removed unnecessary borrow call

.github/workflows/dependency-issue.yml

@@ -2,8 +2,8 @@ name: Create issue to upgrade dependencies
 
 on:
   schedule:
-    # Run the first of the month, every 6 month
-    - cron: '0 0 1 */6 *'
+    # Run the first of the month, every 3 month
+    - cron: '0 0 1 */3 *'
   workflow_dispatch:
 
 jobs:

.github/workflows/publish-apt-brew-pkg.yml

@@ -53,6 +53,5 @@ jobs:
         uses: mislav/bump-homebrew-formula-action@v2
         with:
           formula-name: meilisearch
-          formula-path: Formula/m/meilisearch.rb
         env:
           COMMITTER_TOKEN: ${{ secrets.HOMEBREW_COMMITTER_TOKEN }}

.github/workflows/sdks-tests.yml

@@ -14,7 +14,6 @@ on:
 env:
   MEILI_MASTER_KEY: 'masterKey'
   MEILI_NO_ANALYTICS: 'true'
-  DISABLE_COVERAGE: 'true'
 
 jobs:
   define-docker-image:
@@ -31,117 +30,6 @@ jobs:
           if [[ $event == 'workflow_dispatch' ]]; then
             echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
           fi
-      - name: Docker image is ${{ steps.define-image.outputs.docker-image }}
-        run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
-
-##########
-## SDKs ##
-##########
-
-  meilisearch-dotnet-tests:
-    needs: define-docker-image
-    name: .NET SDK tests
-    runs-on: ubuntu-latest
-    env:
-      MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
-
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-dotnet
-      - name: Setup .NET Core
-        uses: actions/setup-dotnet@v3
-        with:
-          dotnet-version: "6.0.x"
-      - name: Install dependencies
-        run: dotnet restore
-      - name: Build
-        run: dotnet build --configuration Release --no-restore
-      - name: Meilisearch (latest version) setup with Docker
-        run: docker compose up -d
-      - name: Run tests
-        run: dotnet test --no-restore --verbosity normal
-
-  meilisearch-dart-tests:
-    needs: define-docker-image
-    name: Dart SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-dart
-      - uses: dart-lang/setup-dart@v1
-        with:
-          sdk: 3.1.1
-      - name: Install dependencies
-        run: dart pub get
-      - name: Run integration tests
-        run: dart test --concurrency=4
-
-  meilisearch-go-tests:
-    needs: define-docker-image
-    name: Go SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - name: Set up Go
-        uses: actions/setup-go@v4
-        with:
-          go-version: stable
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-go
-      - name: Get dependencies
-        run: |
-          go get -v -t -d ./...
-          if [ -f Gopkg.toml ]; then
-            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
-            dep ensure
-          fi
-      - name: Run integration tests
-        run: go test -v ./...
-
-  meilisearch-java-tests:
-    needs: define-docker-image
-    name: Java SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-java
-      - name: Set up Java
-        uses: actions/setup-java@v3
-        with:
-          java-version: 8
-          distribution: 'zulu'
-          cache: gradle
-      - name: Grant execute permission for gradlew
-        run: chmod +x gradlew
-      - name: Build and run unit and integration tests
-        run: ./gradlew build integrationTest
 
   meilisearch-js-tests:
     needs: define-docker-image
@@ -178,6 +66,33 @@ jobs:
       - name: Run Browser env
         run: yarn test:env:browser
 
+  instant-meilisearch-tests:
+    needs: define-docker-image
+    name: instant-meilisearch tests
+    runs-on: ubuntu-latest
+    services:
+      meilisearch:
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        env:
+          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
+          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/instant-meilisearch
+      - name: Setup node
+        uses: actions/setup-node@v3
+        with:
+          cache: yarn
+      - name: Install dependencies
+        run: yarn install
+      - name: Run tests
+        run: yarn test
+      - name: Build all the playgrounds and the packages
+        run: yarn build
+
   meilisearch-php-tests:
     needs: define-docker-image
     name: PHP SDK tests
@@ -196,6 +111,8 @@ jobs:
           repository: meilisearch/meilisearch-php
       - name: Install PHP
         uses: shivammathur/setup-php@v2
+        with:
+          coverage: none
       - name: Validate composer.json and composer.lock
         run: composer validate
       - name: Install dependencies
@@ -232,6 +149,36 @@ jobs:
       - name: Test with pytest
         run: pipenv run pytest
 
+  meilisearch-go-tests:
+    needs: define-docker-image
+    name: Go SDK tests
+    runs-on: ubuntu-latest
+    services:
+      meilisearch:
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        env:
+          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
+          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: stable
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/meilisearch-go
+      - name: Get dependencies
+        run: |
+          go get -v -t -d ./...
+          if [ -f Gopkg.toml ]; then
+            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
+            dep ensure
+          fi
+      - name: Run integration tests
+        run: go test -v ./...
+
   meilisearch-ruby-tests:
     needs: define-docker-image
     name: Ruby SDK tests
@@ -277,110 +224,3 @@ jobs:
         run: cargo build --verbose
       - name: Run tests
         run: cargo test --verbose
-
-  meilisearch-swift-tests:
-    needs: define-docker-image
-    name: Swift SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-swift
-      - name: Run tests
-        run: swift test
-
-########################
-## FRONT-END PLUGINS ##
-########################
-
-  meilisearch-js-plugins-tests:
-    needs: define-docker-image
-    name: meilisearch-js-plugins tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-js-plugins
-      - name: Setup node
-        uses: actions/setup-node@v3
-        with:
-          cache: yarn
-      - name: Install dependencies
-        run: yarn install
-      - name: Run tests
-        run: yarn test
-      - name: Build all the playgrounds and the packages
-        run: yarn build
-
-########################
-## BACK-END PLUGINS ###
-########################
-
-  meilisearch-rails-tests:
-    needs: define-docker-image
-    name: meilisearch-rails tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-rails
-      - name: Set up Ruby 3
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: 3
-          bundler-cache: true
-      - name: Run tests
-        run: bundle exec rspec
-
-  meilisearch-symfony-tests:
-    needs: define-docker-image
-    name: meilisearch-symfony tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-symfony
-      - name: Install PHP
-        uses: shivammathur/setup-php@v2
-        with:
-          tools: composer:v2, flex
-      - name: Validate composer.json and composer.lock
-        run: composer validate
-      - name: Install dependencies
-        run: composer install --prefer-dist --no-progress --quiet
-      - name: Remove doctrine/annotations
-        run: composer remove --dev doctrine/annotations
-      - name: Run test suite
-        run: composer test:unit

.github/workflows/test-suite.yml

@@ -43,7 +43,7 @@ jobs:
           toolchain: nightly
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.6.2
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -65,7 +65,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.6.2
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -123,10 +123,7 @@ jobs:
           override: true
       - name: Run cargo tree without default features and check lindera is not present
         run: |
-          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -vqz lindera; then
-            echo "lindera has been found in the sources and it shouldn't"
-            exit 1
-          fi
+          cargo tree -f '{p} {f}' -e normal --no-default-features | grep lindera -vqz
       - name: Run cargo tree with default features and check lindera is pressent
         run: |
           cargo tree -f '{p} {f}' -e normal | grep lindera -qz
@@ -149,7 +146,7 @@ jobs:
           toolchain: stable
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.6.2
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -164,11 +161,11 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.71.1
+          toolchain: 1.69.0
           override: true
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.6.2
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -187,7 +184,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.6.2
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo fmt
         # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
         # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate

Cargo.toml

@@ -18,7 +18,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.4.0"
+version = "1.3.0"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"

dump/src/lib.rs

@@ -262,9 +262,6 @@ pub(crate) mod test {
             sortable_attributes: Setting::Set(btreeset! { S("age") }),
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
-            non_separator_tokens: Setting::NotSet,
-            separator_tokens: Setting::NotSet,
-            dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,

dump/src/reader/compat/v5_to_v6.rs

@@ -340,9 +340,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                 }
             },
             stop_words: settings.stop_words.into(),
-            non_separator_tokens: v6::Setting::NotSet,
-            separator_tokens: v6::Setting::NotSet,
-            dictionary: v6::Setting::NotSet,
             synonyms: settings.synonyms.into(),
             distinct_attribute: settings.distinct_attribute.into(),
             typo_tolerance: match settings.typo_tolerance {

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-10.snap

@@ -1,24 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: spells.settings().unwrap()
----
-{
-  "displayedAttributes": [
-    "*"
-  ],
-  "searchableAttributes": [
-    "*"
-  ],
-  "filterableAttributes": [],
-  "sortableAttributes": [],
-  "rankingRules": [
-    "typo",
-    "words",
-    "proximity",
-    "attribute",
-    "exactness"
-  ],
-  "stopWords": [],
-  "synonyms": {},
-  "distinctAttribute": null
-}

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-4.snap

@@ -1,38 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: products.settings().unwrap()
----
-{
-  "displayedAttributes": [
-    "*"
-  ],
-  "searchableAttributes": [
-    "*"
-  ],
-  "filterableAttributes": [],
-  "sortableAttributes": [],
-  "rankingRules": [
-    "typo",
-    "words",
-    "proximity",
-    "attribute",
-    "exactness"
-  ],
-  "stopWords": [],
-  "synonyms": {
-    "android": [
-      "phone",
-      "smartphone"
-    ],
-    "iphone": [
-      "phone",
-      "smartphone"
-    ],
-    "phone": [
-      "android",
-      "iphone",
-      "smartphone"
-    ]
-  },
-  "distinctAttribute": null
-}

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-7.snap

@@ -1,31 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: movies.settings().unwrap()
----
-{
-  "displayedAttributes": [
-    "*"
-  ],
-  "searchableAttributes": [
-    "*"
-  ],
-  "filterableAttributes": [
-    "genres",
-    "id"
-  ],
-  "sortableAttributes": [
-    "genres",
-    "id"
-  ],
-  "rankingRules": [
-    "typo",
-    "words",
-    "proximity",
-    "attribute",
-    "exactness",
-    "release_date:asc"
-  ],
-  "stopWords": [],
-  "synonyms": {},
-  "distinctAttribute": null
-}

filter-parser/Cargo.toml

@@ -14,7 +14,6 @@ license.workspace = true
 [dependencies]
 nom = "7.1.3"
 nom_locate = "4.1.0"
-unescaper = "0.1.2"
 
 [dev-dependencies]
 insta = "1.29.0"

filter-parser/src/error.rs

@@ -62,7 +62,6 @@ pub enum ErrorKind<'a> {
     MisusedGeoRadius,
     MisusedGeoBoundingBox,
     InvalidPrimary,
-    InvalidEscapedNumber,
     ExpectedEof,
     ExpectedValue(ExpectedValueKind),
     MalformedValue,
@@ -148,9 +147,6 @@ impl<'a> Display for Error<'a> {
                 let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) };
                 writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
             }
-            ErrorKind::InvalidEscapedNumber => {
-                writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)?
-            }
             ErrorKind::ExpectedEof => {
                 writeln!(f, "Found unexpected characters at the end of the filter: `{}`. You probably forgot an `OR` or an `AND` rule.", escaped_input)?
             }

filter-parser/src/lib.rs

@@ -545,8 +545,6 @@ impl<'a> std::fmt::Display for Token<'a> {
 
 #[cfg(test)]
 pub mod tests {
-    use FilterCondition as Fc;
-
     use super::*;
 
     /// Create a raw [Token]. You must specify the string that appear BEFORE your element followed by your element
@@ -558,22 +556,14 @@ pub mod tests {
         unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into()
     }
 
-    fn p(s: &str) -> impl std::fmt::Display + '_ {
-        Fc::parse(s).unwrap().unwrap()
-    }
-
-    #[test]
-    fn parse_escaped() {
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\'"#), @r#"{title} = {foo\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\'"#), @r#"{title} = {foo\\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\\\'"#), @r#"{title} = {foo\\\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\\\\\'"#), @r#"{title} = {foo\\\\}"#);
-        // but it also works with other sequencies
-        insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
-    }
-
     #[test]
     fn parse() {
+        use FilterCondition as Fc;
+
+        fn p(s: &str) -> impl std::fmt::Display + '_ {
+            Fc::parse(s).unwrap().unwrap()
+        }
+
         // Test equal
         insta::assert_display_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
         insta::assert_display_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");

filter-parser/src/value.rs

@@ -171,24 +171,7 @@ pub fn parse_value(input: Span) -> IResult<Token> {
         })
     })?;
 
-    match unescaper::unescape(value.value()) {
-        Ok(content) => {
-            if content.len() != value.value().len() {
-                Ok((input, Token::new(value.original_span(), Some(content))))
-            } else {
-                Ok((input, value))
-            }
-        }
-        Err(unescaper::Error::IncompleteStr(_)) => Err(nom::Err::Incomplete(nom::Needed::Unknown)),
-        Err(unescaper::Error::ParseIntError { .. }) => Err(nom::Err::Error(Error::new_from_kind(
-            value.original_span(),
-            ErrorKind::InvalidEscapedNumber,
-        ))),
-        Err(unescaper::Error::InvalidChar { .. }) => Err(nom::Err::Error(Error::new_from_kind(
-            value.original_span(),
-            ErrorKind::MalformedValue,
-        ))),
-    }
+    Ok((input, value))
 }
 
 fn is_value_component(c: char) -> bool {
@@ -335,17 +318,17 @@ pub mod test {
             ("\"cha'nnel\"", "cha'nnel", false),
             ("I'm tamo", "I", false),
             // escaped thing but not quote
-            (r#""\\""#, r#"\"#, true),
-            (r#""\\\\\\""#, r#"\\\"#, true),
-            (r#""aa\\aa""#, r#"aa\aa"#, true),
+            (r#""\\""#, r#"\\"#, false),
+            (r#""\\\\\\""#, r#"\\\\\\"#, false),
+            (r#""aa\\aa""#, r#"aa\\aa"#, false),
             // with double quote
             (r#""Hello \"world\"""#, r#"Hello "world""#, true),
-            (r#""Hello \\\"world\\\"""#, r#"Hello \"world\""#, true),
+            (r#""Hello \\\"world\\\"""#, r#"Hello \\"world\\""#, true),
             (r#""I'm \"super\" tamo""#, r#"I'm "super" tamo"#, true),
             (r#""\"\"""#, r#""""#, true),
             // with simple quote
             (r#"'Hello \'world\''"#, r#"Hello 'world'"#, true),
-            (r#"'Hello \\\'world\\\''"#, r#"Hello \'world\'"#, true),
+            (r#"'Hello \\\'world\\\''"#, r#"Hello \\'world\\'"#, true),
             (r#"'I\'m "super" tamo'"#, r#"I'm "super" tamo"#, true),
             (r#"'\'\''"#, r#"''"#, true),
         ];
@@ -367,14 +350,7 @@ pub mod test {
                 "Filter `{}` was not supposed to be escaped",
                 input
             );
-            assert_eq!(
-                token.value(),
-                expected,
-                "Filter `{}` failed by giving `{}` instead of `{}`.",
-                input,
-                token.value(),
-                expected
-            );
+            assert_eq!(token.value(), expected, "Filter `{}` failed.", input);
         }
     }
 

fuzzers/Cargo.toml

@@ -13,7 +13,7 @@ license.workspace = true
 [dependencies]
 arbitrary = { version = "1.3.0", features = ["derive"] }
 clap = { version = "4.3.0", features = ["derive"] }
-fastrand = "2.0.0"
+fastrand = "1.9.0"
 milli = { path = "../milli" }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }

