_value)?;
-                            let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
-                            let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
-                                Some(FacetGroupValue { bitmap, .. }) => bitmap,
-                                None => {
-                                    error!(
-                                        "the facet value is missing from the facet database: {key:?}"
-                                    );
-                                    continue;
-                                }
-                            };
-                            let count = search_candidates.intersection_len(&docids);
-                            if count != 0 {
-                                results.push(FacetValueHit { value: value.to_string(), count });
-                                length += 1;
-                            }
-                            if length >= MAX_NUMBER_OF_FACETS {
-                                break;
-                            }
-                        }
-                    }
-
-                    Ok(results)
-                } else {
-                    let automaton = Str::new(query).starts_with();
-                    let mut stream = fst.search(automaton).into_stream();
-                    let mut results = vec![];
-                    let mut length = 0;
-                    while let Some(facet_value) = stream.next() {
-                        let value = std::str::from_utf8(facet_value)?;
-                        let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
-                        let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
-                            Some(FacetGroupValue { bitmap, .. }) => bitmap,
-                            None => {
-                                error!(
-                                    "the facet value is missing from the facet database: {key:?}"
-                                );
-                                continue;
-                            }
-                        };
-                        let count = search_candidates.intersection_len(&docids);
-                        if count != 0 {
-                            results.push(FacetValueHit { value: value.to_string(), count });
-                            length += 1;
-                        }
-                        if length >= MAX_NUMBER_OF_FACETS {
-                            break;
-                        }
-                    }
-
-                    Ok(results)
-                }
-            }
-            None => {
-                let mut results = vec![];
-                let mut length = 0;
-                let prefix = FacetGroupKey { field_id: fid, level: 0, left_bound: "" };
-                for result in index.facet_id_string_docids.prefix_iter(rtxn, &prefix)? {
-                    let (FacetGroupKey { left_bound, .. }, FacetGroupValue { bitmap, .. }) =
-                        result?;
-                    let count = search_candidates.intersection_len(&bitmap);
-                    if count != 0 {
-                        results.push(FacetValueHit { value: left_bound.to_string(), count });
-                        length += 1;
-                    }
-                    if length >= MAX_NUMBER_OF_FACETS {
-                        break;
-                    }
-                }
-                Ok(results)
-            }
-        }
-    }
-}
-
-#[derive(Debug, Clone, serde::Serialize, PartialEq)]
-pub struct FacetValueHit {
-    /// The original facet value
-    pub value: String,
-    /// The number of documents associated to this facet
-    pub count: u64,
-}
-
 #[cfg(test)]
 mod test {
     #[allow(unused_imports)]

milli/src/search/new/query_term/parse_query.rs

@@ -77,9 +77,13 @@ pub fn located_query_terms_from_tokens(
                 }
             }
             TokenKind::Separator(separator_kind) => {
-                // add penalty for hard separators
-                if let SeparatorKind::Hard = separator_kind {
-                    position = position.wrapping_add(1);
+                match separator_kind {
+                    SeparatorKind::Hard => {
+                        position += 1;
+                    }
+                    SeparatorKind::Soft => {
+                        position += 0;
+                    }
                 }
 
                 phrase = 'phrase: {
@@ -284,36 +288,3 @@ impl PhraseBuilder {
         })
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use charabia::TokenizerBuilder;
-
-    use super::*;
-    use crate::index::tests::TempIndex;
-
-    fn temp_index_with_documents() -> TempIndex {
-        let temp_index = TempIndex::new();
-        temp_index
-            .add_documents(documents!([
-                { "id": 1, "name": "split this world westfali westfalia the Ŵôřlḑôle" },
-                { "id": 2, "name": "Westfália" },
-                { "id": 3, "name": "Ŵôřlḑôle" },
-            ]))
-            .unwrap();
-        temp_index
-    }
-
-    #[test]
-    fn start_with_hard_separator() -> Result<()> {
-        let tokenizer = TokenizerBuilder::new().build();
-        let tokens = tokenizer.tokenize(".");
-        let index = temp_index_with_documents();
-        let rtxn = index.read_txn()?;
-        let mut ctx = SearchContext::new(&index, &rtxn);
-        // panics with `attempt to add with overflow` before <https://github.com/meilisearch/meilisearch/issues/3785>
-        let located_query_terms = located_query_terms_from_tokens(&mut ctx, tokens, None)?;
-        assert!(located_query_terms.is_empty());
-        Ok(())
-    }
-}

milli/src/update/clear_documents.rs

@@ -35,7 +35,6 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
             script_language_docids,
             facet_id_f64_docids,
             facet_id_string_docids,
-            facet_id_string_fst: _,
             facet_id_exists_docids,
             facet_id_is_null_docids,
             facet_id_is_empty_docids,

milli/src/update/delete_documents.rs

@@ -243,7 +243,6 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             word_prefix_fid_docids,
             facet_id_f64_docids: _,
             facet_id_string_docids: _,
-            facet_id_string_fst: _,
             field_id_docid_facet_f64s: _,
             field_id_docid_facet_strings: _,
             script_language_docids,

milli/src/update/facet/mod.rs

@@ -78,16 +78,15 @@ pub const FACET_MIN_LEVEL_SIZE: u8 = 5;
 
 use std::fs::File;
 
-use heed::types::DecodeIgnore;
 use log::debug;
 use time::OffsetDateTime;
 
 use self::incremental::FacetsUpdateIncremental;
 use super::FacetsUpdateBulk;
 use crate::facet::FacetType;
-use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValueCodec};
+use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec};
 use crate::heed_codec::ByteSliceRefCodec;
-use crate::{Index, Result, BEU16};
+use crate::{Index, Result};
 
 pub mod bulk;
 pub mod delete;
@@ -158,43 +157,6 @@ impl<'i> FacetsUpdate<'i> {
             );
             incremental_update.execute(wtxn)?;
         }
-
-        // We compute one FST by string facet
-        let mut text_fsts = vec![];
-        let mut current_fst: Option<(u16, fst::SetBuilder<Vec<u8>>)> = None;
-        let database = self.index.facet_id_string_docids.remap_data_type::<DecodeIgnore>();
-        for result in database.iter(wtxn)? {
-            let (facet_group_key, _) = result?;
-            if let FacetGroupKey { field_id, level: 0, left_bound } = facet_group_key {
-                current_fst = match current_fst.take() {
-                    Some((fid, fst_builder)) if fid != field_id => {
-                        let fst = fst_builder.into_set();
-                        text_fsts.push((field_id, fst));
-                        Some((field_id, fst::SetBuilder::memory()))
-                    }
-                    Some((field_id, fst_builder)) => Some((field_id, fst_builder)),
-                    None => Some((field_id, fst::SetBuilder::memory())),
-                };
-
-                if let Some((_, fst_builder)) = current_fst.as_mut() {
-                    fst_builder.insert(left_bound)?;
-                }
-            }
-        }
-
-        if let Some((field_id, fst_builder)) = current_fst {
-            let fst = fst_builder.into_set();
-            text_fsts.push((field_id, fst));
-        }
-
-        // We remove all of the previous FSTs that were in this database
-        self.index.facet_id_string_fst.clear(wtxn)?;
-
-        // We write those FSTs in LMDB now
-        for (field_id, fst) in text_fsts {
-            self.index.facet_id_string_fst.put(wtxn, &BEU16::new(field_id), &fst)?;
-        }
-
         Ok(())
     }
 }

milli/src/update/facets.rs

@@ -0,0 +1 @@
+