Merge #4476

4476: Make the `/facet-search` route use the `sortFacetValuesBy` setting r=irevoire a=Kerollmops

This PR fixes #4423 by ensuring that the `/facet-search` route uses the `sortFacetValuesBy` setting.

Note for the documentation team (to be moved in the tracking issue): Using the new `sortFacetValuesBy` setting can slow down the facet-search requests as Meilisearch iterates over the whole list of facet values and computes the count of documents on every entry. That is hardly or even impossible to optimize correctly.

### TODO
 - [x] Create a custom HashMap wrapper for the facet `OrderBy` settings.
         This wrapper will return the `OrderBy` setting of the facet, if not defined will use the default `*` one, and if not there either (strange) will fall back on the lexicographic one.
- [x] Create a `ValuesCollection` wrapper that implements the logic for the lexicographic and count order by.
  - [x] Use it when there is no search query.
  - [x] Use it when there is a search query with and without allowed typos.
  - [x] Do not change the original logic, only use a wrapper.
- [x] Add tests

Co-authored-by: Clément Renault <clement@meilisearch.com>

meilisearch/src/search.rs

@@ -671,27 +671,16 @@ pub fn perform_search(
 
             let sort_facet_values_by =
                 index.sort_facet_values_by(&rtxn).map_err(milli::Error::from)?;
-            let default_sort_facet_values_by =
-                sort_facet_values_by.get("*").copied().unwrap_or_default();
 
             if fields.iter().all(|f| f != "*") {
-                let fields: Vec<_> = fields
+                let fields: Vec<_> =
-                    .iter()
+                    fields.iter().map(|n| (n, sort_facet_values_by.get(n))).collect();
-                    .map(|n| {
-                        (
-                            n,
-                            sort_facet_values_by
-                                .get(n)
-                                .copied()
-                                .unwrap_or(default_sort_facet_values_by),
-                        )
-                    })
-                    .collect();
                 facet_distribution.facets(fields);
             }
+
             let distribution = facet_distribution
                 .candidates(candidates)
-                .default_order_by(default_sort_facet_values_by)
+                .default_order_by(sort_facet_values_by.get("*"))
                 .execute()?;
             let stats = facet_distribution.compute_stats()?;
             (Some(distribution), Some(stats))

meilisearch/tests/search/facet_search.rs

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

milli/src/index.rs

@@ -20,13 +20,13 @@ use crate::heed_codec::facet::{
 use crate::heed_codec::{
     BEU16StrCodec, FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec,
 };
+use crate::order_by_map::OrderByMap;
 use crate::proximity::ProximityPrecision;
 use crate::vector::EmbeddingConfig;
 use crate::{
     default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
     FacetDistribution, FieldDistribution, FieldId, FieldIdWordCountCodec, GeoPoint, ObkvCodec,
-    OrderBy, Result, RoaringBitmapCodec, RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16,
+    Result, RoaringBitmapCodec, RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16, BEU32, BEU64,
-    BEU32, BEU64,
 };
 
 pub const DEFAULT_MIN_WORD_LEN_ONE_TYPO: u8 = 5;
@@ -1373,21 +1373,19 @@ impl Index {
         self.main.remap_key_type::<Str>().delete(txn, main_key::MAX_VALUES_PER_FACET)
     }
 
-    pub fn sort_facet_values_by(&self, txn: &RoTxn) -> heed::Result<HashMap<String, OrderBy>> {
+    pub fn sort_facet_values_by(&self, txn: &RoTxn) -> heed::Result<OrderByMap> {
-        let mut orders = self
+        let orders = self
             .main
-            .remap_types::<Str, SerdeJson<HashMap<String, OrderBy>>>()
+            .remap_types::<Str, SerdeJson<OrderByMap>>()
             .get(txn, main_key::SORT_FACET_VALUES_BY)?
             .unwrap_or_default();
-        // Insert the default ordering if it is not already overwritten by the user.
-        orders.entry("*".to_string()).or_insert(OrderBy::Lexicographic);
         Ok(orders)
     }
 
     pub(crate) fn put_sort_facet_values_by(
         &self,
         txn: &mut RwTxn,
-        val: &HashMap<String, OrderBy>,
+        val: &OrderByMap,
     ) -> heed::Result<()> {
         self.main.remap_types::<Str, SerdeJson<_>>().put(txn, main_key::SORT_FACET_VALUES_BY, &val)
     }