index-scheduler/src/batch.rs

@@ -67,6 +67,10 @@ pub(crate) enum Batch {
         op: IndexOperation,
         must_create_index: bool,
     },
+    IndexDocumentDeletionByFilter {
+        index_uid: String,
+        task: Task,
+    },
     IndexCreation {
         index_uid: String,
         primary_key: Option<String>,
@@ -110,10 +114,6 @@ pub(crate) enum IndexOperation {
         documents: Vec<Vec<String>>,
         tasks: Vec<Task>,
     },
-    IndexDocumentDeletionByFilter {
-        index_uid: String,
-        task: Task,
-    },
     DocumentClear {
         index_uid: String,
         tasks: Vec<Task>,
@@ -155,6 +155,7 @@ impl Batch {
             | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
+            | Batch::IndexDocumentDeletionByFilter { task, .. }
             | Batch::IndexUpdate { task, .. } => vec![task.uid],
             Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
                 tasks.iter().map(|task| task.uid).collect()
@@ -166,7 +167,6 @@ impl Batch {
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     tasks.iter().map(|task| task.uid).collect()
                 }
-                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
@@ -194,7 +194,8 @@ impl Batch {
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid, .. } => Some(index_uid),
+            | IndexDeletion { index_uid, .. }
+            | IndexDocumentDeletionByFilter { index_uid, .. } => Some(index_uid),
         }
     }
 }
@@ -204,7 +205,6 @@ impl IndexOperation {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
             | IndexOperation::DocumentDeletion { index_uid, .. }
-            | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -239,12 +239,9 @@ impl IndexScheduler {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 match &task.kind {
                     KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
-                        Ok(Some(Batch::IndexOperation {
-                            op: IndexOperation::IndexDocumentDeletionByFilter {
-                                index_uid: index_uid.clone(),
-                                task,
-                            },
-                            must_create_index: false,
+                        Ok(Some(Batch::IndexDocumentDeletionByFilter {
+                            index_uid: index_uid.clone(),
+                            task,
                         }))
                     }
                     _ => unreachable!(),
@@ -899,6 +896,51 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            Batch::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
+                let (index_uid, filter) =
+                    if let KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } =
+                        &task.kind
+                    {
+                        (index_uid, filter_expr)
+                    } else {
+                        unreachable!()
+                    };
+                let index = {
+                    let rtxn = self.env.read_txn()?;
+                    self.index_mapper.index(&rtxn, index_uid)?
+                };
+                let deleted_documents = delete_document_by_filter(filter, index);
+                let original_filter = if let Some(Details::DocumentDeletionByFilter {
+                    original_filter,
+                    deleted_documents: _,
+                }) = task.details
+                {
+                    original_filter
+                } else {
+                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    unreachable!();
+                };
+
+                match deleted_documents {
+                    Ok(deleted_documents) => {
+                        task.status = Status::Succeeded;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(deleted_documents),
+                        });
+                    }
+                    Err(e) => {
+                        task.status = Status::Failed;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(0),
+                        });
+                        task.error = Some(e.into());
+                    }
+                }
+
+                Ok(vec![task])
+            }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 let wtxn = self.env.write_txn()?;
                 if self.index_mapper.exists(&wtxn, &index_uid)? {
@@ -1257,47 +1299,6 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
-            IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
-                let filter =
-                    if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
-                        &task.kind
-                    {
-                        filter_expr
-                    } else {
-                        unreachable!()
-                    };
-                let deleted_documents = delete_document_by_filter(index_wtxn, filter, index);
-                let original_filter = if let Some(Details::DocumentDeletionByFilter {
-                    original_filter,
-                    deleted_documents: _,
-                }) = task.details
-                {
-                    original_filter
-                } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
-                    unreachable!();
-                };
-
-                match deleted_documents {
-                    Ok(deleted_documents) => {
-                        task.status = Status::Succeeded;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(deleted_documents),
-                        });
-                    }
-                    Err(e) => {
-                        task.status = Status::Failed;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(0),
-                        });
-                        task.error = Some(e.into());
-                    }
-                }
-
-                Ok(vec![task])
-            }
             IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
                 let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config);
@@ -1497,22 +1498,23 @@ impl IndexScheduler {
     }
 }
 
-fn delete_document_by_filter<'a>(
-    wtxn: &mut RwTxn<'a, '_>,
-    filter: &serde_json::Value,
-    index: &'a Index,
-) -> Result<u64> {
+fn delete_document_by_filter(filter: &serde_json::Value, index: Index) -> Result<u64> {
     let filter = Filter::from_json(filter)?;
     Ok(if let Some(filter) = filter {
-        let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
+        let mut wtxn = index.write_txn()?;
+
+        let candidates = filter.evaluate(&wtxn, &index).map_err(|err| match err {
             milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
                 Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
             }
             e => e.into(),
         })?;
-        let mut delete_operation = DeleteDocuments::new(wtxn, index)?;
+        let mut delete_operation = DeleteDocuments::new(&mut wtxn, &index)?;
         delete_operation.delete_documents(&candidates);
-        delete_operation.execute().map(|result| result.deleted_documents)?
+        let deleted_documents =
+            delete_operation.execute().map(|result| result.deleted_documents)?;
+        wtxn.commit()?;
+        deleted_documents
     } else {
         0
     })

index-scheduler/src/lib.rs

@@ -790,19 +790,10 @@ impl IndexScheduler {
 
         let mut res = BTreeMap::new();
 
-        let processing_tasks = { self.processing_tasks.read().unwrap().processing.len() };
-
         res.insert(
             "statuses".to_string(),
             enum_iterator::all::<Status>()
-                .map(|s| {
-                    let tasks = self.get_status(&rtxn, s)?.len();
-                    match s {
-                        Status::Enqueued => Ok((s.to_string(), tasks - processing_tasks)),
-                        Status::Processing => Ok((s.to_string(), processing_tasks)),
-                        s => Ok((s.to_string(), tasks)),
-                    }
-                })
+                .map(|s| Ok((s.to_string(), self.get_status(&rtxn, s)?.len())))
                 .collect::<Result<BTreeMap<String, u64>>>()?,
         );
         res.insert(
@@ -4140,154 +4131,4 @@ mod tests {
         snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "everything_has_been_processed");
         drop(rtxn);
     }
-
-    #[test]
-    fn basic_get_stats() {
-        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
-
-        let kind = index_creation_task("catto", "mouse");
-        let _task = index_scheduler.register(kind).unwrap();
-        let kind = index_creation_task("doggo", "sheep");
-        let _task = index_scheduler.register(kind).unwrap();
-        let kind = index_creation_task("whalo", "fish");
-        let _task = index_scheduler.register(kind).unwrap();
-
-        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
-        {
-          "indexes": {
-            "catto": 1,
-            "doggo": 1,
-            "whalo": 1
-          },
-          "statuses": {
-            "canceled": 0,
-            "enqueued": 3,
-            "failed": 0,
-            "processing": 0,
-            "succeeded": 0
-          },
-          "types": {
-            "documentAdditionOrUpdate": 0,
-            "documentDeletion": 0,
-            "dumpCreation": 0,
-            "indexCreation": 3,
-            "indexDeletion": 0,
-            "indexSwap": 0,
-            "indexUpdate": 0,
-            "settingsUpdate": 0,
-            "snapshotCreation": 0,
-            "taskCancelation": 0,
-            "taskDeletion": 0
-          }
-        }
-        "###);
-
-        handle.advance_till([Start, BatchCreated]);
-        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
-        {
-          "indexes": {
-            "catto": 1,
-            "doggo": 1,
-            "whalo": 1
-          },
-          "statuses": {
-            "canceled": 0,
-            "enqueued": 2,
-            "failed": 0,
-            "processing": 1,
-            "succeeded": 0
-          },
-          "types": {
-            "documentAdditionOrUpdate": 0,
-            "documentDeletion": 0,
-            "dumpCreation": 0,
-            "indexCreation": 3,
-            "indexDeletion": 0,
-            "indexSwap": 0,
-            "indexUpdate": 0,
-            "settingsUpdate": 0,
-            "snapshotCreation": 0,
-            "taskCancelation": 0,
-            "taskDeletion": 0
-          }
-        }
-        "###);
-
-        handle.advance_till([
-            InsideProcessBatch,
-            InsideProcessBatch,
-            ProcessBatchSucceeded,
-            AfterProcessing,
-            Start,
-            BatchCreated,
-        ]);
-        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
-        {
-          "indexes": {
-            "catto": 1,
-            "doggo": 1,
-            "whalo": 1
-          },
-          "statuses": {
-            "canceled": 0,
-            "enqueued": 1,
-            "failed": 0,
-            "processing": 1,
-            "succeeded": 1
-          },
-          "types": {
-            "documentAdditionOrUpdate": 0,
-            "documentDeletion": 0,
-            "dumpCreation": 0,
-            "indexCreation": 3,
-            "indexDeletion": 0,
-            "indexSwap": 0,
-            "indexUpdate": 0,
-            "settingsUpdate": 0,
-            "snapshotCreation": 0,
-            "taskCancelation": 0,
-            "taskDeletion": 0
-          }
-        }
-        "###);
-
-        // now we make one more batch, the started_at field of the new tasks will be past `second_start_time`
-        handle.advance_till([
-            InsideProcessBatch,
-            InsideProcessBatch,
-            ProcessBatchSucceeded,
-            AfterProcessing,
-            Start,
-            BatchCreated,
-        ]);
-        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
-        {
-          "indexes": {
-            "catto": 1,
-            "doggo": 1,
-            "whalo": 1
-          },
-          "statuses": {
-            "canceled": 0,
-            "enqueued": 0,
-            "failed": 0,
-            "processing": 1,
-            "succeeded": 2
-          },
-          "types": {
-            "documentAdditionOrUpdate": 0,
-            "documentDeletion": 0,
-            "dumpCreation": 0,
-            "indexCreation": 3,
-            "indexDeletion": 0,
-            "indexSwap": 0,
-            "indexUpdate": 0,
-            "settingsUpdate": 0,
-            "snapshotCreation": 0,
-            "taskCancelation": 0,
-            "taskDeletion": 0
-          }
-        }
-        "###);
-    }
 }

meili-snap/src/lib.rs

@@ -167,9 +167,7 @@ macro_rules! snapshot {
         let (settings, snap_name, _) = $crate::default_snapshot_settings_for_test(test_name, Some(&snap_name));
         settings.bind(|| {
             let snap = format!("{}", $value);
-            insta::allow_duplicates! {
-                meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
-            }
+            meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
         });
     };
     ($value:expr, @$inline:literal) => {
@@ -178,9 +176,7 @@ macro_rules! snapshot {
         let (settings, _, _) = $crate::default_snapshot_settings_for_test("", Some("_dummy_argument"));
         settings.bind(|| {
             let snap = format!("{}", $value);
-            insta::allow_duplicates! {
-                meili_snap::insta::assert_snapshot!(snap, @$inline);
-            }
+            meili_snap::insta::assert_snapshot!(snap, @$inline);
         });
     };
     ($value:expr) => {
@@ -198,9 +194,7 @@ macro_rules! snapshot {
         let (settings, snap_name, _) = $crate::default_snapshot_settings_for_test(test_name, None);
         settings.bind(|| {
             let snap = format!("{}", $value);
-            insta::allow_duplicates! {
-                meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
-            }
+            meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
         });
     };
 }

meilisearch-auth/src/store.rs

@@ -129,9 +129,6 @@ impl HeedAuthStore {
                 Action::DumpsAll => {
                     actions.insert(Action::DumpsCreate);
                 }
-                Action::SnapshotsAll => {
-                    actions.insert(Action::SnapshotsCreate);
-                }
                 Action::TasksAll => {
                     actions.extend([Action::TasksGet, Action::TasksDelete, Action::TasksCancel]);
                 }

meilisearch-types/Cargo.toml

@@ -15,13 +15,13 @@ actix-web = { version = "4.3.1", default-features = false }
 anyhow = "1.0.70"
 convert_case = "0.6.0"
 csv = "1.2.1"
-deserr = { version = "0.6.0", features = ["actix-web"]}
+deserr = "0.5.0"
 either = { version = "1.8.1", features = ["serde"] }
 enum-iterator = "1.4.0"
 file-store = { path = "../file-store" }
 flate2 = "1.0.25"
 fst = "0.4.7"
-memmap2 = "0.7.1"
+memmap2 = "0.5.10"
 milli = { path = "../milli" }
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }

meilisearch-types/src/error.rs

@@ -259,9 +259,6 @@ InvalidSettingsRankingRules           , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSortableAttributes     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsStopWords              , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsNonSeparatorTokens     , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsSeparatorTokens        , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsDictionary             , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSynonyms               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsTypoTolerance          , InvalidRequest       , BAD_REQUEST ;
 InvalidState                          , Internal             , INTERNAL_SERVER_ERROR ;

meilisearch-types/src/keys.rs

@@ -257,12 +257,6 @@ pub enum Action {
     #[serde(rename = "dumps.create")]
     #[deserr(rename = "dumps.create")]
     DumpsCreate,
-    #[serde(rename = "snapshots.*")]
-    #[deserr(rename = "snapshots.*")]
-    SnapshotsAll,
-    #[serde(rename = "snapshots.create")]
-    #[deserr(rename = "snapshots.create")]
-    SnapshotsCreate,
     #[serde(rename = "version")]
     #[deserr(rename = "version")]
     Version,
@@ -315,7 +309,6 @@ impl Action {
             METRICS_GET => Some(Self::MetricsGet),
             DUMPS_ALL => Some(Self::DumpsAll),
             DUMPS_CREATE => Some(Self::DumpsCreate),
-            SNAPSHOTS_CREATE => Some(Self::SnapshotsCreate),
             VERSION => Some(Self::Version),
             KEYS_CREATE => Some(Self::KeysAdd),
             KEYS_GET => Some(Self::KeysGet),
@@ -360,7 +353,6 @@ pub mod actions {
     pub const METRICS_GET: u8 = MetricsGet.repr();
     pub const DUMPS_ALL: u8 = DumpsAll.repr();
     pub const DUMPS_CREATE: u8 = DumpsCreate.repr();
-    pub const SNAPSHOTS_CREATE: u8 = SnapshotsCreate.repr();
     pub const VERSION: u8 = Version.repr();
     pub const KEYS_CREATE: u8 = KeysAdd.repr();
     pub const KEYS_GET: u8 = KeysGet.repr();

meilisearch-types/src/settings.rs

@@ -171,15 +171,6 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsStopWords>)]
     pub stop_words: Setting<BTreeSet<String>>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsNonSeparatorTokens>)]
-    pub non_separator_tokens: Setting<BTreeSet<String>>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsSeparatorTokens>)]
-    pub separator_tokens: Setting<BTreeSet<String>>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsDictionary>)]
-    pub dictionary: Setting<BTreeSet<String>>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsSynonyms>)]
     pub synonyms: Setting<BTreeMap<String, Vec<String>>>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
@@ -210,9 +201,6 @@ impl Settings<Checked> {
             ranking_rules: Setting::Reset,
             stop_words: Setting::Reset,
             synonyms: Setting::Reset,
-            non_separator_tokens: Setting::Reset,
-            separator_tokens: Setting::Reset,
-            dictionary: Setting::Reset,
             distinct_attribute: Setting::Reset,
             typo_tolerance: Setting::Reset,
             faceting: Setting::Reset,
@@ -229,9 +217,6 @@ impl Settings<Checked> {
             sortable_attributes,
             ranking_rules,
             stop_words,
-            non_separator_tokens,
-            separator_tokens,
-            dictionary,
             synonyms,
             distinct_attribute,
             typo_tolerance,
@@ -247,9 +232,6 @@ impl Settings<Checked> {
             sortable_attributes,
             ranking_rules,
             stop_words,
-            non_separator_tokens,
-            separator_tokens,
-            dictionary,
             synonyms,
             distinct_attribute,
             typo_tolerance,
@@ -292,9 +274,6 @@ impl Settings<Unchecked> {
             ranking_rules: self.ranking_rules,
             stop_words: self.stop_words,
             synonyms: self.synonyms,
-            non_separator_tokens: self.non_separator_tokens,
-            separator_tokens: self.separator_tokens,
-            dictionary: self.dictionary,
             distinct_attribute: self.distinct_attribute,
             typo_tolerance: self.typo_tolerance,
             faceting: self.faceting,
@@ -356,28 +335,6 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.non_separator_tokens {
-        Setting::Set(ref non_separator_tokens) => {
-            builder.set_non_separator_tokens(non_separator_tokens.clone())
-        }
-        Setting::Reset => builder.reset_non_separator_tokens(),
-        Setting::NotSet => (),
-    }
-
-    match settings.separator_tokens {
-        Setting::Set(ref separator_tokens) => {
-            builder.set_separator_tokens(separator_tokens.clone())
-        }
-        Setting::Reset => builder.reset_separator_tokens(),
-        Setting::NotSet => (),
-    }
-
-    match settings.dictionary {
-        Setting::Set(ref dictionary) => builder.set_dictionary(dictionary.clone()),
-        Setting::Reset => builder.reset_dictionary(),
-        Setting::NotSet => (),
-    }
-
     match settings.synonyms {
         Setting::Set(ref synonyms) => builder.set_synonyms(synonyms.clone().into_iter().collect()),
         Setting::Reset => builder.reset_synonyms(),
@@ -502,14 +459,15 @@ pub fn settings(
         })
         .transpose()?
         .unwrap_or_default();
-
-    let non_separator_tokens = index.non_separator_tokens(rtxn)?.unwrap_or_default();
-    let separator_tokens = index.separator_tokens(rtxn)?.unwrap_or_default();
-    let dictionary = index.dictionary(rtxn)?.unwrap_or_default();
-
     let distinct_field = index.distinct_field(rtxn)?.map(String::from);
 
