Merge meilisearch#4621

4621: Bring back changes from v1.8.0 into main r=curquiza a=curquiza



Co-authored-by: ManyTheFish <[email protected]>
Co-authored-by: Tamo <[email protected]>
Co-authored-by: meili-bors[bot] <89034592+meili-bors[bot]@users.noreply.github.com>
Co-authored-by: Clément Renault <[email protected]>

dump/src/lib.rs

@@ -256,8 +256,8 @@ pub(crate) mod test {
 
     pub fn create_test_settings() -> Settings<Checked> {
         let settings = Settings {
-            displayed_attributes: Setting::Set(vec![S("race"), S("name")]),
-            searchable_attributes: Setting::Set(vec![S("name"), S("race")]),
+            displayed_attributes: Setting::Set(vec![S("race"), S("name")]).into(),
+            searchable_attributes: Setting::Set(vec![S("name"), S("race")]).into(),
             filterable_attributes: Setting::Set(btreeset! { S("race"), S("age") }),
             sortable_attributes: Setting::Set(btreeset! { S("age") }),
             ranking_rules: Setting::NotSet,

dump/src/reader/compat/v5_to_v6.rs

@@ -315,8 +315,8 @@ impl From<v5::ResponseError> for v6::ResponseError {
 impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
     fn from(settings: v5::Settings<T>) -> Self {
         v6::Settings {
-            displayed_attributes: settings.displayed_attributes.into(),
-            searchable_attributes: settings.searchable_attributes.into(),
+            displayed_attributes: v6::Setting::from(settings.displayed_attributes).into(),
+            searchable_attributes: v6::Setting::from(settings.searchable_attributes).into(),
             filterable_attributes: settings.filterable_attributes.into(),
             sortable_attributes: settings.sortable_attributes.into(),
             ranking_rules: {

index-scheduler/src/lib.rs

@@ -3041,6 +3041,7 @@ mod tests {
             source: Setting::Set(milli::vector::settings::EmbedderSource::Rest),
             api_key: Setting::Set(S("My super secret")),
             url: Setting::Set(S("http://localhost:7777")),
+            dimensions: Setting::Set(4),
             ..Default::default()
         };
         embedders.insert(S("default"), Setting::Set(embedding_settings));

index-scheduler/src/snapshots/index_scheduler__tests__settings_update-2.snap

@@ -7,6 +7,7 @@ expression: task.details
     "default": {
       "source": "rest",
       "apiKey": "MyXXXX...",
+      "dimensions": 4,
       "url": "http://localhost:7777"
     }
   }

index-scheduler/src/snapshots/index_scheduler__tests__settings_update-3.snap

@@ -6,7 +6,7 @@ expression: embedding_config.embedder_options
   "Rest": {
     "api_key": "My super secret",
     "distribution": null,
-    "dimensions": null,
+    "dimensions": 4,
     "url": "http://localhost:7777",
     "query": null,
     "input_field": [

index-scheduler/src/snapshots/index_scheduler__tests__settings_update.snap

@@ -7,6 +7,7 @@ expression: task.details
     "default": {
       "source": "rest",
       "apiKey": "MyXXXX...",
+      "dimensions": 4,
       "url": "http://localhost:7777"
     }
   }

index-scheduler/src/snapshots/lib.rs/test_settings_update/after_registering_settings_task.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: NotSet, searchable_attributes: NotSet, filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: NotSet, searchable_attributes: NotSet, filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

index-scheduler/src/snapshots/lib.rs/test_settings_update/settings_update_processed.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: NotSet, searchable_attributes: NotSet, filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: NotSet, searchable_attributes: NotSet, filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

meilisearch-types/Cargo.toml

@@ -44,6 +44,7 @@ all-tokenizations = ["milli/all-tokenizations"]
 