milli/src/lib.rs

@@ -16,6 +16,7 @@ pub mod facet;
 mod fields_ids_map;
 pub mod heed_codec;
 pub mod index;
+pub mod order_by_map;
 pub mod prompt;
 pub mod proximity;
 pub mod score_details;
@@ -56,10 +57,10 @@ pub use self::heed_codec::{
     UncheckedU8StrStrCodec,
 };
 pub use self::index::Index;
+pub use self::search::facet::{FacetValueHit, SearchForFacetValues};
 pub use self::search::{
-    FacetDistribution, FacetValueHit, Filter, FormatOptions, MatchBounds, MatcherBuilder,
+    FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, OrderBy,
-    MatchingWords, OrderBy, Search, SearchForFacetValues, SearchResult, TermsMatchingStrategy,
+    Search, SearchResult, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
-    DEFAULT_VALUES_PER_FACET,
 };
 
 pub type Result<T> = std::result::Result<T, error::Error>;

milli/src/order_by_map.rs

@@ -0,0 +1,57 @@
+use std::collections::{hash_map, HashMap};
+use std::iter::FromIterator;
+
+use serde::{Deserialize, Deserializer, Serialize};
+
+use crate::OrderBy;
+
+#[derive(Serialize)]
+pub struct OrderByMap(HashMap<String, OrderBy>);
+
+impl OrderByMap {
+    pub fn get(&self, key: impl AsRef<str>) -> OrderBy {
+        self.0
+            .get(key.as_ref())
+            .copied()
+            .unwrap_or_else(|| self.0.get("*").copied().unwrap_or_default())
+    }
+
+    pub fn insert(&mut self, key: String, value: OrderBy) -> Option<OrderBy> {
+        self.0.insert(key, value)
+    }
+}
+
+impl Default for OrderByMap {
+    fn default() -> Self {
+        let mut map = HashMap::new();
+        map.insert("*".to_string(), OrderBy::Lexicographic);
+        OrderByMap(map)
+    }
+}
+
+impl FromIterator<(String, OrderBy)> for OrderByMap {
+    fn from_iter<T: IntoIterator<Item = (String, OrderBy)>>(iter: T) -> Self {
+        OrderByMap(iter.into_iter().collect())
+    }
+}
+
+impl IntoIterator for OrderByMap {
+    type Item = (String, OrderBy);
+    type IntoIter = hash_map::IntoIter<String, OrderBy>;
+
+    fn into_iter(self) -> Self::IntoIter {
+        self.0.into_iter()
+    }
+}
+
+impl<'de> Deserialize<'de> for OrderByMap {
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        let mut map = Deserialize::deserialize(deserializer).map(OrderByMap)?;
+        // Insert the default ordering if it is not already overwritten by the user.
+        map.0.entry("*".to_string()).or_insert(OrderBy::default());
+        Ok(map)
+    }
+}

milli/src/search/facet/mod.rs

@@ -6,15 +6,18 @@ use roaring::RoaringBitmap;
 
 pub use self::facet_distribution::{FacetDistribution, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::filter::{BadGeoError, Filter};
+pub use self::search::{FacetValueHit, SearchForFacetValues};
 use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec, OrderedF64Codec};
 use crate::heed_codec::BytesRefCodec;
 use crate::{Index, Result};
+
 mod facet_distribution;
 mod facet_distribution_iter;
 mod facet_range_search;
 mod facet_sort_ascending;
 mod facet_sort_descending;
 mod filter;
+mod search;
 
 fn facet_extreme_value<'t>(
     mut extreme_it: impl Iterator<Item = heed::Result<(RoaringBitmap, &'t [u8])>> + 't,