-    let synonyms = index.user_defined_synonyms(rtxn)?;
+    // in milli each word in the synonyms map were split on their separator. Since we lost
+    // this information we are going to put space between words.
+    let synonyms = index
+        .synonyms(rtxn)?
+        .iter()
+        .map(|(key, values)| (key.join(" "), values.iter().map(|value| value.join(" ")).collect()))
+        .collect();
 
     let min_typo_word_len = MinWordSizeTyposSetting {
         one_typo: Setting::Set(index.min_word_len_one_typo(rtxn)?),
@@ -562,9 +520,6 @@ pub fn settings(
         sortable_attributes: Setting::Set(sortable_attributes),
         ranking_rules: Setting::Set(criteria.iter().map(|c| c.clone().into()).collect()),
         stop_words: Setting::Set(stop_words),
-        non_separator_tokens: Setting::Set(non_separator_tokens),
-        separator_tokens: Setting::Set(separator_tokens),
-        dictionary: Setting::Set(dictionary),
         distinct_attribute: match distinct_field {
             Some(field) => Setting::Set(field),
             None => Setting::Reset,
@@ -687,9 +642,6 @@ pub(crate) mod test {
             sortable_attributes: Setting::NotSet,
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
-            non_separator_tokens: Setting::NotSet,
-            separator_tokens: Setting::NotSet,
-            dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
@@ -711,9 +663,6 @@ pub(crate) mod test {
             sortable_attributes: Setting::NotSet,
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
-            non_separator_tokens: Setting::NotSet,
-            separator_tokens: Setting::NotSet,
-            dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,

meilisearch/Cargo.toml

@@ -39,7 +39,7 @@ byte-unit = { version = "4.0.19", default-features = false, features = [
 bytes = "1.4.0"
 clap = { version = "4.2.1", features = ["derive", "env"] }
 crossbeam-channel = "0.5.8"
-deserr = { version = "0.6.0", features = ["actix-web"]}
+deserr = "0.5.0"
 dump = { path = "../dump" }
 either = "1.8.1"
 env_logger = "0.10.0"
@@ -50,9 +50,9 @@ futures = "0.3.28"
 futures-util = "0.3.28"
 http = "0.2.9"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.0.0", features = ["serde"] }
+indexmap = { version = "1.9.3", features = ["serde-1"] }
 is-terminal = "0.4.8"
-itertools = "0.11.0"
+itertools = "0.10.5"
 jsonwebtoken = "8.3.0"
 lazy_static = "1.4.0"
 log = "0.4.17"
@@ -87,7 +87,7 @@ sha2 = "0.10.6"
 siphasher = "0.3.10"
 slice-group-by = "0.3.0"
 static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.29.7"
+sysinfo = "0.28.4"
 tar = "0.4.38"
 tempfile = "3.5.0"
 thiserror = "1.0.40"

meilisearch/src/analytics/mock_analytics.rs

@@ -20,7 +20,7 @@ pub struct SearchAggregator;
 #[allow(dead_code)]
 impl SearchAggregator {
     pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
+        Self::default()
     }
 
     pub fn succeed(&mut self, _: &dyn Any) {}
@@ -32,7 +32,7 @@ pub struct MultiSearchAggregator;
 #[allow(dead_code)]
 impl MultiSearchAggregator {
     pub fn from_queries(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
+        Self::default()
     }
 
     pub fn succeed(&mut self) {}
@@ -44,7 +44,7 @@ pub struct FacetSearchAggregator;
 #[allow(dead_code)]
 impl FacetSearchAggregator {
     pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
+        Self::default()
     }
 
     pub fn succeed(&mut self, _: &dyn Any) {}

meilisearch/src/analytics/mod.rs

@@ -1,5 +1,6 @@
 mod mock_analytics;
-#[cfg(feature = "analytics")]
+// if we are in release mode and the feature analytics was enabled
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 mod segment_analytics;
 
 use std::fs;
@@ -16,25 +17,26 @@ use serde_json::Value;
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
 use crate::routes::tasks::TasksFilterQuery;
 
-// if the analytics feature is disabled
+// if we are in debug mode OR the analytics feature is disabled
 // the `SegmentAnalytics` point to the mock instead of the real analytics
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type SegmentAnalytics = mock_analytics::MockAnalytics;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type SearchAggregator = mock_analytics::SearchAggregator;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
-// if the feature analytics is enabled we use the real analytics
-#[cfg(feature = "analytics")]
+// if we are in release mode and the feature analytics was enabled
+// we use the real analytics
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type SearchAggregator = segment_analytics::SearchAggregator;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
 
 /// The Meilisearch config dir:

meilisearch/src/option.rs

@@ -28,7 +28,7 @@ const MEILI_DB_PATH: &str = "MEILI_DB_PATH";
 const MEILI_HTTP_ADDR: &str = "MEILI_HTTP_ADDR";
 const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
 const MEILI_SSL_CERT_PATH: &str = "MEILI_SSL_CERT_PATH";
@@ -159,7 +159,7 @@ pub struct Opt {
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
     /// All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted
     /// at any time.
-    #[cfg(feature = "analytics")]
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     #[serde(default)] // we can't send true
     #[clap(long, env = MEILI_NO_ANALYTICS)]
     pub no_analytics: bool,
@@ -390,7 +390,7 @@ impl Opt {
             ignore_missing_dump: _,
             ignore_dump_if_db_exists: _,
             config_file_path: _,
-            #[cfg(feature = "analytics")]
+            #[cfg(all(not(debug_assertions), feature = "analytics"))]
             no_analytics,
             experimental_enable_metrics: enable_metrics_route,
             experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
@@ -401,7 +401,7 @@ impl Opt {
             export_to_env_if_not_present(MEILI_MASTER_KEY, master_key);
         }
         export_to_env_if_not_present(MEILI_ENV, env);
-        #[cfg(feature = "analytics")]
+        #[cfg(all(not(debug_assertions), feature = "analytics"))]
         {
             export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
         }

meilisearch/src/routes/indexes/settings.rs

@@ -310,81 +310,6 @@ make_setting_route!(
     }
 );
 
-make_setting_route!(
-    "/non-separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsNonSeparatorTokens,
-    >,
-    non_separator_tokens,
-    "nonSeparatorTokens",
-    analytics,
-    |non_separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "nonSeparatorTokens Updated".to_string(),
-            json!({
-                "non_separator_tokens": {
-                    "total": non_separator_tokens.as_ref().map(|non_separator_tokens| non_separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
-);
-
-make_setting_route!(
-    "/separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSeparatorTokens,
-    >,
-    separator_tokens,
-    "separatorTokens",
-    analytics,
-    |separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "separatorTokens Updated".to_string(),
-            json!({
-                "separator_tokens": {
-                    "total": separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
-);
-
-make_setting_route!(
-    "/dictionary",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDictionary,
-    >,
-    dictionary,
-    "dictionary",
-    analytics,
-    |dictionary: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "dictionary Updated".to_string(),
-            json!({
-                "dictionary": {
-                    "total": dictionary.as_ref().map(|dictionary| dictionary.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
-);
-
 make_setting_route!(
     "/synonyms",
     put,
@@ -541,9 +466,6 @@ generate_configure!(
     searchable_attributes,
     distinct_attribute,
     stop_words,
-    separator_tokens,
-    non_separator_tokens,
-    dictionary,
     synonyms,
     ranking_rules,
     typo_tolerance,

meilisearch/src/routes/mod.rs

@@ -24,7 +24,6 @@ pub mod features;
 pub mod indexes;
 mod metrics;
 mod multi_search;
-mod snapshot;
 mod swap_indexes;
 pub mod tasks;
 
@@ -33,7 +32,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::resource("/health").route(web::get().to(get_health)))
         .service(web::scope("/keys").configure(api_key::configure))
         .service(web::scope("/dumps").configure(dump::configure))
-        .service(web::scope("/snapshots").configure(snapshot::configure))
         .service(web::resource("/stats").route(web::get().to(get_stats)))
         .service(web::resource("/version").route(web::get().to(get_version)))
         .service(web::scope("/indexes").configure(indexes::configure))

meilisearch/src/routes/snapshot.rs

@@ -1,32 +0,0 @@
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use index_scheduler::IndexScheduler;
-use log::debug;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
-
-use crate::analytics::Analytics;
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::SummarizedTaskView;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(SeqHandler(create_snapshot))));
-}
-
-pub async fn create_snapshot(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SNAPSHOTS_CREATE }>, Data<IndexScheduler>>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Snapshot Created".to_string(), json!({}), Some(&req));
-
-    let task = KindWithContent::SnapshotCreation;
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
-
-    debug!("returns: {:?}", task);
-    Ok(HttpResponse::Accepted().json(task))
-}

meilisearch/src/routes/swap_indexes.rs

@@ -60,7 +60,8 @@ pub async fn swap_indexes(
     }
 
     let task = KindWithContent::IndexSwap { swaps };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+
+    let task = index_scheduler.register(task)?;
+    let task: SummarizedTaskView = task.into();
     Ok(HttpResponse::Accepted().json(task))
 }

meilisearch/src/search.rs

@@ -491,20 +491,6 @@ pub fn perform_search(
         tokenizer_builder.allow_list(&script_lang_map);
     }
 
-    let separators = index.allowed_separators(&rtxn)?;
-    let separators: Option<Vec<_>> =
-        separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref separators) = separators {
-        tokenizer_builder.separators(separators);
-    }
-
-    let dictionary = index.dictionary(&rtxn)?;
-    let dictionary: Option<Vec<_>> =
-        dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref dictionary) = dictionary {
-        tokenizer_builder.words_dict(dictionary);
-    }
-
     let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_builder.build());
     formatter_builder.crop_marker(query.crop_marker);
     formatter_builder.highlight_prefix(query.highlight_pre_tag);
@@ -680,7 +666,6 @@ fn compute_semantic_score(query: &[f32], vectors: Value) -> milli::Result<Option
         .map_err(InternalError::SerdeJson)?;
     Ok(vectors
         .into_iter()
-        .flatten()
         .map(|v| OrderedFloat(dot_product_similarity(query, &v)))
         .max()
         .map(OrderedFloat::into_inner))

meilisearch/tests/auth/api_keys.rs

@@ -1,7 +1,8 @@
 use std::{thread, time};
 
-use crate::common::{Server, Value};
-use crate::json;
+use serde_json::{json, Value};
+
+use crate::common::Server;
 
 #[actix_rt::test]
 async fn add_valid_api_key() {
@@ -161,7 +162,7 @@ async fn add_valid_api_key_null_description() {
     server.use_api_key("MASTER_KEY");
 
     let content = json!({
-        "description": json!(null),
+        "description": Value::Null,
         "indexes": ["products"],
         "actions": ["documents.add"],
         "expiresAt": "2050-11-13T00:00:00"
@@ -364,7 +365,7 @@ async fn error_add_api_key_invalid_index_uids() {
     server.use_api_key("MASTER_KEY");
 
     let content = json!({
-        "description": json!(null),
+        "description": Value::Null,
         "indexes": ["invalid index # / \\name with spaces"],
         "actions": [
             "documents.add"
@@ -421,7 +422,7 @@ async fn error_add_api_key_invalid_parameters_actions() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]" }), @r###"
     {
-      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"
@@ -506,7 +507,7 @@ async fn error_add_api_key_invalid_parameters_uid() {
 async fn error_add_api_key_parameters_uid_already_exist() {
     let mut server = Server::new_auth().await;
     server.use_api_key("MASTER_KEY");
-    let content: Value = json!({
+    let content = json!({
         "uid": "4bc0887a-0e41-4f3b-935d-0c451dcee9c8",
         "indexes": ["products"],
         "actions": ["search"],
@@ -1145,7 +1146,7 @@ async fn patch_api_key_description() {
     meili_snap::snapshot!(code, @"200 OK");
 
     // Remove the description
-    let content = json!({ "description": null });
+    let content = json!({ "description": serde_json::Value::Null });
 
     let (response, code) = server.patch_api_key(&uid, content).await;
     meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]", ".uid" => "[ignored]", ".key" => "[ignored]" }), @r###"

meilisearch/tests/auth/authorization.rs

@@ -3,10 +3,10 @@ use std::collections::{HashMap, HashSet};
 use ::time::format_description::well_known::Rfc3339;
 use maplit::{hashmap, hashset};
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'static str>>> =
     Lazy::new(|| {
@@ -54,7 +54,6 @@ pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'
             ("GET",     "/indexes/products/stats") =>                          hashset!{"stats.get", "stats.*", "*"},
             ("GET",     "/stats") =>                                           hashset!{"stats.get", "stats.*", "*"},
             ("POST",    "/dumps") =>                                           hashset!{"dumps.create", "dumps.*", "*"},
-            ("POST",    "/snapshots") =>                                       hashset!{"snapshots.create", "snapshots.*", "*"},
             ("GET",     "/version") =>                                         hashset!{"version", "*"},
             ("GET",     "/metrics") =>                                         hashset!{"metrics.get", "metrics.*", "*"},
             ("PATCH",   "/keys/mykey/") =>                                     hashset!{"keys.update", "*"},

meilisearch/tests/auth/errors.rs

@@ -1,8 +1,8 @@
 use meili_snap::*;
+use serde_json::json;
 use uuid::Uuid;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn create_api_key_bad_description() {
@@ -90,7 +90,7 @@ async fn create_api_key_bad_actions() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"

meilisearch/tests/auth/mod.rs

@@ -7,9 +7,9 @@ mod tenant_token;
 mod tenant_token_multi_search;
 
 use actix_web::http::StatusCode;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 impl Server {
     pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {

meilisearch/tests/auth/tenant_token.rs

@@ -3,11 +3,11 @@ use std::collections::HashMap;
 use ::time::format_description::well_known::Rfc3339;
 use maplit::hashmap;
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
 use super::authorization::{ALL_ACTIONS, AUTHORIZATIONS};
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 fn generate_tenant_token(
     parent_uid: impl AsRef<str>,
@@ -233,31 +233,31 @@ async fn search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
     ];
 
@@ -386,7 +386,7 @@ async fn error_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -398,7 +398,7 @@ async fn error_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -428,15 +428,15 @@ async fn error_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -444,7 +444,7 @@ async fn error_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -456,7 +456,7 @@ async fn error_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {

meilisearch/tests/auth/tenant_token_multi_search.rs

@@ -3,11 +3,11 @@ use std::collections::HashMap;
 use ::time::format_description::well_known::Rfc3339;
 use maplit::hashmap;
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
 use super::authorization::ALL_ACTIONS;
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 fn generate_tenant_token(
     parent_uid: impl AsRef<str>,
@@ -512,31 +512,31 @@ async fn single_search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
     ];
 