 # chinese specialized tokenization
 chinese = ["milli/chinese"]
+chinese-pinyin = ["milli/chinese-pinyin"]
 # hebrew specialized tokenization
 hebrew = ["milli/hebrew"]
 # japanese specialized tokenization
@@ -56,3 +57,5 @@ greek = ["milli/greek"]
 khmer = ["milli/khmer"]
 # allow vietnamese specialized tokenization
 vietnamese = ["milli/vietnamese"]
+# force swedish character recomposition
+swedish-recomposition = ["milli/swedish-recomposition"]

meilisearch-types/src/settings.rs

@@ -3,7 +3,7 @@ use std::convert::Infallible;
 use std::fmt;
 use std::marker::PhantomData;
 use std::num::NonZeroUsize;
-use std::ops::ControlFlow;
+use std::ops::{ControlFlow, Deref};
 use std::str::FromStr;
 
 use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
@@ -143,21 +143,13 @@ impl MergeWithError<milli::CriterionError> for DeserrJsonError<InvalidSettingsRa
 )]
 #[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
 pub struct Settings<T> {
-    #[serde(
-        default,
-        serialize_with = "serialize_with_wildcard",
-        skip_serializing_if = "Setting::is_not_set"
-    )]
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsDisplayedAttributes>)]
-    pub displayed_attributes: Setting<Vec<String>>,
+    pub displayed_attributes: WildcardSetting,
 
-    #[serde(
-        default,
-        serialize_with = "serialize_with_wildcard",
-        skip_serializing_if = "Setting::is_not_set"
-    )]
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsSearchableAttributes>)]
-    pub searchable_attributes: Setting<Vec<String>>,
+    pub searchable_attributes: WildcardSetting,
 
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsFilterableAttributes>)]
@@ -251,8 +243,8 @@ impl<T> Settings<T> {
 impl Settings<Checked> {
     pub fn cleared() -> Settings<Checked> {
         Settings {
-            displayed_attributes: Setting::Reset,
-            searchable_attributes: Setting::Reset,
+            displayed_attributes: Setting::Reset.into(),
+            searchable_attributes: Setting::Reset.into(),
             filterable_attributes: Setting::Reset,
             sortable_attributes: Setting::Reset,
             ranking_rules: Setting::Reset,
@@ -319,7 +311,7 @@ impl Settings<Checked> {
 
 impl Settings<Unchecked> {
     pub fn check(self) -> Settings<Checked> {
-        let displayed_attributes = match self.displayed_attributes {
+        let displayed_attributes = match self.displayed_attributes.0 {
             Setting::Set(fields) => {
                 if fields.iter().any(|f| f == "*") {
                     Setting::Reset
@@ -330,7 +322,7 @@ impl Settings<Unchecked> {
             otherwise => otherwise,
         };
 
-        let searchable_attributes = match self.searchable_attributes {
+        let searchable_attributes = match self.searchable_attributes.0 {
             Setting::Set(fields) => {
                 if fields.iter().any(|f| f == "*") {
                     Setting::Reset
@@ -342,8 +334,8 @@ impl Settings<Unchecked> {
         };
 
         Settings {
-            displayed_attributes,
-            searchable_attributes,
+            displayed_attributes: displayed_attributes.into(),
+            searchable_attributes: searchable_attributes.into(),
             filterable_attributes: self.filterable_attributes,
             sortable_attributes: self.sortable_attributes,
             ranking_rules: self.ranking_rules,
@@ -412,13 +404,13 @@ pub fn apply_settings_to_builder(
         _kind,
     } = settings;
 
-    match searchable_attributes {
+    match searchable_attributes.deref() {
         Setting::Set(ref names) => builder.set_searchable_fields(names.clone()),
         Setting::Reset => builder.reset_searchable_fields(),
         Setting::NotSet => (),
     }
 
-    match displayed_attributes {
+    match displayed_attributes.deref() {
         Setting::Set(ref names) => builder.set_displayed_fields(names.clone()),
         Setting::Reset => builder.reset_displayed_fields(),
         Setting::NotSet => (),
@@ -690,11 +682,13 @@ pub fn settings(
         displayed_attributes: match displayed_attributes {
             Some(attrs) => Setting::Set(attrs),
             None => Setting::Reset,
-        },
+        }
+        .into(),
         searchable_attributes: match searchable_attributes {
             Some(attrs) => Setting::Set(attrs),
             None => Setting::Reset,
-        },
+        }
+        .into(),
         filterable_attributes: Setting::Set(filterable_attributes),
         sortable_attributes: Setting::Set(sortable_attributes),
         ranking_rules: Setting::Set(criteria.iter().map(|c| c.clone().into()).collect()),
@@ -848,6 +842,41 @@ impl From<ProximityPrecisionView> for ProximityPrecision {
     }
 }
 