milli/src/search/facet/search.rs

@@ -0,0 +1,326 @@
+use std::cmp::{Ordering, Reverse};
+use std::collections::BinaryHeap;
+use std::ops::ControlFlow;
+
+use charabia::normalizer::NormalizerOption;
+use charabia::Normalize;
+use fst::automaton::{Automaton, Str};
+use fst::{IntoStreamer, Streamer};
+use roaring::RoaringBitmap;
+use tracing::error;
+
+use crate::error::UserError;
+use crate::heed_codec::facet::{FacetGroupKey, FacetGroupValue};
+use crate::search::build_dfa;
+use crate::{DocumentId, FieldId, OrderBy, Result, Search};
+
+/// The maximum number of values per facet returned by the facet search route.
+const DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET: usize = 100;
+
+pub struct SearchForFacetValues<'a> {
+    query: Option<String>,
+    facet: String,
+    search_query: Search<'a>,
+    max_values: usize,
+    is_hybrid: bool,
+}
+
+impl<'a> SearchForFacetValues<'a> {
+    pub fn new(
+        facet: String,
+        search_query: Search<'a>,
+        is_hybrid: bool,
+    ) -> SearchForFacetValues<'a> {
+        SearchForFacetValues {
+            query: None,
+            facet,
+            search_query,
+            max_values: DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET,
+            is_hybrid,
+        }
+    }
+
+    pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
+        self.query = Some(query.into());
+        self
+    }
+
+    pub fn max_values(&mut self, max: usize) -> &mut Self {
+        self.max_values = max;
+        self
+    }
+
+    fn one_original_value_of(
+        &self,
+        field_id: FieldId,
+        facet_str: &str,
+        any_docid: DocumentId,
+    ) -> Result<Option<String>> {
+        let index = self.search_query.index;
+        let rtxn = self.search_query.rtxn;
+        let key: (FieldId, _, &str) = (field_id, any_docid, facet_str);
+        Ok(index.field_id_docid_facet_strings.get(rtxn, &key)?.map(|v| v.to_owned()))
+    }
+
+    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) {
+            let (valid_fields, hidden_fields) =
+                index.remove_hidden_fields(rtxn, filterable_fields)?;
+
+            return Err(UserError::InvalidFacetSearchFacetName {
+                field: self.facet.clone(),
+                valid_fields,
+                hidden_fields,
+            }
+            .into());
+        }
+
+        let fields_ids_map = index.fields_ids_map(rtxn)?;
+        let fid = match fields_ids_map.id(&self.facet) {
+            Some(fid) => fid,
+            // we return an empty list of results when the attribute has been
+            // set as filterable but no document contains this field (yet).
+            None => return Ok(Vec::new()),
+        };
+
+        let fst = match self.search_query.index.facet_id_string_fst.get(rtxn, &fid)? {
+            Some(fst) => fst,
+            None => return Ok(Vec::new()),
+        };
+
+        let search_candidates = self
+            .search_query
+            .execute_for_candidates(self.is_hybrid || self.search_query.vector.is_some())?;
+
+        let mut results = match index.sort_facet_values_by(rtxn)?.get(&self.facet) {
+            OrderBy::Lexicographic => ValuesCollection::by_lexicographic(self.max_values),
+            OrderBy::Count => ValuesCollection::by_count(self.max_values),
+        };
+
+        match self.query.as_ref() {
+            Some(query) => {
+                let options = NormalizerOption { lossy: true, ..Default::default() };
+                let query = query.normalize(&options);
+                let query = query.as_ref();
+
+                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 exact_words_fst = self.search_query.index.exact_words(rtxn)?;
+                    if exact_words_fst.map_or(false, |fst| fst.contains(query)) {
+                        if fst.contains(query) {
+                            self.fetch_original_facets_using_normalized(
+                                fid,
+                                query,
+                                query,
+                                &search_candidates,
+                                &mut results,
+                            )?;
+                        }
+                    } 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();
+                        while let Some(facet_value) = stream.next() {
+                            let value = std::str::from_utf8(facet_value)?;
+                            if self
+                                .fetch_original_facets_using_normalized(
+                                    fid,
+                                    value,
+                                    query,
+                                    &search_candidates,
+                                    &mut results,
+                                )?
+                                .is_break()
+                            {
+                                break;
+                            }
+                        }
+                    }
+                } else {
+                    let automaton = Str::new(query).starts_with();
+                    let mut stream = fst.search(automaton).into_stream();
+                    while let Some(facet_value) = stream.next() {
+                        let value = std::str::from_utf8(facet_value)?;
+                        if self
+                            .fetch_original_facets_using_normalized(
+                                fid,
+                                value,
+                                query,
+                                &search_candidates,
+                                &mut results,