@@ -564,31 +564,31 @@ async fn multi_search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}, "products": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null, "products": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"sales": Value::Null, "products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales", "products"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*", "pro*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
     ];
 
@@ -823,7 +823,7 @@ async fn error_single_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -835,7 +835,7 @@ async fn error_single_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -864,7 +864,7 @@ async fn error_multi_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -876,7 +876,7 @@ async fn error_multi_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null, "products": null}),
+            "searchRules" => json!({"sales": Value::Null, "products": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -919,15 +919,15 @@ async fn error_single_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -935,7 +935,7 @@ async fn error_single_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -947,7 +947,7 @@ async fn error_single_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -978,15 +978,15 @@ async fn error_multi_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
@@ -998,15 +998,15 @@ async fn error_multi_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -1014,7 +1014,7 @@ async fn error_multi_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -1026,7 +1026,7 @@ async fn error_multi_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null, "products": {}}),
+            "searchRules" => json!({"sales": Value::Null, "products": {}}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {

meilisearch/tests/common/index.rs

@@ -3,13 +3,12 @@ use std::panic::{catch_unwind, resume_unwind, UnwindSafe};
 use std::time::Duration;
 
 use actix_web::http::StatusCode;
+use serde_json::{json, Value};
 use tokio::time::sleep;
 use urlencoding::encode as urlencode;
 
 use super::encoder::Encoder;
 use super::service::Service;
-use super::Value;
-use crate::json;
 
 pub struct Index<'a> {
     pub uid: String,
@@ -243,9 +242,7 @@ impl Index<'_> {
 
     pub async fn delete_batch(&self, ids: Vec<u64>) -> (Value, StatusCode) {
         let url = format!("/indexes/{}/documents/delete-batch", urlencode(self.uid.as_ref()));
-        self.service
-            .post_encoded(url, serde_json::to_value(&ids).unwrap().into(), self.encoder)
-            .await
+        self.service.post_encoded(url, serde_json::to_value(&ids).unwrap(), self.encoder).await
     }
 
     pub async fn delete_batch_raw(&self, body: Value) -> (Value, StatusCode) {

meilisearch/tests/common/mod.rs

@@ -3,83 +3,9 @@ pub mod index;
 pub mod server;
 pub mod service;
 
-use std::fmt::{self, Display};
-
 pub use index::{GetAllDocumentsOptions, GetDocumentOptions};
-use meili_snap::json_string;
-use serde::{Deserialize, Serialize};
 pub use server::{default_settings, Server};
 
-#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
-pub struct Value(pub serde_json::Value);
-
-impl Value {
-    pub fn uid(&self) -> u64 {
-        if let Some(uid) = self["uid"].as_u64() {
-            uid
-        } else if let Some(uid) = self["taskUid"].as_u64() {
-            uid
-        } else {
-            panic!("Didn't find any task id in: {self}");
-        }
-    }
-}
-
-impl From<serde_json::Value> for Value {
-    fn from(value: serde_json::Value) -> Self {
-        Value(value)
-    }
-}
-
-impl std::ops::Deref for Value {
-    type Target = serde_json::Value;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl PartialEq<serde_json::Value> for Value {
-    fn eq(&self, other: &serde_json::Value) -> bool {
-        &self.0 == other
-    }
-}
-
-impl PartialEq<Value> for serde_json::Value {
-    fn eq(&self, other: &Value) -> bool {
-        self == &other.0
-    }
-}
-
-impl PartialEq<&str> for Value {
-    fn eq(&self, other: &&str) -> bool {
-        self.0.eq(other)
-    }
-}
-
-impl Display for Value {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "{}",
-            json_string!(self, { ".enqueuedAt" => "[date]", ".processedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]" })
-        )
-    }
-}
-
-impl From<Vec<Value>> for Value {
-    fn from(value: Vec<Value>) -> Self {
-        Self(value.into_iter().map(|value| value.0).collect::<serde_json::Value>())
-    }
-}
-
-#[macro_export]
-macro_rules! json {
-    ($($json:tt)+) => {
-        $crate::common::Value(serde_json::json!($($json)+))
-    };
-}
-
 /// Performs a search test on both post and get routes
 #[macro_export]
 macro_rules! test_post_get_search {

meilisearch/tests/common/server.rs

@@ -11,14 +11,13 @@ use clap::Parser;
 use meilisearch::option::{IndexerOpts, MaxMemory, Opt};
 use meilisearch::{analytics, create_app, setup_meilisearch};
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use tempfile::TempDir;
 use tokio::time::sleep;
 
 use super::index::Index;
 use super::service::Service;
 use crate::common::encoder::Encoder;
-use crate::common::Value;
-use crate::json;
 
 pub struct Server {
     pub service: Service,
@@ -157,10 +156,6 @@ impl Server {
         self.service.post("/dumps", json!(null)).await
     }
 
-    pub async fn create_snapshot(&self) -> (Value, StatusCode) {
-        self.service.post("/snapshots", json!(null)).await
-    }
-
     pub async fn index_swap(&self, value: Value) -> (Value, StatusCode) {
         self.service.post("/swap-indexes", value).await
     }
@@ -209,7 +204,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
         db_path: dir.as_ref().join("db"),
         dump_dir: dir.as_ref().join("dumps"),
         env: "development".to_owned(),
-        #[cfg(feature = "analytics")]
+        #[cfg(all(not(debug_assertions), feature = "analytics"))]
         no_analytics: true,
         max_index_size: Byte::from_unit(100.0, ByteUnit::MiB).unwrap(),
         max_task_db_size: Byte::from_unit(1.0, ByteUnit::GiB).unwrap(),

meilisearch/tests/common/service.rs

@@ -7,9 +7,9 @@ use actix_web::test::TestRequest;
 use index_scheduler::IndexScheduler;
 use meilisearch::{analytics, create_app, Opt};
 use meilisearch_auth::AuthController;
+use serde_json::Value;
 
 use crate::common::encoder::Encoder;
-use crate::common::Value;
 
 pub struct Service {
     pub index_scheduler: Arc<IndexScheduler>,

meilisearch/tests/content_type.rs

@@ -3,8 +3,9 @@
 mod common;
 
 use actix_web::test;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
+use crate::common::Server;
 
 enum HttpVerb {
     Put,

meilisearch/tests/documents/add_documents.rs

@@ -1,11 +1,11 @@
 use actix_web::test;
 use meili_snap::{json_string, snapshot};
+use serde_json::{json, Value};
 use time::format_description::well_known::Rfc3339;
 use time::OffsetDateTime;
 
 use crate::common::encoder::Encoder;
-use crate::common::{GetAllDocumentsOptions, Server, Value};
-use crate::json;
+use crate::common::{GetAllDocumentsOptions, Server};
 
 /// This is the basic usage of our API and every other tests uses the content-type application/json
 #[actix_rt::test]

meilisearch/tests/documents/delete_documents.rs

@@ -1,7 +1,7 @@
 use meili_snap::{json_string, snapshot};
+use serde_json::json;
 
 use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
 
 #[actix_rt::test]
 async fn delete_one_document_unexisting_index() {
@@ -154,19 +154,6 @@ async fn delete_document_by_filter() {
         )
         .await;
     index.wait_task(1).await;
-
-    let (stats, _) = index.stats().await;
-    snapshot!(json_string!(stats), @r###"
-    {
-      "numberOfDocuments": 4,
-      "isIndexing": false,
-      "fieldDistribution": {
-        "color": 3,
-        "id": 4
-      }
-    }
-    "###);
-
     let (response, code) =
         index.delete_document_by_filter(json!({ "filter": "color = blue"})).await;
     snapshot!(code, @"202 Accepted");
@@ -201,18 +188,6 @@ async fn delete_document_by_filter() {
     }
     "###);
 
-    let (stats, _) = index.stats().await;
-    snapshot!(json_string!(stats), @r###"
-    {
-      "numberOfDocuments": 2,
-      "isIndexing": false,
-      "fieldDistribution": {
-        "color": 1,
-        "id": 2
-      }
-    }
-    "###);
-
     let (documents, code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(documents), @r###"
@@ -266,18 +241,6 @@ async fn delete_document_by_filter() {
     }
     "###);
 
-    let (stats, _) = index.stats().await;
-    snapshot!(json_string!(stats), @r###"
-    {
-      "numberOfDocuments": 1,
-      "isIndexing": false,
-      "fieldDistribution": {
-        "color": 1,
-        "id": 1
-      }
-    }
-    "###);
-
     let (documents, code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(documents), @r###"

meilisearch/tests/documents/errors.rs

@@ -1,8 +1,8 @@
 use meili_snap::*;
+use serde_json::json;
 use urlencoding::encode;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn get_all_documents_bad_offset() {

meilisearch/tests/documents/get_documents.rs

@@ -1,11 +1,11 @@
 use actix_web::test;
 use http::header::ACCEPT_ENCODING;
 use meili_snap::*;
+use serde_json::{json, Value};
 use urlencoding::encode as urlencode;
 
 use crate::common::encoder::Encoder;
-use crate::common::{GetAllDocumentsOptions, GetDocumentOptions, Server, Value};
-use crate::json;
+use crate::common::{GetAllDocumentsOptions, GetDocumentOptions, Server};
 
 // TODO: partial test since we are testing error, amd error is not yet fully implemented in
 // transplant
@@ -40,7 +40,7 @@ async fn get_document() {
     let server = Server::new().await;
     let index = server.index("test");
     index.create(None).await;
-    let documents = json!([
+    let documents = serde_json::json!([
         {
             "id": 0,
             "nested": { "content": "foobar" },
@@ -53,7 +53,7 @@ async fn get_document() {
     assert_eq!(code, 200);
     assert_eq!(
         response,
-        json!({
+        serde_json::json!({
             "id": 0,
             "nested": { "content": "foobar" },
         })
@@ -64,7 +64,7 @@ async fn get_document() {
     assert_eq!(code, 200);
     assert_eq!(
         response,
-        json!({
+        serde_json::json!({
             "id": 0,
         })
     );
@@ -75,7 +75,7 @@ async fn get_document() {
     assert_eq!(code, 200);
     assert_eq!(
         response,
-        json!({
+        serde_json::json!({
             "nested": { "content": "foobar" },
         })
     );
@@ -122,7 +122,7 @@ async fn get_all_documents_no_options() {
     assert_eq!(code, 200);
     let arr = response["results"].as_array().unwrap();
     assert_eq!(arr.len(), 20);
-    let first = json!({
+    let first = serde_json::json!({
         "id":0,
         "isActive":false,
         "balance":"$2,668.55",

meilisearch/tests/documents/update_documents.rs

@@ -1,8 +1,7 @@
-use meili_snap::snapshot;
+use serde_json::json;
 
 use crate::common::encoder::Encoder;
 use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
 
 #[actix_rt::test]
 async fn error_document_update_create_index_bad_uid() {
@@ -85,13 +84,7 @@ async fn update_document() {
 
     let (response, code) = index.get_document(1, None).await;
     assert_eq!(code, 200);
-    snapshot!(response, @r###"
-    {
-      "doc_id": 1,
-      "content": "foo",
-      "other": "bar"
-    }
-    "###);
+    assert_eq!(response.to_string(), r##"{"doc_id":1,"content":"foo","other":"bar"}"##);
 }
 
 #[actix_rt::test]
@@ -129,13 +122,7 @@ async fn update_document_gzip_encoded() {
 
     let (response, code) = index.get_document(1, None).await;
     assert_eq!(code, 200);
-    snapshot!(response, @r###"
-    {
-      "doc_id": 1,
-      "content": "foo",
-      "other": "bar"
-    }
-    "###);
+    assert_eq!(response.to_string(), r##"{"doc_id":1,"content":"foo","other":"bar"}"##);
 }
 
 #[actix_rt::test]

meilisearch/tests/features/mod.rs

@@ -1,5 +1,6 @@
+use serde_json::json;
+
 use crate::common::Server;
-use crate::json;
 
 /// Feature name to test against.
 /// This will have to be changed by a different one when that feature is stabilized.

meilisearch/tests/index/create_index.rs

@@ -2,10 +2,10 @@ use actix_web::http::header::ContentType;
 use actix_web::test;
 use http::header::ACCEPT_ENCODING;
 use meili_snap::{json_string, snapshot};
+use serde_json::{json, Value};
 
 use crate::common::encoder::Encoder;
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 #[actix_rt::test]
 async fn create_index_no_primary_key() {
@@ -21,7 +21,7 @@ async fn create_index_no_primary_key() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -38,7 +38,7 @@ async fn create_index_with_gzip_encoded_request() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -86,7 +86,7 @@ async fn create_index_with_zlib_encoded_request() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -103,7 +103,7 @@ async fn create_index_with_brotli_encoded_request() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -136,7 +136,7 @@ async fn create_index_with_invalid_primary_key() {
 
     let (response, code) = index.get().await;
     assert_eq!(code, 200);
-    assert_eq!(response["primaryKey"], json!(null));
+    assert_eq!(response["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]

meilisearch/tests/index/delete_index.rs

@@ -1,5 +1,6 @@
+use serde_json::json;
+
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn create_and_delete_index() {

meilisearch/tests/index/errors.rs

@@ -1,7 +1,7 @@
 use meili_snap::*;
+use serde_json::json;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn get_indexes_bad_offset() {

meilisearch/tests/index/stats.rs

@@ -1,5 +1,6 @@
+use serde_json::json;
+
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn stats() {

meilisearch/tests/index/update_index.rs

@@ -1,9 +1,9 @@
+use serde_json::json;
 use time::format_description::well_known::Rfc3339;
 use time::OffsetDateTime;
 
 use crate::common::encoder::Encoder;
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn update_primary_key() {

meilisearch/tests/search/errors.rs

@@ -1,8 +1,8 @@
 use meili_snap::*;
+use serde_json::json;
 
 use super::DOCUMENTS;
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn search_unexisting_index() {

meilisearch/tests/search/facet_search.rs

@@ -1,8 +1,8 @@
 use meili_snap::snapshot;
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     json!([

meilisearch/tests/search/formatted.rs

@@ -1,8 +1,8 @@
 use insta::{allow_duplicates, assert_json_snapshot};
+use serde_json::json;
 
 use super::*;
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn formatted_contain_wildcard() {

meilisearch/tests/search/geo.rs

@@ -1,8 +1,7 @@
-use meili_snap::{json_string, snapshot};
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     json!([
@@ -61,59 +60,3 @@ async fn geo_sort_with_geo_strings() {
         )
         .await;
 }
-
-#[actix_rt::test]
-async fn geo_bounding_box_with_string_and_number() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.update_settings_filterable_attributes(json!(["_geo"])).await;
-    index.update_settings_sortable_attributes(json!(["_geo"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
-
-    index
-        .search(
-            json!({
-                "filter": "_geoBoundingBox([89, 179], [-89, -179])",
-            }),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r###"
-                {
-                  "hits": [
-                    {
-                      "id": 1,
-                      "name": "Taco Truck",
-                      "address": "444 Salsa Street, Burritoville",
-                      "type": "Mexican",
-                      "rating": 9,
-                      "_geo": {
-                        "lat": 34.0522,
-                        "lng": -118.2437
-                      }
-                    },
-                    {
-                      "id": 2,
-                      "name": "La Bella Italia",
-                      "address": "456 Elm Street, Townsville",
-                      "type": "Italian",
-                      "rating": 9,
-                      "_geo": {
-                        "lat": "45.4777599",
-                        "lng": "9.1967508"
-                      }
-                    }
-                  ],
-                  "query": "",
-                  "processingTimeMs": "[time]",
-                  "limit": 20,
-                  "offset": 0,
-                  "estimatedTotalHits": 2
-                }
-                "###);
-            },
-        )
-        .await;
-}

meilisearch/tests/search/mod.rs

@@ -10,9 +10,9 @@ mod pagination;
 mod restrict_searchable;
 
