Introduce a new OrderByMap struct to simplify the sort by usage

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,
-    BEU32, BEU64,
+    Result, RoaringBitmapCodec, RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16, 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>> {
-        let mut orders = self
+    pub fn sort_facet_values_by(&self, txn: &RoTxn) -> heed::Result<OrderByMap> {
+        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;

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/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);
     }