+                            )?
+                            .is_break()
+                        {
+                            break;
+                        }
+                    }
+                }
+            }
+            None => {
+                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 {
+                        let value = self
+                            .one_original_value_of(fid, left_bound, bitmap.min().unwrap())?
+                            .unwrap_or_else(|| left_bound.to_string());
+                        if results.insert(FacetValueHit { value, count }).is_break() {
+                            break;
+                        }
+                    }
+                }
+            }
+        }
+
+        Ok(results.into_sorted_vec())
+    }
+
+    fn fetch_original_facets_using_normalized(
+        &self,
+        fid: FieldId,
+        value: &str,
+        query: &str,
+        search_candidates: &RoaringBitmap,
+        results: &mut ValuesCollection,
+    ) -> Result<ControlFlow<()>> {
+        let index = self.search_query.index;
+        let rtxn = self.search_query.rtxn;
+
+        let database = index.facet_id_normalized_string_strings;
+        let key = (fid, value);
+        let original_strings = match database.get(rtxn, &key)? {
+            Some(original_strings) => original_strings,
+            None => {
+                error!("the facet value is missing from the facet database: {key:?}");
+                return Ok(ControlFlow::Continue(()));
+            }
+        };
+        for original in original_strings {
+            let key = FacetGroupKey { field_id: fid, level: 0, left_bound: original.as_str() };
+            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:?}");
+                    return Ok(ControlFlow::Continue(()));
+                }
+            };
+            let count = search_candidates.intersection_len(&docids);
+            if count != 0 {
+                let value = self
+                    .one_original_value_of(fid, &original, docids.min().unwrap())?
+                    .unwrap_or_else(|| query.to_string());
+                if results.insert(FacetValueHit { value, count }).is_break() {
+                    break;
+                }
+            }
+        }
+
+        Ok(ControlFlow::Continue(()))
+    }
+}
+
+#[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,
+}
+
+impl PartialOrd for FacetValueHit {
+    fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
+        Some(self.cmp(other))
+    }
+}
+
+impl Ord for FacetValueHit {
+    fn cmp(&self, other: &Self) -> Ordering {
+        self.count.cmp(&other.count).then_with(|| self.value.cmp(&other.value))
+    }
+}
+
+impl Eq for FacetValueHit {}
+
+/// A wrapper type that collects the best facet values by
+/// lexicographic or number of associated values.
+enum ValuesCollection {
+    /// Keeps the top values according to the lexicographic order.
+    Lexicographic { max: usize, content: Vec<FacetValueHit> },
+    /// Keeps the top values according to the number of values associated to them.
+    ///
+    /// Note that it is a max heap and we need to move the smallest counts
+    /// at the top to be able to pop them when we reach the max_values limit.
+    Count { max: usize, content: BinaryHeap<Reverse<FacetValueHit>> },
+}
+
+impl ValuesCollection {
+    pub fn by_lexicographic(max: usize) -> Self {
+        ValuesCollection::Lexicographic { max, content: Vec::new() }
+    }
+
+    pub fn by_count(max: usize) -> Self {
+        ValuesCollection::Count { max, content: BinaryHeap::new() }
+    }
+
+    pub fn insert(&mut self, value: FacetValueHit) -> ControlFlow<()> {
+        match self {
+            ValuesCollection::Lexicographic { max, content } => {
+                if content.len() < *max {
+                    content.push(value);
+                    if content.len() < *max {
+                        return ControlFlow::Continue(());
+                    }
+                }
+                ControlFlow::Break(())
+            }
+            ValuesCollection::Count { max, content } => {
+                if content.len() == *max {
+                    // Peeking gives us the worst value in the list as
+                    // this is a max-heap and we reversed it.
+                    let Some(mut peek) = content.peek_mut() else { return ControlFlow::Break(()) };
+                    if peek.0.count <= value.count {
+                        // Replace the current worst value in the heap
+                        // with the new one we received that is better.
+                        *peek = Reverse(value);
+                    }
+                } else {
+                    content.push(Reverse(value));
+                }
+                ControlFlow::Continue(())
+            }
+        }
+    }
+
+    /// Returns the list of facet values in descending order of, either,
+    /// count or lexicographic order of the value depending on the type.
+    pub fn into_sorted_vec(self) -> Vec<FacetValueHit> {
+        match self {
+            ValuesCollection::Lexicographic { content, .. } => content.into_iter().collect(),
+            ValuesCollection::Count { content, .. } => {
+                // Convert the heap into a vec of hits by removing the Reverse wrapper.
+                // Hits are already in the right order as they were reversed and there
+                // are output in ascending order.
+                content.into_sorted_vec().into_iter().map(|Reverse(hit)| hit).collect()
+            }
+        }
+    }
+}