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     json!([
@@ -1104,59 +1104,3 @@ async fn camelcased_words() {
         })
         .await;
 }
-
-#[actix_rt::test]
-async fn simple_search_with_strange_synonyms() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({ "synonyms": {"&": ["to"], "to": ["&"]} })).await;
-    let r = index.wait_task(0).await;
-    meili_snap::snapshot!(r["status"], @r###""succeeded""###);
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
-    index
-        .search(json!({"q": "How to train"}), |response, code| {
-            meili_snap::snapshot!(code, @"200 OK");
-            meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
-            [
-              {
-                "title": "How to Train Your Dragon: The Hidden World",
-                "id": "166428"
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "How & train"}), |response, code| {
-            meili_snap::snapshot!(code, @"200 OK");
-            meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
-            [
-              {
-                "title": "How to Train Your Dragon: The Hidden World",
-                "id": "166428"
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "to"}), |response, code| {
-            meili_snap::snapshot!(code, @"200 OK");
-            meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
-            [
-              {
-                "title": "How to Train Your Dragon: The Hidden World",
-                "id": "166428"
-              }
-            ]
-            "###);
-        })
-        .await;
-}

meilisearch/tests/search/multi.rs

@@ -1,8 +1,8 @@
 use meili_snap::{json_string, snapshot};
+use serde_json::json;
 
 use super::{DOCUMENTS, NESTED_DOCUMENTS};
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn search_empty_list() {

meilisearch/tests/search/pagination.rs

@@ -1,5 +1,6 @@
+use serde_json::json;
+
 use crate::common::Server;
-use crate::json;
 use crate::search::DOCUMENTS;
 
 #[actix_rt::test]

meilisearch/tests/search/restrict_searchable.rs

@@ -1,9 +1,9 @@
 use meili_snap::{json_string, snapshot};
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 
 use crate::common::index::Index;
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
     let index = server.index("test");

meilisearch/tests/settings/distinct.rs

@@ -1,5 +1,6 @@
+use serde_json::json;
+
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn set_and_reset_distinct_attribute() {

meilisearch/tests/settings/errors.rs

@@ -1,7 +1,7 @@
 use meili_snap::*;
+use serde_json::json;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn settings_bad_displayed_attributes() {

meilisearch/tests/settings/get_settings.rs

@@ -1,24 +1,21 @@
 use std::collections::HashMap;
 
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|| {
     let mut map = HashMap::new();
     map.insert("displayed_attributes", json!(["*"]));
     map.insert("searchable_attributes", json!(["*"]));
     map.insert("filterable_attributes", json!([]));
-    map.insert("distinct_attribute", json!(null));
+    map.insert("distinct_attribute", json!(Value::Null));
     map.insert(
         "ranking_rules",
         json!(["words", "typo", "proximity", "attribute", "sort", "exactness"]),
     );
     map.insert("stop_words", json!([]));
-    map.insert("non_separator_tokens", json!([]));
-    map.insert("separator_tokens", json!([]));
-    map.insert("dictionary", json!([]));
     map.insert("synonyms", json!({}));
     map.insert(
         "faceting",
@@ -54,7 +51,7 @@ async fn get_settings() {
     let (response, code) = index.settings().await;
     assert_eq!(code, 200);
     let settings = response.as_object().unwrap();
-    assert_eq!(settings.keys().len(), 14);
+    assert_eq!(settings.keys().len(), 11);
     assert_eq!(settings["displayedAttributes"], json!(["*"]));
     assert_eq!(settings["searchableAttributes"], json!(["*"]));
     assert_eq!(settings["filterableAttributes"], json!([]));
@@ -65,9 +62,6 @@ async fn get_settings() {
         json!(["words", "typo", "proximity", "attribute", "sort", "exactness"])
     );
     assert_eq!(settings["stopWords"], json!([]));
-    assert_eq!(settings["nonSeparatorTokens"], json!([]));
-    assert_eq!(settings["separatorTokens"], json!([]));
-    assert_eq!(settings["dictionary"], json!([]));
     assert_eq!(
         settings["faceting"],
         json!({
@@ -229,7 +223,7 @@ macro_rules! test_setting_routes {
                         .chars()
                         .map(|c| if c == '_' { '-' } else { c })
                         .collect::<String>());
-                    let (response, code) = server.service.$write_method(url, serde_json::Value::Null.into()).await;
+                    let (response, code) = server.service.$write_method(url, serde_json::Value::Null).await;
                     assert_eq!(code, 202, "{}", response);
                     server.index("").wait_task(0).await;
                     let (response, code) = server.index("test").get().await;
@@ -278,9 +272,6 @@ test_setting_routes!(
     searchable_attributes put,
     distinct_attribute put,
     stop_words put,
-    separator_tokens put,
-    non_separator_tokens put,
-    dictionary put,
     ranking_rules put,
     synonyms put,
     pagination patch,

meilisearch/tests/settings/mod.rs

@@ -1,4 +1,3 @@
 mod distinct;
 mod errors;
 mod get_settings;
-mod tokenizer_customization;

meilisearch/tests/settings/tokenizer_customization.rs

@@ -1,467 +0,0 @@
-use meili_snap::{json_string, snapshot};
-
-use crate::common::Server;
-use crate::json;
-
-#[actix_rt::test]
-async fn set_and_reset() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let (_response, _code) = index
-        .update_settings(json!({
-            "nonSeparatorTokens": ["#", "&"],
-            "separatorTokens": ["&sep", "<br/>"],
-            "dictionary": ["J.R.R.", "J. R. R."],
-        }))
-        .await;
-    index.wait_task(0).await;
-
-    let (response, _) = index.settings().await;
-    snapshot!(json_string!(response["nonSeparatorTokens"]), @r###"
-    [
-      "#",
-      "&"
-    ]
-    "###);
-    snapshot!(json_string!(response["separatorTokens"]), @r###"
-    [
-      "&sep",
-      "<br/>"
-    ]
-    "###);
-    snapshot!(json_string!(response["dictionary"]), @r###"
-    [
-      "J. R. R.",
-      "J.R.R."
-    ]
-    "###);
-
-    index
-        .update_settings(json!({
-            "nonSeparatorTokens": null,
-            "separatorTokens": null,
-            "dictionary": null,
-        }))
-        .await;
-
-    index.wait_task(1).await;
-
-    let (response, _) = index.settings().await;
-    snapshot!(json_string!(response["nonSeparatorTokens"]), @"[]");
-    snapshot!(json_string!(response["separatorTokens"]), @"[]");
-    snapshot!(json_string!(response["dictionary"]), @"[]");
-}
-
-#[actix_rt::test]
-async fn set_and_search() {
-    let documents = json!([
-        {
-            "id": 1,
-            "content": "Mac & cheese",
-        },
-        {
-            "id": 2,
-            "content": "G#D#G#D#G#C#D#G#C#",
-        },
-        {
-            "id": 3,
-            "content": "Mac&sep&&sepcheese",
-        },
-    ]);
-
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
-    let (_response, _code) = index
-        .update_settings(json!({
-            "nonSeparatorTokens": ["#", "&"],
-            "separatorTokens": ["<br/>", "&sep"],
-            "dictionary": ["#", "A#", "B#", "C#", "D#", "E#", "F#", "G#"],
-        }))
-        .await;
-    index.wait_task(1).await;
-
-    index
-        .search(json!({"q": "&", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 1,
-                "content": "Mac & cheese",
-                "_formatted": {
-                  "id": "1",
-                  "content": "Mac <em>&</em> cheese"
-                }
-              },
-              {
-                "id": 3,
-                "content": "Mac&sep&&sepcheese",
-                "_formatted": {
-                  "id": "3",
-                  "content": "Mac&sep<em>&</em>&sepcheese"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(
-            json!({"q": "Mac & cheese", "attributesToHighlight": ["content"]}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "id": 1,
-                    "content": "Mac & cheese",
-                    "_formatted": {
-                      "id": "1",
-                      "content": "<em>Mac</em> <em>&</em> <em>cheese</em>"
-                    }
-                  },
-                  {
-                    "id": 3,
-                    "content": "Mac&sep&&sepcheese",
-                    "_formatted": {
-                      "id": "3",
-                      "content": "<em>Mac</em>&sep<em>&</em>&sep<em>cheese</em>"
-                    }
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .search(
-            json!({"q": "Mac&sep&&sepcheese", "attributesToHighlight": ["content"]}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "id": 1,
-                    "content": "Mac & cheese",
-                    "_formatted": {
-                      "id": "1",
-                      "content": "<em>Mac</em> <em>&</em> <em>cheese</em>"
-                    }
-                  },
-                  {
-                    "id": 3,
-                    "content": "Mac&sep&&sepcheese",
-                    "_formatted": {
-                      "id": "3",
-                      "content": "<em>Mac</em>&sep<em>&</em>&sep<em>cheese</em>"
-                    }
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .search(json!({"q": "C#D#G", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 2,
-                "content": "G#D#G#D#G#C#D#G#C#",
-                "_formatted": {
-                  "id": "2",
-                  "content": "<em>G</em>#<em>D#</em><em>G</em>#<em>D#</em><em>G</em>#<em>C#</em><em>D#</em><em>G</em>#<em>C#</em>"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "#", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @"[]");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn advanced_synergies() {
-    let documents = json!([
-        {
-            "id": 1,
-            "content": "J.R.R. Tolkien",
-        },
-        {
-            "id": 2,
-            "content": "J. R. R. Tolkien",
-        },
-        {
-            "id": 3,
-            "content": "jrr Tolkien",
-        },
-        {
-            "id": 4,
-            "content": "J.K. Rowlings",
-        },
-        {
-            "id": 5,
-            "content": "J. K. Rowlings",
-        },
-        {
-            "id": 6,
-            "content": "jk Rowlings",
-        },
-    ]);
-
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
-    let (_response, _code) = index
-        .update_settings(json!({
-            "dictionary": ["J.R.R.", "J. R. R."],
-            "synonyms": {
-                "J.R.R.": ["jrr", "J. R. R."],
-                "J. R. R.": ["jrr", "J.R.R."],
-                "jrr": ["J.R.R.", "J. R. R."],
-                "J.K.": ["jk", "J. K."],
-                "J. K.": ["jk", "J.K."],
-                "jk": ["J.K.", "J. K."],
-            }
-        }))
-        .await;
-    index.wait_task(1).await;
-
-    index
-        .search(json!({"q": "J.R.R.", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 1,
-                "content": "J.R.R. Tolkien",
-                "_formatted": {
-                  "id": "1",
-                  "content": "<em>J.R.R.</em> Tolkien"
-                }
-              },
-              {
-                "id": 2,
-                "content": "J. R. R. Tolkien",
-                "_formatted": {
-                  "id": "2",
-                  "content": "<em>J. R. R.</em> Tolkien"
-                }
-              },
-              {
-                "id": 3,
-                "content": "jrr Tolkien",
-                "_formatted": {
-                  "id": "3",
-                  "content": "<em>jrr</em> Tolkien"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "jrr", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 3,
-                "content": "jrr Tolkien",
-                "_formatted": {
-                  "id": "3",
-                  "content": "<em>jrr</em> Tolkien"
-                }
-              },
-              {
-                "id": 1,
-                "content": "J.R.R. Tolkien",
-                "_formatted": {
-                  "id": "1",
-                  "content": "<em>J.R.R.</em> Tolkien"
-                }
-              },
-              {
-                "id": 2,
-                "content": "J. R. R. Tolkien",
-                "_formatted": {
-                  "id": "2",
-                  "content": "<em>J. R. R.</em> Tolkien"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "J. R. R.", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 2,
-                "content": "J. R. R. Tolkien",
-                "_formatted": {
-                  "id": "2",
-                  "content": "<em>J. R. R.</em> Tolkien"
-                }
-              },
-              {
-                "id": 1,
-                "content": "J.R.R. Tolkien",
-                "_formatted": {
-                  "id": "1",
-                  "content": "<em>J.R.R.</em> Tolkien"
-                }
-              },
-              {
-                "id": 3,
-                "content": "jrr Tolkien",
-                "_formatted": {
-                  "id": "3",
-                  "content": "<em>jrr</em> Tolkien"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    // Only update dictionary, the synonyms should be recomputed.
-    let (_response, _code) = index
-        .update_settings(json!({
-            "dictionary": ["J.R.R.", "J. R. R.", "J.K.", "J. K."],
-        }))
-        .await;
-    index.wait_task(2).await;
-
-    index
-        .search(json!({"q": "jk", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 6,
-                "content": "jk Rowlings",
-                "_formatted": {
-                  "id": "6",
-                  "content": "<em>jk</em> Rowlings"
-                }
-              },
-              {
-                "id": 4,
-                "content": "J.K. Rowlings",
-                "_formatted": {
-                  "id": "4",
-                  "content": "<em>J.K.</em> Rowlings"
-                }
-              },
-              {
-                "id": 5,
-                "content": "J. K. Rowlings",
-                "_formatted": {
-                  "id": "5",
-                  "content": "<em>J. K.</em> Rowlings"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "J.K.", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 4,
-                "content": "J.K. Rowlings",
-                "_formatted": {
-                  "id": "4",
-                  "content": "<em>J.K.</em> Rowlings"
-                }
-              },
-              {
-                "id": 5,
-                "content": "J. K. Rowlings",
-                "_formatted": {
-                  "id": "5",
-                  "content": "<em>J. K.</em> Rowlings"
-                }
-              },
-              {
-                "id": 6,
-                "content": "jk Rowlings",
-                "_formatted": {
-                  "id": "6",
-                  "content": "<em>jk</em> Rowlings"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "J. K.", "attributesToHighlight": ["content"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "id": 5,
-                "content": "J. K. Rowlings",
-                "_formatted": {
-                  "id": "5",
-                  "content": "<em>J. K.</em> Rowlings"
-                }
-              },
-              {
-                "id": 4,
-                "content": "J.K. Rowlings",
-                "_formatted": {
-                  "id": "4",
-                  "content": "<em>J.K.</em> Rowlings"
-                }
-              },
-              {
-                "id": 6,
-                "content": "jk Rowlings",
-                "_formatted": {
-                  "id": "6",
-                  "content": "<em>jk</em> Rowlings"
-                }
-              },
-              {
-                "id": 2,
-                "content": "J. R. R. Tolkien",
-                "_formatted": {
-                  "id": "2",
-                  "content": "<em>J. R.</em> R. Tolkien"
-                }
-              }
-            ]
-            "###);
-        })
-        .await;
-}

meilisearch/tests/snapshot/mod.rs

@@ -1,13 +1,11 @@
 use std::time::Duration;
 
 use actix_rt::time::sleep;
-use meili_snap::{json_string, snapshot};
 use meilisearch::option::ScheduleSnapshot;
 use meilisearch::Opt;
 
 use crate::common::server::default_settings;
 use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
 
 macro_rules! verify_snapshot {
     (
@@ -46,7 +44,7 @@ async fn perform_snapshot() {
 