+#[derive(Debug, Clone, Default, Deserialize, PartialEq, Eq)]
+pub struct WildcardSetting(Setting<Vec<String>>);
+
+impl From<Setting<Vec<String>>> for WildcardSetting {
+    fn from(setting: Setting<Vec<String>>) -> Self {
+        Self(setting)
+    }
+}
+
+impl Serialize for WildcardSetting {
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: Serializer,
+    {
+        serialize_with_wildcard(&self.0, serializer)
+    }
+}
+
+impl<E: deserr::DeserializeError> Deserr<E> for WildcardSetting {
+    fn deserialize_from_value<V: deserr::IntoValue>(
+        value: deserr::Value<V>,
+        location: ValuePointerRef<'_>,
+    ) -> Result<Self, E> {
+        Ok(Self(Setting::deserialize_from_value(value, location)?))
+    }
+}
+
+impl std::ops::Deref for WildcardSetting {
+    type Target = Setting<Vec<String>>;
+
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
+
 #[cfg(test)]
 pub(crate) mod test {
     use super::*;
@@ -856,8 +885,8 @@ pub(crate) mod test {
     fn test_setting_check() {
         // test no changes
         let settings = Settings {
-            displayed_attributes: Setting::Set(vec![String::from("hello")]),
-            searchable_attributes: Setting::Set(vec![String::from("hello")]),
+            displayed_attributes: Setting::Set(vec![String::from("hello")]).into(),
+            searchable_attributes: Setting::Set(vec![String::from("hello")]).into(),
             filterable_attributes: Setting::NotSet,
             sortable_attributes: Setting::NotSet,
             ranking_rules: Setting::NotSet,
@@ -883,8 +912,9 @@ pub(crate) mod test {
         // test wildcard
         // test no changes
         let settings = Settings {
-            displayed_attributes: Setting::Set(vec![String::from("*")]),
-            searchable_attributes: Setting::Set(vec![String::from("hello"), String::from("*")]),
+            displayed_attributes: Setting::Set(vec![String::from("*")]).into(),
+            searchable_attributes: Setting::Set(vec![String::from("hello"), String::from("*")])
+                .into(),
             filterable_attributes: Setting::NotSet,
             sortable_attributes: Setting::NotSet,
             ranking_rules: Setting::NotSet,
@@ -904,7 +934,7 @@ pub(crate) mod test {
         };
 
         let checked = settings.check();
-        assert_eq!(checked.displayed_attributes, Setting::Reset);
-        assert_eq!(checked.searchable_attributes, Setting::Reset);
+        assert_eq!(checked.displayed_attributes, Setting::Reset.into());
+        assert_eq!(checked.searchable_attributes, Setting::Reset.into());
     }
 }

meilisearch/Cargo.toml

@@ -149,12 +149,14 @@ mini-dashboard = [
     "zip",
 ]
 chinese = ["meilisearch-types/chinese"]
+chinese-pinyin = ["meilisearch-types/chinese-pinyin"]
 hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]
 thai = ["meilisearch-types/thai"]
 greek = ["meilisearch-types/greek"]
 khmer = ["meilisearch-types/khmer"]
 vietnamese = ["meilisearch-types/vietnamese"]
+swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
 
 [package.metadata.mini-dashboard]
 assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.13/build.zip"

meilisearch/src/analytics/mock_analytics.rs

@@ -7,7 +7,6 @@ use serde_json::Value;
 
 use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
-use crate::routes::tasks::TasksFilterQuery;
 use crate::Opt;
 
 pub struct MockAnalytics {
@@ -86,6 +85,4 @@ impl Analytics for MockAnalytics {
     }
     fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
     fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-    fn get_tasks(&self, _query: &TasksFilterQuery, _request: &HttpRequest) {}
-    fn health_seen(&self, _request: &HttpRequest) {}
 }

meilisearch/src/analytics/mod.rs

@@ -14,7 +14,6 @@ use platform_dirs::AppDirs;
 use serde_json::Value;
 
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
-use crate::routes::tasks::TasksFilterQuery;
 
 // if the analytics feature is disabled
 // the `SegmentAnalytics` point to the mock instead of the real analytics
@@ -117,10 +116,4 @@ pub trait Analytics: Sync + Send {
         index_creation: bool,
         request: &HttpRequest,
     );
-
-    // this method should be called to aggregate the get tasks requests.
-    fn get_tasks(&self, query: &TasksFilterQuery, request: &HttpRequest);
-
-    // this method should be called to aggregate a add documents request
-    fn health_seen(&self, request: &HttpRequest);
 }