milli/src/search/mod.rs

@@ -1,25 +1,17 @@
 use std::fmt;
-use std::ops::ControlFlow;
 
-use charabia::normalizer::NormalizerOption;
-use charabia::Normalize;
-use fst::automaton::{Automaton, Str};
-use fst::{IntoStreamer, Streamer};
 use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
 use once_cell::sync::Lazy;
 use roaring::bitmap::RoaringBitmap;
-use tracing::error;
 
 pub use self::facet::{FacetDistribution, Filter, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::new::matches::{FormatOptions, MatchBounds, MatcherBuilder, MatchingWords};
 use self::new::{execute_vector_search, PartialSearchResult};
-use crate::error::UserError;
-use crate::heed_codec::facet::{FacetGroupKey, FacetGroupValue};
 use crate::score_details::{ScoreDetails, ScoringStrategy};
 use crate::vector::DistributionShift;
 use crate::{
-    execute_search, filtered_universe, AscDesc, DefaultSearchLogger, DocumentId, FieldId, Index,
+    execute_search, filtered_universe, AscDesc, DefaultSearchLogger, DocumentId, Index, Result,
-    Result, SearchContext,
+    SearchContext,
 };
 
 // Building these factories is not free.
@@ -27,9 +19,6 @@ 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 values per facet returned by the facet search route.
-const DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET: usize = 100;
-
 pub mod facet;
 mod fst_utils;
 pub mod hybrid;
@@ -302,240 +291,6 @@ 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>,
-    max_values: usize,
-    is_hybrid: bool,
-}
-
-impl<'a> SearchForFacetValues<'a> {
-    pub fn new(
-        facet: String,
-        search_query: Search<'a>,
-        is_hybrid: bool,
-    ) -> SearchForFacetValues<'a> {
-        SearchForFacetValues {
-            query: None,
-            facet,
-            search_query,
-            max_values: DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET,
-            is_hybrid,
-        }
-    }
-
-    pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
-        self.query = Some(query.into());
-        self
-    }
-
-    pub fn max_values(&mut self, max: usize) -> &mut Self {
-        self.max_values = max;
-        self
-    }
-
-    fn one_original_value_of(
-        &self,
-        field_id: FieldId,
-        facet_str: &str,
-        any_docid: DocumentId,
-    ) -> Result<Option<String>> {
-        let index = self.search_query.index;
-        let rtxn = self.search_query.rtxn;
-        let key: (FieldId, _, &str) = (field_id, any_docid, facet_str);
-        Ok(index.field_id_docid_facet_strings.get(rtxn, &key)?.map(|v| v.to_owned()))
-    }
-
-    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) {
-            let (valid_fields, hidden_fields) =
-                index.remove_hidden_fields(rtxn, filterable_fields)?;
-
-            return Err(UserError::InvalidFacetSearchFacetName {
-                field: self.facet.clone(),
-                valid_fields,
-                hidden_fields,
-            }
-            .into());
-        }
-
-        let fields_ids_map = index.fields_ids_map(rtxn)?;
-        let fid = match fields_ids_map.id(&self.facet) {
-            Some(fid) => fid,
-            // we return an empty list of results when the attribute has been
-            // set as filterable but no document contains this field (yet).
-            None => return Ok(Vec::new()),
-        };
-
-        let fst = match self.search_query.index.facet_id_string_fst.get(rtxn, &fid)? {
-            Some(fst) => fst,
-            None => return Ok(vec![]),
-        };
-
-        let search_candidates = self
-            .search_query
-            .execute_for_candidates(self.is_hybrid || self.search_query.vector.is_some())?;
-
-        match self.query.as_ref() {
-            Some(query) => {
-                let options = NormalizerOption { lossy: true, ..Default::default() };
-                let query = query.normalize(&options);
-                let query = query.as_ref();
-
-                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 exact_words_fst = self.search_query.index.exact_words(rtxn)?;
-                    if exact_words_fst.map_or(false, |fst| fst.contains(query)) {
-                        let mut results = vec![];
-                        if fst.contains(query) {
-                            self.fetch_original_facets_using_normalized(
-                                fid,
-                                query,
-                                query,
-                                &search_candidates,
-                                &mut results,
-                            )?;
-                        }
-                        Ok(results)
-                    } 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 results = vec![];
-                        while let Some(facet_value) = stream.next() {
-                            let value = std::str::from_utf8(facet_value)?;
-                            if self
-                                .fetch_original_facets_using_normalized(
-                                    fid,
-                                    value,
-                                    query,
-                                    &search_candidates,
-                                    &mut results,
-                                )?
-                                .is_break()
-                            {
-                                break;
-                            }
-                        }
-
-                        Ok(results)
-                    }
-                } else {
-                    let automaton = Str::new(query).starts_with();
-                    let mut stream = fst.search(automaton).into_stream();
-                    let mut results = vec![];
-                    while let Some(facet_value) = stream.next() {
-                        let value = std::str::from_utf8(facet_value)?;
-                        if self
-                            .fetch_original_facets_using_normalized(
-                                fid,
-                                value,
-                                query,
-                                &search_candidates,
-                                &mut results,
-                            )?
-                            .is_break()
-                        {
-                            break;
-                        }
-                    }
-
-                    Ok(results)
-                }
-            }
-            None => {
-                let mut results = vec![];
-                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 {
-                        let value = self
-                            .one_original_value_of(fid, left_bound, bitmap.min().unwrap())?
-                            .unwrap_or_else(|| left_bound.to_string());
-                        results.push(FacetValueHit { value, count });
-                    }
-                    if results.len() >= self.max_values {
-                        break;
-                    }
-                }
-                Ok(results)
-            }
-        }
-    }
-
-    fn fetch_original_facets_using_normalized(
-        &self,
-        fid: FieldId,
-        value: &str,
-        query: &str,
-        search_candidates: &RoaringBitmap,
-        results: &mut Vec<FacetValueHit>,
-    ) -> Result<ControlFlow<()>> {
-        let index = self.search_query.index;
-        let rtxn = self.search_query.rtxn;
-
-        let database = index.facet_id_normalized_string_strings;
-        let key = (fid, value);
-        let original_strings = match database.get(rtxn, &key)? {
-            Some(original_strings) => original_strings,
-            None => {
-                error!("the facet value is missing from the facet database: {key:?}");
-                return Ok(ControlFlow::Continue(()));
-            }
-        };
-        for original in original_strings {
-            let key = FacetGroupKey { field_id: fid, level: 0, left_bound: original.as_str() };
-            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:?}");
-                    return Ok(ControlFlow::Continue(()));
-                }
-            };
-            let count = search_candidates.intersection_len(&docids);
-            if count != 0 {
-                let value = self
-                    .one_original_value_of(fid, &original, docids.min().unwrap())?
-                    .unwrap_or_else(|| query.to_string());
-                results.push(FacetValueHit { value, count });
-            }
-            if results.len() >= self.max_values {
-                return Ok(ControlFlow::Break(()));
-            }
-        }
-
-        Ok(ControlFlow::Continue(()))
-    }
-}
-
-#[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/update/settings.rs