     let index = server.index("test");
     index
-        .update_settings(json! ({
+        .update_settings(serde_json::json! ({
         "searchableAttributes": [],
         }))
         .await;
@@ -92,95 +90,3 @@ async fn perform_snapshot() {
         server.index("test1").settings(),
     );
 }
-
-#[actix_rt::test]
-async fn perform_on_demand_snapshot() {
-    let temp = tempfile::tempdir().unwrap();
-    let snapshot_dir = tempfile::tempdir().unwrap();
-
-    let options =
-        Opt { snapshot_dir: snapshot_dir.path().to_owned(), ..default_settings(temp.path()) };
-
-    let server = Server::new_with_options(options).await.unwrap();
-
-    let index = server.index("catto");
-    index
-        .update_settings(json! ({
-        "searchableAttributes": [],
-        }))
-        .await;
-
-    index.load_test_set().await;
-
-    server.index("doggo").create(Some("bone")).await;
-    index.wait_task(2).await;
-
-    server.index("doggo").create(Some("bone")).await;
-    index.wait_task(2).await;
-
-    let (task, code) = server.create_snapshot().await;
-    snapshot!(code, @"202 Accepted");
-    snapshot!(json_string!(task, { ".enqueuedAt" => "[date]" }), @r###"
-    {
-      "taskUid": 4,
-      "indexUid": null,
-      "status": "enqueued",
-      "type": "snapshotCreation",
-      "enqueuedAt": "[date]"
-    }
-    "###);
-    let task = index.wait_task(task.uid()).await;
-    snapshot!(json_string!(task, { ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]" }), @r###"
-    {
-      "uid": 4,
-      "indexUid": null,
-      "status": "succeeded",
-      "type": "snapshotCreation",
-      "canceledBy": null,
-      "error": null,
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let temp = tempfile::tempdir().unwrap();
-
-    let snapshots: Vec<String> = std::fs::read_dir(&snapshot_dir)
-        .unwrap()
-        .map(|entry| entry.unwrap().path().file_name().unwrap().to_str().unwrap().to_string())
-        .collect();
-    meili_snap::snapshot!(format!("{snapshots:?}"), @r###"["db.snapshot"]"###);
-
-    let snapshot_path = snapshot_dir.path().to_owned().join("db.snapshot");
-    #[cfg_attr(windows, allow(unused))]
-    let snapshot_meta = std::fs::metadata(&snapshot_path).unwrap();
-
-    #[cfg(unix)]
-    {
-        use std::os::unix::fs::PermissionsExt;
-        let mode = snapshot_meta.permissions().mode();
-        //                                                    rwxrwxrwx
-        meili_snap::snapshot!(format!("{:b}", mode), @"1000000100100100");
-    }
-
-    let options = Opt { import_snapshot: Some(snapshot_path), ..default_settings(temp.path()) };
-
-    let snapshot_server = Server::new_with_options(options).await.unwrap();
-
-    verify_snapshot!(server, snapshot_server, |server| =>
-        server.list_indexes(None, None),
-        // for some reason the db sizes differ. this may be due to the compaction options we have
-        // set when performing the snapshot
-        //server.stats(),
-
-        // The original instance contains the snapshotCreation task, while the snapshotted-instance does not. For this reason we need to compare the task queue **after** the task 4
-        server.tasks_filter("?from=2"),
-
-        server.index("catto").get_all_documents(GetAllDocumentsOptions::default()),
-        server.index("catto").settings(),
-        server.index("doggo").get_all_documents(GetAllDocumentsOptions::default()),
-        server.index("doggo").settings(),
-    );
-}

meilisearch/tests/stats/mod.rs

@@ -1,8 +1,8 @@
+use serde_json::json;
 use time::format_description::well_known::Rfc3339;
 use time::OffsetDateTime;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn get_settings_unexisting_index() {

meilisearch/tests/swap_indexes/errors.rs

@@ -1,7 +1,7 @@
 use meili_snap::*;
+use serde_json::json;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn swap_indexes_bad_format() {

meilisearch/tests/swap_indexes/mod.rs

@@ -1,9 +1,9 @@
 mod errors;
 
 use meili_snap::{json_string, snapshot};
+use serde_json::json;
 
 use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
 
 #[actix_rt::test]
 async fn swap_indexes() {

meilisearch/tests/tasks/mod.rs

@@ -1,11 +1,11 @@
 mod errors;
 
 use meili_snap::insta::assert_json_snapshot;
+use serde_json::json;
 use time::format_description::well_known::Rfc3339;
 use time::OffsetDateTime;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn error_get_unexisting_task_status() {
@@ -33,7 +33,7 @@ async fn get_task_status() {
     index.create(None).await;
     index
         .add_documents(
-            json!([{
+            serde_json::json!([{
                 "id": 1,
                 "content": "foobar",
             }]),

milli/Cargo.toml

@@ -17,10 +17,10 @@ bincode = "1.3.3"
 bstr = "1.4.0"
 bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
 byteorder = "1.4.3"
-charabia = { version = "0.8.3", default-features = false }
+charabia = { version = "0.8.2", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.8"
-deserr = { version = "0.6.0", features = ["actix-web"]}
+deserr = "0.5.0"
 either = { version = "1.8.1", features = ["serde"] }
 flatten-serde-json = { path = "../flatten-serde-json" }
 fst = "0.4.7"
@@ -32,18 +32,18 @@ grenad = { version = "0.4.4", default-features = false, features = [
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.7", default-features = false, features = [
     "lmdb", "read-txn-no-tls"
 ] }
-indexmap = { version = "2.0.0", features = ["serde"] }
+indexmap = { version = "1.9.3", features = ["serde"] }
 instant-distance = { version = "0.6.1", features = ["with-serde"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
-memmap2 = "0.7.1"
+memmap2 = "0.5.10"
 obkv = "0.2.0"
 once_cell = "1.17.1"
 ordered-float = "3.6.0"
 rand_pcg = { version = "0.3.1", features = ["serde1"] }
 rayon = "1.7.0"
 roaring = "0.10.1"
-rstar = { version = "0.11.0", features = ["serde"] }
+rstar = { version = "0.10.0", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
 slice-group-by = "0.3.0"
@@ -63,7 +63,7 @@ uuid = { version = "1.3.1", features = ["v4"] }
 filter-parser = { path = "../filter-parser" }
 
 # documents words self-join
-itertools = "0.11.0"
+itertools = "0.10.5"
 
 # profiling
 puffin = "0.16.0"

milli/src/documents/enriched.rs

@@ -1,5 +1,4 @@
 use std::fs::File;
-use std::io::BufReader;
 use std::{io, str};
 
 use obkv::KvReader;
@@ -20,14 +19,14 @@ use crate::FieldId;
 pub struct EnrichedDocumentsBatchReader<R> {
     documents: DocumentsBatchReader<R>,
     primary_key: String,
-    external_ids: grenad::ReaderCursor<BufReader<File>>,
+    external_ids: grenad::ReaderCursor<File>,
 }
 
 impl<R: io::Read + io::Seek> EnrichedDocumentsBatchReader<R> {
     pub fn new(
         documents: DocumentsBatchReader<R>,
         primary_key: String,
-        external_ids: grenad::Reader<BufReader<File>>,
+        external_ids: grenad::Reader<File>,
     ) -> Result<Self, Error> {
         if documents.documents_count() as u64 == external_ids.len() {
             Ok(EnrichedDocumentsBatchReader {
@@ -76,7 +75,7 @@ pub struct EnrichedDocument<'a> {
 pub struct EnrichedDocumentsBatchCursor<R> {
     documents: DocumentsBatchCursor<R>,
     primary_key: String,
-    external_ids: grenad::ReaderCursor<BufReader<File>>,
+    external_ids: grenad::ReaderCursor<File>,
 }
 
 impl<R> EnrichedDocumentsBatchCursor<R> {

milli/src/error.rs

@@ -47,8 +47,6 @@ pub enum InternalError {
     IndexingMergingKeys { process: &'static str },
     #[error("{}", HeedError::InvalidDatabaseTyping)]
     InvalidDatabaseTyping,
-    #[error("Could not access the inner of a buf-reader/writer: {0}")]
-    BufIntoInnerError(String),
     #[error(transparent)]
     RayonThreadPool(#[from] ThreadPoolBuildError),
     #[error(transparent)]
@@ -124,28 +122,22 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
         .field,
         match .valid_fields.is_empty() {
             true => "This index does not have configured sortable attributes.".to_string(),
-            false => format!("Available sortable attributes are: `{}{}`.",
-                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
-                    .hidden_fields.then_some(", <..hidden-attributes>").unwrap_or(""),
+            false => format!("Available sortable attributes are: `{}`.",
+                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
                 ),
         }
     )]
-    InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String>, hidden_fields: bool },
+    InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
     #[error("Attribute `{}` is not facet-searchable. {}",
         .field,
         match .valid_fields.is_empty() {
             true => "This index does not have configured facet-searchable attributes. To make it facet-searchable add it to the `filterableAttributes` index settings.".to_string(),
-            false => format!("Available facet-searchable attributes are: `{}{}`. To make it facet-searchable add it to the `filterableAttributes` index settings.",
-                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
-                    .hidden_fields.then_some(", <..hidden-attributes>").unwrap_or(""),
+            false => format!("Available facet-searchable attributes are: `{}`. To make it facet-searchable add it to the `filterableAttributes` index settings.",
+                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
                 ),
         }
     )]
-    InvalidFacetSearchFacetName {
-        field: String,
-        valid_fields: BTreeSet<String>,
-        hidden_fields: bool,
-    },
+    InvalidFacetSearchFacetName { field: String, valid_fields: BTreeSet<String> },
     #[error("Attribute `{}` is not searchable. Available searchable attributes are: `{}{}`.",
         .field,
         .valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
@@ -348,11 +340,8 @@ fn conditionally_lookup_for_error_message() {
     ];
 
     for (list, suffix) in messages {
-        let err = UserError::InvalidSortableAttribute {
-            field: "name".to_string(),
-            valid_fields: list,
-            hidden_fields: false,
-        };
+        let err =
+            UserError::InvalidSortableAttribute { field: "name".to_string(), valid_fields: list };
 
         assert_eq!(err.to_string(), format!("{} {}", prefix, suffix));
     }

milli/src/index.rs

@@ -1,5 +1,5 @@
 use std::borrow::Cow;
-use std::collections::{BTreeMap, BTreeSet, HashMap, HashSet};
+use std::collections::{BTreeSet, HashMap, HashSet};
 use std::fs::File;
 use std::mem::size_of;
 use std::path::Path;
@@ -61,12 +61,8 @@ pub mod main_key {
     pub const USER_DEFINED_SEARCHABLE_FIELDS_KEY: &str = "user-defined-searchable-fields";
     pub const SOFT_EXTERNAL_DOCUMENTS_IDS_KEY: &str = "soft-external-documents-ids";
     pub const STOP_WORDS_KEY: &str = "stop-words";
-    pub const NON_SEPARATOR_TOKENS_KEY: &str = "non-separator-tokens";
-    pub const SEPARATOR_TOKENS_KEY: &str = "separator-tokens";
-    pub const DICTIONARY_KEY: &str = "dictionary";
     pub const STRING_FACETED_DOCUMENTS_IDS_PREFIX: &str = "string-faceted-documents-ids";
     pub const SYNONYMS_KEY: &str = "synonyms";
-    pub const USER_DEFINED_SYNONYMS_KEY: &str = "user-defined-synonyms";
     pub const WORDS_FST_KEY: &str = "words-fst";
     pub const WORDS_PREFIXES_FST_KEY: &str = "words-prefixes-fst";
     pub const CREATED_AT_KEY: &str = "created-at";
@@ -655,26 +651,6 @@ impl Index {
         }
     }
 
-    /* remove hidden fields */
-    pub fn remove_hidden_fields(
-        &self,
-        rtxn: &RoTxn,
-        fields: impl IntoIterator<Item = impl AsRef<str>>,
-    ) -> Result<(BTreeSet<String>, bool)> {
-        let mut valid_fields =
-            fields.into_iter().map(|f| f.as_ref().to_string()).collect::<BTreeSet<String>>();
-
-        let fields_len = valid_fields.len();
-
-        if let Some(dn) = self.displayed_fields(rtxn)? {
-            let displayable_names = dn.iter().map(|s| s.to_string()).collect();
-            valid_fields = &valid_fields & &displayable_names;
-        }
-
-        let hidden_fields = fields_len > valid_fields.len();
-        Ok((valid_fields, hidden_fields))
-    }
-
     /* searchable fields */
 
     /// Write the user defined searchable fields and generate the real searchable fields from the specified fields ids map.
@@ -1079,116 +1055,18 @@ impl Index {
         }
     }
 
-    /* non separator tokens */
-
-    pub(crate) fn put_non_separator_tokens(
-        &self,
-        wtxn: &mut RwTxn,
-        set: &BTreeSet<String>,
-    ) -> heed::Result<()> {
-        self.main.put::<_, Str, SerdeBincode<_>>(wtxn, main_key::NON_SEPARATOR_TOKENS_KEY, set)
-    }
-
-    pub(crate) fn delete_non_separator_tokens(&self, wtxn: &mut RwTxn) -> heed::Result<bool> {
-        self.main.delete::<_, Str>(wtxn, main_key::NON_SEPARATOR_TOKENS_KEY)
-    }
-
-    pub fn non_separator_tokens(&self, rtxn: &RoTxn) -> Result<Option<BTreeSet<String>>> {
-        Ok(self.main.get::<_, Str, SerdeBincode<BTreeSet<String>>>(
-            rtxn,
-            main_key::NON_SEPARATOR_TOKENS_KEY,
-        )?)
-    }
-
-    /* separator tokens */
-
-    pub(crate) fn put_separator_tokens(
-        &self,
-        wtxn: &mut RwTxn,
-        set: &BTreeSet<String>,
-    ) -> heed::Result<()> {
-        self.main.put::<_, Str, SerdeBincode<_>>(wtxn, main_key::SEPARATOR_TOKENS_KEY, set)
-    }
-
-    pub(crate) fn delete_separator_tokens(&self, wtxn: &mut RwTxn) -> heed::Result<bool> {
-        self.main.delete::<_, Str>(wtxn, main_key::SEPARATOR_TOKENS_KEY)
-    }
-
-    pub fn separator_tokens(&self, rtxn: &RoTxn) -> Result<Option<BTreeSet<String>>> {
-        Ok(self
-            .main
-            .get::<_, Str, SerdeBincode<BTreeSet<String>>>(rtxn, main_key::SEPARATOR_TOKENS_KEY)?)
-    }
-
-    /* separators easing method */
-
-    pub fn allowed_separators(&self, rtxn: &RoTxn) -> Result<Option<BTreeSet<String>>> {
-        let default_separators =
-            charabia::separators::DEFAULT_SEPARATORS.iter().map(|s| s.to_string());
-        let mut separators: Option<BTreeSet<_>> = None;
-        if let Some(mut separator_tokens) = self.separator_tokens(rtxn)? {
-            separator_tokens.extend(default_separators.clone());
-            separators = Some(separator_tokens);
-        }
-
-        if let Some(non_separator_tokens) = self.non_separator_tokens(rtxn)? {
-            separators = separators
-                .or_else(|| Some(default_separators.collect()))
-                .map(|separators| &separators - &non_separator_tokens);
-        }
-
-        Ok(separators)
-    }
-
-    /* dictionary */
-
-    pub(crate) fn put_dictionary(
-        &self,
-        wtxn: &mut RwTxn,
-        set: &BTreeSet<String>,
-    ) -> heed::Result<()> {
-        self.main.put::<_, Str, SerdeBincode<_>>(wtxn, main_key::DICTIONARY_KEY, set)
-    }
-
-    pub(crate) fn delete_dictionary(&self, wtxn: &mut RwTxn) -> heed::Result<bool> {
-        self.main.delete::<_, Str>(wtxn, main_key::DICTIONARY_KEY)
-    }
-
-    pub fn dictionary(&self, rtxn: &RoTxn) -> Result<Option<BTreeSet<String>>> {
-        Ok(self
-            .main
-            .get::<_, Str, SerdeBincode<BTreeSet<String>>>(rtxn, main_key::DICTIONARY_KEY)?)
-    }
-
     /* synonyms */
 
     pub(crate) fn put_synonyms(
         &self,
         wtxn: &mut RwTxn,
         synonyms: &HashMap<Vec<String>, Vec<Vec<String>>>,
-        user_defined_synonyms: &BTreeMap<String, Vec<String>>,
     ) -> heed::Result<()> {
-        self.main.put::<_, Str, SerdeBincode<_>>(wtxn, main_key::SYNONYMS_KEY, synonyms)?;
-        self.main.put::<_, Str, SerdeBincode<_>>(
-            wtxn,
-            main_key::USER_DEFINED_SYNONYMS_KEY,
-            user_defined_synonyms,
-        )
+        self.main.put::<_, Str, SerdeBincode<_>>(wtxn, main_key::SYNONYMS_KEY, synonyms)
     }
 
     pub(crate) fn delete_synonyms(&self, wtxn: &mut RwTxn) -> heed::Result<bool> {
-        self.main.delete::<_, Str>(wtxn, main_key::SYNONYMS_KEY)?;
-        self.main.delete::<_, Str>(wtxn, main_key::USER_DEFINED_SYNONYMS_KEY)
-    }
-
-    pub fn user_defined_synonyms(
-        &self,
-        rtxn: &RoTxn,
-    ) -> heed::Result<BTreeMap<String, Vec<String>>> {
-        Ok(self
-            .main
-            .get::<_, Str, SerdeBincode<_>>(rtxn, main_key::USER_DEFINED_SYNONYMS_KEY)?
-            .unwrap_or_default())
+        self.main.delete::<_, Str>(wtxn, main_key::SYNONYMS_KEY)
     }
 
     pub fn synonyms(&self, rtxn: &RoTxn) -> heed::Result<HashMap<Vec<String>, Vec<Vec<String>>>> {
@@ -1840,11 +1718,11 @@ pub(crate) mod tests {
             .unwrap();
         index
             .add_documents(documents!([
-                { "id": 0, "_geo": { "lat": "0", "lng": "0" } },
-                { "id": 1, "_geo": { "lat": 0, "lng": "-175" } },
-                { "id": 2, "_geo": { "lat": "0", "lng": 175 } },
+                { "id": 0, "_geo": { "lat": 0, "lng": 0 } },
+                { "id": 1, "_geo": { "lat": 0, "lng": -175 } },
+                { "id": 2, "_geo": { "lat": 0, "lng": 175 } },
                 { "id": 3, "_geo": { "lat": 85, "lng": 0 } },
-                { "id": 4, "_geo": { "lat": "-85", "lng": "0" } },
+                { "id": 4, "_geo": { "lat": -85, "lng": 0 } },
             ]))
             .unwrap();
 

milli/src/lib.rs

@@ -97,7 +97,7 @@ const MAX_LMDB_KEY_LENGTH: usize = 500;
 ///
 /// This number is determined by the keys of the different facet databases
 /// and adding a margin of safety.
-pub const MAX_FACET_VALUE_LENGTH: usize = MAX_LMDB_KEY_LENGTH - 32;
+pub const MAX_FACET_VALUE_LENGTH: usize = MAX_LMDB_KEY_LENGTH - 20;
 
 /// The maximum length a word can be
 pub const MAX_WORD_LENGTH: usize = MAX_LMDB_KEY_LENGTH / 2;
@@ -293,15 +293,15 @@ pub fn normalize_facet(original: &str) -> String {
 #[derive(serde::Serialize, serde::Deserialize, Debug)]
 #[serde(transparent)]
 pub struct VectorOrArrayOfVectors {
-    #[serde(with = "either::serde_untagged_optional")]
-    inner: Option<either::Either<Vec<f32>, Vec<Vec<f32>>>>,
+    #[serde(with = "either::serde_untagged")]
+    inner: either::Either<Vec<f32>, Vec<Vec<f32>>>,
 }
 
 impl VectorOrArrayOfVectors {
-    pub fn into_array_of_vectors(self) -> Option<Vec<Vec<f32>>> {
-        match self.inner? {
-            either::Either::Left(vector) => Some(vec![vector]),
-            either::Either::Right(vectors) => Some(vectors),
+    pub fn into_array_of_vectors(self) -> Vec<Vec<f32>> {
+        match self.inner {
+            either::Either::Left(vector) => vec![vector],
+            either::Either::Right(vectors) => vectors,
         }
     }
 }

milli/src/search/mod.rs

@@ -280,13 +280,9 @@ impl<'a> SearchForFacetValues<'a> {
 
         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,
+                valid_fields: filterable_fields.into_iter().collect(),
             }
             .into());
         }

milli/src/search/new/bucket_sort.rs

@@ -91,12 +91,11 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     /// Update the universes accordingly and inform the logger.
     macro_rules! back {
         () => {
-            // FIXME: temporarily disabled assert: see <https://github.com/meilisearch/meilisearch/pull/4013>
-            // assert!(
-            //     ranking_rule_universes[cur_ranking_rule_index].is_empty(),
-            //     "The ranking rule {} did not sort its bucket exhaustively",
-            //     ranking_rules[cur_ranking_rule_index].id()
-            // );
+            assert!(
+                ranking_rule_universes[cur_ranking_rule_index].is_empty(),
+                "The ranking rule {} did not sort its bucket exhaustively",
+                ranking_rules[cur_ranking_rule_index].id()
+            );
             logger.end_iteration_ranking_rule(
                 cur_ranking_rule_index,
                 ranking_rules[cur_ranking_rule_index].as_ref(),

milli/src/search/new/matches/mod.rs

@@ -418,11 +418,19 @@ impl<'t> Matcher<'t, '_> {
         } else {
             match &self.matches {
                 Some((tokens, matches)) => {
+                    // If the text has to be cropped,
+                    // compute the best interval to crop around.
+                    let matches = match format_options.crop {
+                        Some(crop_size) if crop_size > 0 => {
+                            self.find_best_match_interval(matches, crop_size)
+                        }
+                        _ => matches,
+                    };
+
                     // If the text has to be cropped,
                     // crop around the best interval.
                     let (byte_start, byte_end) = match format_options.crop {
                         Some(crop_size) if crop_size > 0 => {
-                            let matches = self.find_best_match_interval(matches, crop_size);
                             self.crop_bounds(tokens, matches, crop_size)
                         }
                         _ => (0, self.text.len()),
@@ -442,11 +450,6 @@ impl<'t> Matcher<'t, '_> {
                         for m in matches {
                             let token = &tokens[m.token_position];
 
-                            // skip matches out of the crop window.
-                            if token.byte_start < byte_start || token.byte_end > byte_end {
-                                continue;
-                            }
-
                             if byte_index < token.byte_start {
                                 formatted.push(&self.text[byte_index..token.byte_start]);
                             }
@@ -797,37 +800,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn format_highlight_crop_phrase_query() {
-        //! testing: https://github.com/meilisearch/meilisearch/issues/3975
-        let temp_index = TempIndex::new();
-        temp_index
-            .add_documents(documents!([
-                { "id": 1, "text": "The groundbreaking invention had the power to split the world between those who embraced progress and those who resisted change!" }
-            ]))
-            .unwrap();
-        let rtxn = temp_index.read_txn().unwrap();
-
-        let format_options = FormatOptions { highlight: true, crop: Some(10) };
-        let text = "The groundbreaking invention had the power to split the world between those who embraced progress and those who resisted change!";
-
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "\"the world\"");
-        let mut matcher = builder.build(text);
-        // should return 10 words with a marker at the start as well the end, and the highlighted matches.
-        insta::assert_snapshot!(
-            matcher.format(format_options),
-            @"…had the power to split <em>the</em> <em>world</em> between those who…"
-        );
-
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "those \"and those\"");
-        let mut matcher = builder.build(text);
-        // should highlight "those" and the phrase "and those".
-        insta::assert_snapshot!(
-            matcher.format(format_options),
-            @"…world between <em>those</em> who embraced progress <em>and</em> <em>those</em> who resisted…"
-        );
-    }
-
     #[test]
     fn smaller_crop_size() {
         //! testing: https://github.com/meilisearch/specifications/pull/120#discussion_r836536295

milli/src/search/new/mod.rs

@@ -20,7 +20,7 @@ mod sort;
 #[cfg(test)]
 mod tests;
 
-use std::collections::HashSet;
+use std::collections::{BTreeSet, HashSet};
 
 use bucket_sort::{bucket_sort, BucketSortOutput};
 use charabia::TokenizerBuilder;
@@ -108,11 +108,24 @@ impl<'ctx> SearchContext<'ctx> {
                 (None, None) => continue,
                 // The field is not searchable => User error
                 (_fid, Some(false)) => {
-                    let (valid_fields, hidden_fields) = match searchable_names {
-                        Some(sn) => self.index.remove_hidden_fields(self.txn, sn)?,
-                        None => self.index.remove_hidden_fields(self.txn, fids_map.names())?,
-                    };
+                    let mut valid_fields: BTreeSet<_> =
+                        fids_map.names().map(String::from).collect();
 
+                    // Filter by the searchable names
+                    if let Some(sn) = searchable_names {
+                        let searchable_names = sn.iter().map(|s| s.to_string()).collect();
+                        valid_fields = &valid_fields & &searchable_names;
+                    }
+
+                    let searchable_count = valid_fields.len();
+
+                    // Remove hidden fields
+                    if let Some(dn) = self.index.displayed_fields(self.txn)? {
+                        let displayable_names = dn.iter().map(|s| s.to_string()).collect();
+                        valid_fields = &valid_fields & &displayable_names;
+                    }
+
+                    let hidden_fields = searchable_count > valid_fields.len();
                     let field = field_name.to_string();
                     return Err(UserError::InvalidSearchableAttribute {
                         field,
@@ -475,20 +488,6 @@ pub fn execute_search(
             tokbuilder.stop_words(stop_words);
         }
 
-        let separators = ctx.index.allowed_separators(ctx.txn)?;
-        let separators: Option<Vec<_>> =
-            separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
-        if let Some(ref separators) = separators {
-            tokbuilder.separators(separators);
-        }
-
-        let dictionary = ctx.index.dictionary(ctx.txn)?;
-        let dictionary: Option<Vec<_>> =
-            dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
-        if let Some(ref dictionary) = dictionary {
-            tokbuilder.words_dict(dictionary);
-        }
-
         let script_lang_map = ctx.index.script_language(ctx.txn)?;
         if !script_lang_map.is_empty() {
             tokbuilder.allow_list(&script_lang_map);
@@ -591,24 +590,16 @@ fn check_sort_criteria(ctx: &SearchContext, sort_criteria: Option<&Vec<AscDesc>>
     for asc_desc in sort_criteria {
         match asc_desc.member() {
             Member::Field(ref field) if !crate::is_faceted(field, &sortable_fields) => {
-                let (valid_fields, hidden_fields) =
-                    ctx.index.remove_hidden_fields(ctx.txn, sortable_fields)?;
-
                 return Err(UserError::InvalidSortableAttribute {
                     field: field.to_string(),
-                    valid_fields,
-                    hidden_fields,
-                })?;
+                    valid_fields: sortable_fields.into_iter().collect(),
+                })?
             }
             Member::Geo(_) if !sortable_fields.contains("_geo") => {
-                let (valid_fields, hidden_fields) =
-                    ctx.index.remove_hidden_fields(ctx.txn, sortable_fields)?;
-
                 return Err(UserError::InvalidSortableAttribute {
                     field: "_geo".to_string(),
-                    valid_fields,
-                    hidden_fields,
-                })?;
+                    valid_fields: sortable_fields.into_iter().collect(),
+                })?
             }
             _ => (),
         }

milli/src/search/new/tests/integration.rs

@@ -2,7 +2,7 @@ use std::io::Cursor;
 
 use big_s::S;
 use heed::EnvOpenOptions;
-use maplit::{btreemap, hashset};
+use maplit::{hashmap, hashset};
 
 use crate::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use crate::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
@@ -33,7 +33,7 @@ pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
         S("tag"),
         S("asc_desc_rank"),
     });
-    builder.set_synonyms(btreemap! {
+    builder.set_synonyms(hashmap! {
         S("hello") => vec![S("good morning")],
         S("world") => vec![S("earth")],
         S("america") => vec![S("the united states")],

milli/src/search/new/tests/proximity.rs

@@ -15,7 +15,7 @@ they store fewer sprximities than the regular word sprximity DB.
 
 */
 
-use std::collections::BTreeMap;
+use std::collections::HashMap;
 
 use crate::index::tests::TempIndex;
 use crate::search::new::tests::collect_field_values;
@@ -336,7 +336,7 @@ fn test_proximity_split_word() {
 
     index
         .update_settings(|s| {
-            let mut syns = BTreeMap::new();
+            let mut syns = HashMap::new();
             syns.insert("xyz".to_owned(), vec!["sun flower".to_owned()]);
             s.set_synonyms(syns);
         })

milli/src/search/new/tests/typo.rs

@@ -18,7 +18,7 @@ if `words` doesn't exist before it.
 14. Synonyms cost nothing according to the typo ranking rule
 */
 
-use std::collections::BTreeMap;
+use std::collections::HashMap;
 
 use crate::index::tests::TempIndex;
 use crate::search::new::tests::collect_field_values;
@@ -591,7 +591,7 @@ fn test_typo_synonyms() {
         .update_settings(|s| {
             s.set_criteria(vec![Criterion::Typo]);
 
-            let mut synonyms = BTreeMap::new();
+            let mut synonyms = HashMap::new();
             synonyms.insert("lackadaisical".to_owned(), vec!["lazy".to_owned()]);
             synonyms.insert("fast brownish".to_owned(), vec!["quick brown".to_owned()]);
 

milli/src/update/facet/bulk.rs

@@ -1,6 +1,5 @@
 use std::borrow::Cow;
 use std::fs::File;
-use std::io::BufReader;
 
 use grenad::CompressionType;
 use heed::types::ByteSlice;
@@ -31,7 +30,7 @@ pub struct FacetsUpdateBulk<'i> {
     facet_type: FacetType,
     field_ids: Vec<FieldId>,
     // None if level 0 does not need to be updated
-    new_data: Option<grenad::Reader<BufReader<File>>>,
+    new_data: Option<grenad::Reader<File>>,
 }
 
 impl<'i> FacetsUpdateBulk<'i> {
@@ -39,7 +38,7 @@ impl<'i> FacetsUpdateBulk<'i> {
         index: &'i Index,
         field_ids: Vec<FieldId>,
         facet_type: FacetType,
-        new_data: grenad::Reader<BufReader<File>>,
+        new_data: grenad::Reader<File>,
         group_size: u8,
         min_level_size: u8,
     ) -> FacetsUpdateBulk<'i> {
@@ -188,7 +187,7 @@ impl<R: std::io::Read + std::io::Seek> FacetsUpdateBulkInner<R> {
         &self,
         field_id: FieldId,
         txn: &RoTxn,
-    ) -> Result<(Vec<grenad::Reader<BufReader<File>>>, RoaringBitmap)> {
+    ) -> Result<(Vec<grenad::Reader<File>>, RoaringBitmap)> {
         let mut all_docids = RoaringBitmap::new();
         let subwriters = self.compute_higher_levels(txn, field_id, 32, &mut |bitmaps, _| {
             for bitmap in bitmaps {
@@ -260,7 +259,7 @@ impl<R: std::io::Read + std::io::Seek> FacetsUpdateBulkInner<R> {
         field_id: u16,
         level: u8,
         handle_group: &mut dyn FnMut(&[RoaringBitmap], &'t [u8]) -> Result<()>,
-    ) -> Result<Vec<grenad::Reader<BufReader<File>>>> {
+    ) -> Result<Vec<grenad::Reader<File>>> {
         if level == 0 {
             self.read_level_0(rtxn, field_id, handle_group)?;
             // Level 0 is already in the database

milli/src/update/facet/incremental.rs

@@ -1,6 +1,5 @@
 use std::collections::HashMap;
 use std::fs::File;
-use std::io::BufReader;
 
 use heed::types::{ByteSlice, DecodeIgnore};
 use heed::{BytesDecode, Error, RoTxn, RwTxn};
@@ -35,14 +34,14 @@ pub struct FacetsUpdateIncremental<'i> {
     index: &'i Index,
     inner: FacetsUpdateIncrementalInner,
     facet_type: FacetType,
-    new_data: grenad::Reader<BufReader<File>>,
+    new_data: grenad::Reader<File>,
 }
 
 impl<'i> FacetsUpdateIncremental<'i> {
     pub fn new(
         index: &'i Index,
         facet_type: FacetType,
-        new_data: grenad::Reader<BufReader<File>>,
+        new_data: grenad::Reader<File>,
         group_size: u8,
         min_level_size: u8,
         max_group_size: u8,