@@ -14,12 +14,13 @@ use super::IndexerConfig;
 use crate::criterion::Criterion;
 use crate::error::UserError;
 use crate::index::{DEFAULT_MIN_WORD_LEN_ONE_TYPO, DEFAULT_MIN_WORD_LEN_TWO_TYPOS};
+use crate::order_by_map::OrderByMap;
 use crate::proximity::ProximityPrecision;
 use crate::update::index_documents::IndexDocumentsMethod;
 use crate::update::{IndexDocuments, UpdateIndexingStep};
 use crate::vector::settings::{check_set, check_unset, EmbedderSource, EmbeddingSettings};
 use crate::vector::{Embedder, EmbeddingConfig, EmbeddingConfigs};
-use crate::{FieldsIdsMap, Index, OrderBy, Result};
+use crate::{FieldsIdsMap, Index, Result};
 
 #[derive(Debug, Clone, PartialEq, Eq, Copy)]
 pub enum Setting<T> {
@@ -145,7 +146,7 @@ pub struct Settings<'a, 't, 'i> {
     /// Attributes on which typo tolerance is disabled.
     exact_attributes: Setting<HashSet<String>>,
     max_values_per_facet: Setting<usize>,
-    sort_facet_values_by: Setting<HashMap<String, OrderBy>>,
+    sort_facet_values_by: Setting<OrderByMap>,
     pagination_max_total_hits: Setting<usize>,
     proximity_precision: Setting<ProximityPrecision>,
     embedder_settings: Setting<BTreeMap<String, Setting<EmbeddingSettings>>>,
@@ -340,7 +341,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
         self.max_values_per_facet = Setting::Reset;
     }
 
-    pub fn set_sort_facet_values_by(&mut self, value: HashMap<String, OrderBy>) {
+    pub fn set_sort_facet_values_by(&mut self, value: OrderByMap) {
         self.sort_facet_values_by = Setting::Set(value);
     }