milli/src/update/facet/mod.rs

@@ -78,7 +78,6 @@ pub const FACET_MIN_LEVEL_SIZE: u8 = 5;
 
 use std::collections::BTreeSet;
 use std::fs::File;
-use std::io::BufReader;
 use std::iter::FromIterator;
 
 use charabia::normalizer::{Normalize, NormalizerOption};
@@ -95,7 +94,7 @@ use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValu
 use crate::heed_codec::ByteSliceRefCodec;
 use crate::update::index_documents::create_sorter;
 use crate::update::merge_btreeset_string;
-use crate::{BEU16StrCodec, Index, Result, BEU16, MAX_FACET_VALUE_LENGTH};
+use crate::{BEU16StrCodec, Index, Result, BEU16};
 
 pub mod bulk;
 pub mod delete;
@@ -109,17 +108,13 @@ pub struct FacetsUpdate<'i> {
     index: &'i Index,
     database: heed::Database<FacetGroupKeyCodec<ByteSliceRefCodec>, FacetGroupValueCodec>,
     facet_type: FacetType,
-    new_data: grenad::Reader<BufReader<File>>,
+    new_data: grenad::Reader<File>,
     group_size: u8,
     max_group_size: u8,
     min_level_size: u8,
 }
 impl<'i> FacetsUpdate<'i> {
-    pub fn new(
-        index: &'i Index,
-        facet_type: FacetType,
-        new_data: grenad::Reader<BufReader<File>>,
-    ) -> Self {
+    pub fn new(index: &'i Index, facet_type: FacetType, new_data: grenad::Reader<File>) -> Self {
         let database = match facet_type {
             FacetType::String => index
                 .facet_id_string_docids
@@ -196,16 +191,7 @@ impl<'i> FacetsUpdate<'i> {
         for result in database.iter(wtxn)? {
             let (facet_group_key, ()) = result?;
             if let FacetGroupKey { field_id, level: 0, left_bound } = facet_group_key {
-                let mut normalized_facet = left_bound.normalize(&options);
-                let normalized_truncated_facet: String;
-                if normalized_facet.len() > MAX_FACET_VALUE_LENGTH {
-                    normalized_truncated_facet = normalized_facet
-                        .char_indices()
-                        .take_while(|(idx, _)| *idx < MAX_FACET_VALUE_LENGTH)
-                        .map(|(_, c)| c)
-                        .collect();
-                    normalized_facet = normalized_truncated_facet.into();
-                }
+                let normalized_facet = left_bound.normalize(&options);
                 let set = BTreeSet::from_iter(std::iter::once(left_bound));
                 let key = (field_id, normalized_facet.as_ref());
                 let key = BEU16StrCodec::bytes_encode(&key).ok_or(heed::Error::Encoding)?;

milli/src/update/index_documents/enrich.rs

@@ -1,4 +1,4 @@
-use std::io::{BufWriter, Read, Seek};
+use std::io::{Read, Seek};
 use std::result::Result as StdResult;
 use std::{fmt, iter};
 
@@ -35,7 +35,7 @@ pub fn enrich_documents_batch<R: Read + Seek>(
 
     let (mut cursor, mut documents_batch_index) = reader.into_cursor_and_fields_index();
 
-    let mut external_ids = tempfile::tempfile().map(BufWriter::new).map(grenad::Writer::new)?;
+    let mut external_ids = tempfile::tempfile().map(grenad::Writer::new)?;
     let mut uuid_buffer = [0; uuid::fmt::Hyphenated::LENGTH];
 
     // The primary key *field id* that has already been set for this index or the one

milli/src/update/index_documents/extract/extract_docid_word_positions.rs

@@ -1,7 +1,6 @@
 use std::collections::{HashMap, HashSet};
 use std::convert::TryInto;
 use std::fs::File;
-use std::io::BufReader;
 use std::{io, mem, str};
 
 use charabia::{Language, Script, SeparatorKind, Token, TokenKind, Tokenizer, TokenizerBuilder};
@@ -29,10 +28,8 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     searchable_fields: &Option<HashSet<FieldId>>,
     stop_words: Option<&fst::Set<&[u8]>>,
-    allowed_separators: Option<&[&str]>,
-    dictionary: Option<&[&str]>,
     max_positions_per_attributes: Option<u32>,
-) -> Result<(RoaringBitmap, grenad::Reader<BufReader<File>>, ScriptLanguageDocidsMap)> {
+) -> Result<(RoaringBitmap, grenad::Reader<File>, ScriptLanguageDocidsMap)> {
     puffin::profile_function!();
 
     let max_positions_per_attributes = max_positions_per_attributes
@@ -55,12 +52,6 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
     if let Some(stop_words) = stop_words {
         tokenizer_builder.stop_words(stop_words);
     }
-    if let Some(dictionary) = dictionary {
-        tokenizer_builder.words_dict(dictionary);
-    }
-    if let Some(separators) = allowed_separators {
-        tokenizer_builder.separators(separators);
-    }
     let tokenizer = tokenizer_builder.build();
 
     let mut cursor = obkv_documents.into_cursor()?;
@@ -227,9 +218,9 @@ fn process_tokens<'a>(
 ) -> impl Iterator<Item = (usize, Token<'a>)> {
     tokens
         .skip_while(|token| token.is_separator())
-        .scan((0, None), |(offset, prev_kind), mut token| {
+        .scan((0, None), |(offset, prev_kind), token| {
             match token.kind {
-                TokenKind::Word | TokenKind::StopWord if !token.lemma().is_empty() => {
+                TokenKind::Word | TokenKind::StopWord | TokenKind::Unknown => {
                     *offset += match *prev_kind {
                         Some(TokenKind::Separator(SeparatorKind::Hard)) => 8,
                         Some(_) => 1,
@@ -245,7 +236,7 @@ fn process_tokens<'a>(
                 {
                     *prev_kind = Some(token.kind);
                 }
-                _ => token.kind = TokenKind::Unknown,
+                _ => (),
             }
             Some((*offset, token))
         })

milli/src/update/index_documents/extract/extract_facet_number_docids.rs

@@ -1,5 +1,5 @@
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 
 use heed::{BytesDecode, BytesEncode};
 
@@ -19,7 +19,7 @@ use crate::Result;
 pub fn extract_facet_number_docids<R: io::Read + io::Seek>(
     docid_fid_facet_number: grenad::Reader<R>,
     indexer: GrenadParameters,
-) -> Result<grenad::Reader<BufReader<File>>> {
+) -> Result<grenad::Reader<File>> {
     puffin::profile_function!();
 
     let max_memory = indexer.max_memory_by_thread();

milli/src/update/index_documents/extract/extract_facet_string_docids.rs

@@ -1,5 +1,5 @@
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 
 use heed::BytesEncode;
 
@@ -17,7 +17,7 @@ use crate::{FieldId, Result, MAX_FACET_VALUE_LENGTH};
 pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
     docid_fid_facet_string: grenad::Reader<R>,
     indexer: GrenadParameters,
-) -> Result<grenad::Reader<BufReader<File>>> {
+) -> Result<grenad::Reader<File>> {
     puffin::profile_function!();
 
     let max_memory = indexer.max_memory_by_thread();
@@ -46,7 +46,7 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
         if normalised_value.len() > MAX_FACET_VALUE_LENGTH {
             normalised_truncated_value = normalised_value
                 .char_indices()
-                .take_while(|(idx, _)| *idx < MAX_FACET_VALUE_LENGTH)
+                .take_while(|(idx, _)| idx + 4 < MAX_FACET_VALUE_LENGTH)
                 .map(|(_, c)| c)
                 .collect();
             normalised_value = normalised_truncated_value.as_str();

milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs

@@ -1,7 +1,7 @@
 use std::collections::{BTreeMap, HashSet};
 use std::convert::TryInto;
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 use std::mem::size_of;
 
 use heed::zerocopy::AsBytes;
@@ -17,24 +17,22 @@ use crate::{CboRoaringBitmapCodec, DocumentId, FieldId, Result, BEU32, MAX_FACET
 
 /// The extracted facet values stored in grenad files by type.
 pub struct ExtractedFacetValues {
-    pub docid_fid_facet_numbers_chunk: grenad::Reader<BufReader<File>>,
-    pub docid_fid_facet_strings_chunk: grenad::Reader<BufReader<File>>,
-    pub fid_facet_is_null_docids_chunk: grenad::Reader<BufReader<File>>,
-    pub fid_facet_is_empty_docids_chunk: grenad::Reader<BufReader<File>>,
-    pub fid_facet_exists_docids_chunk: grenad::Reader<BufReader<File>>,
+    pub docid_fid_facet_numbers_chunk: grenad::Reader<File>,
+    pub docid_fid_facet_strings_chunk: grenad::Reader<File>,
+    pub fid_facet_is_null_docids_chunk: grenad::Reader<File>,
+    pub fid_facet_is_empty_docids_chunk: grenad::Reader<File>,
+    pub fid_facet_exists_docids_chunk: grenad::Reader<File>,
 }
 
 /// Extracts the facet values of each faceted field of each document.
 ///
 /// Returns the generated grenad reader containing the docid the fid and the orginal value as key
 /// and the normalized value as value extracted from the given chunk of documents.
-/// We need the fid of the geofields to correctly parse them as numbers if they were sent as strings initially.
 #[logging_timer::time]
 pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
     obkv_documents: grenad::Reader<R>,
     indexer: GrenadParameters,
     faceted_fields: &HashSet<FieldId>,
-    geo_fields_ids: Option<(FieldId, FieldId)>,
 ) -> Result<ExtractedFacetValues> {
     puffin::profile_function!();
 
@@ -86,10 +84,7 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
 
                 let value = from_slice(field_bytes).map_err(InternalError::SerdeJson)?;
 
-                match extract_facet_values(
-                    &value,
-                    geo_fields_ids.map_or(false, |(lat, lng)| field_id == lat || field_id == lng),
-                ) {
+                match extract_facet_values(&value) {
                     FilterableValues::Null => {
                         facet_is_null_docids.entry(field_id).or_default().insert(document);
                     }
@@ -182,13 +177,12 @@ enum FilterableValues {
     Values { numbers: Vec<f64>, strings: Vec<(String, String)> },
 }
 
-fn extract_facet_values(value: &Value, geo_field: bool) -> FilterableValues {
+fn extract_facet_values(value: &Value) -> FilterableValues {
     fn inner_extract_facet_values(
         value: &Value,
         can_recurse: bool,
         output_numbers: &mut Vec<f64>,
         output_strings: &mut Vec<(String, String)>,
-        geo_field: bool,
     ) {
         match value {
             Value::Null => (),
@@ -199,30 +193,13 @@ fn extract_facet_values(value: &Value, geo_field: bool) -> FilterableValues {
                 }
             }
             Value::String(original) => {
-                // if we're working on a geofield it MUST be something we can parse or else there was an internal error
-                // in the enrich pipeline. But since the enrich pipeline worked, we want to avoid crashing at all costs.
-                if geo_field {
-                    if let Ok(float) = original.parse() {
-                        output_numbers.push(float);
-                    } else {
-                        log::warn!(
-                            "Internal error, could not parse a geofield that has been validated. Please open an issue."
-                        )
-                    }
-                }
                 let normalized = crate::normalize_facet(original);
                 output_strings.push((normalized, original.clone()));
             }
             Value::Array(values) => {
                 if can_recurse {
                     for value in values {
-                        inner_extract_facet_values(
-                            value,
-                            false,
-                            output_numbers,
-                            output_strings,
-                            geo_field,
-                        );
+                        inner_extract_facet_values(value, false, output_numbers, output_strings);
                     }
                 }
             }
@@ -238,7 +215,7 @@ fn extract_facet_values(value: &Value, geo_field: bool) -> FilterableValues {
         otherwise => {
             let mut numbers = Vec::new();
             let mut strings = Vec::new();
-            inner_extract_facet_values(otherwise, true, &mut numbers, &mut strings, geo_field);
+            inner_extract_facet_values(otherwise, true, &mut numbers, &mut strings);
             FilterableValues::Values { numbers, strings }
         }
     }

milli/src/update/index_documents/extract/extract_fid_word_count_docids.rs

@@ -1,6 +1,6 @@
 use std::collections::HashMap;
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 
 use grenad::Sorter;
 
@@ -21,7 +21,7 @@ use crate::{relative_from_absolute_position, DocumentId, FieldId, Result};
 pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
-) -> Result<grenad::Reader<BufReader<File>>> {
+) -> Result<grenad::Reader<File>> {
     puffin::profile_function!();
 
     let max_memory = indexer.max_memory_by_thread();

milli/src/update/index_documents/extract/extract_geo_points.rs

@@ -1,5 +1,5 @@
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 
 use concat_arrays::concat_arrays;
 use serde_json::Value;
@@ -18,7 +18,7 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     primary_key_id: FieldId,
     (lat_fid, lng_fid): (FieldId, FieldId),
-) -> Result<grenad::Reader<BufReader<File>>> {
+) -> Result<grenad::Reader<File>> {
     puffin::profile_function!();
 
     let mut writer = create_writer(

milli/src/update/index_documents/extract/extract_vector_points.rs

@@ -1,6 +1,6 @@
 use std::convert::TryFrom;
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 
 use bytemuck::cast_slice;
 use serde_json::{from_slice, Value};
@@ -18,7 +18,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     primary_key_id: FieldId,
     vectors_fid: FieldId,
-) -> Result<grenad::Reader<BufReader<File>>> {
+) -> Result<grenad::Reader<File>> {
     puffin::profile_function!();
 
     let mut writer = create_writer(
@@ -35,7 +35,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
         // lazily get it when needed
         let document_id = || -> Value {
             let document_id = obkv.get(primary_key_id).unwrap();
-            from_slice(document_id).unwrap()
+            serde_json::from_slice(document_id).unwrap()
         };
 
         // first we retrieve the _vectors field
@@ -52,14 +52,12 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                 }
             };
 
-            if let Some(vectors) = vectors {
-                for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
-                    let index = u16::try_from(i).unwrap();
-                    let mut key = docid_bytes.to_vec();
-                    key.extend_from_slice(&index.to_be_bytes());
-                    let bytes = cast_slice(&vector);
-                    writer.insert(key, bytes)?;
-                }
+            for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
+                let index = u16::try_from(i).unwrap();
+                let mut key = docid_bytes.to_vec();
+                key.extend_from_slice(&index.to_be_bytes());
+                let bytes = cast_slice(&vector);
+                writer.insert(key, bytes)?;
             }
         }
         // else => the `_vectors` object was `null`, there is nothing to do

milli/src/update/index_documents/extract/extract_word_docids.rs

@@ -1,6 +1,6 @@
 use std::collections::HashSet;
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 use std::iter::FromIterator;
 
 use roaring::RoaringBitmap;
@@ -26,7 +26,7 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
     exact_attributes: &HashSet<FieldId>,
-) -> Result<(grenad::Reader<BufReader<File>>, grenad::Reader<BufReader<File>>)> {
+) -> Result<(grenad::Reader<File>, grenad::Reader<File>)> {
     puffin::profile_function!();
 
     let max_memory = indexer.max_memory_by_thread();

milli/src/update/index_documents/extract/extract_word_fid_docids.rs

@@ -1,5 +1,5 @@
 use std::fs::File;
-use std::io::{self, BufReader};
+use std::io;
 
 use super::helpers::{
     create_sorter, merge_cbo_roaring_bitmaps, read_u32_ne_bytes, sorter_into_reader,
@@ -14,7 +14,7 @@ use crate::{relative_from_absolute_position, DocumentId, Result};
 pub fn extract_word_fid_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
-) -> Result<grenad::Reader<BufReader<File>>> {
+) -> Result<grenad::Reader<File>> {
     puffin::profile_function!();
 
     let max_memory = indexer.max_memory_by_thread();