Change the error codes of the faceting settings

.dockerignore

@@ -2,3 +2,4 @@ target
 Dockerfile
 .dockerignore
 .gitignore
+**/.git

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

@@ -35,7 +35,7 @@ jobs:
     - name: Build deb package
       run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
     - name: Upload debian pkg to release
-      uses: svenstaro/upload-release-action@2.6.1
+      uses: svenstaro/upload-release-action@2.5.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/debian/meilisearch.deb

.github/workflows/publish-binaries.yml

@@ -54,7 +54,7 @@ jobs:
     # No need to upload binaries for dry run (cron)
     - name: Upload binaries to release
       if: github.event_name == 'release'
-      uses: svenstaro/upload-release-action@2.6.1
+      uses: svenstaro/upload-release-action@2.5.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/release/meilisearch
@@ -87,7 +87,7 @@ jobs:
     # No need to upload binaries for dry run (cron)
     - name: Upload binaries to release
       if: github.event_name == 'release'
-      uses: svenstaro/upload-release-action@2.6.1
+      uses: svenstaro/upload-release-action@2.5.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/release/${{ matrix.artifact_name }}
@@ -121,7 +121,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.6.1
+        uses: svenstaro/upload-release-action@2.5.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch
@@ -183,7 +183,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.6.1
+        uses: svenstaro/upload-release-action@2.5.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch

.github/workflows/publish-docker-images.yml

@@ -58,9 +58,13 @@ jobs:
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v2
+        with:
+          platforms: linux/amd64,linux/arm64
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
+        with:
+          platforms: linux/amd64,linux/arm64
 
       - name: Login to Docker Hub
         uses: docker/login-action@v2
@@ -88,10 +92,13 @@ jobs:
           push: true
           platforms: linux/amd64,linux/arm64
           tags: ${{ steps.meta.outputs.tags }}
+          builder: ${{ steps.buildx.outputs.name }}
           build-args: |
             COMMIT_SHA=${{ github.sha }}
             COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
             GIT_TAG=${{ github.ref_name }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
 
       # /!\ Don't touch this without checking with Cloud team
       - name: Send CI information to Cloud team

.github/workflows/sdks-tests.yml

@@ -3,11 +3,6 @@ name: SDKs tests
 
 on:
   workflow_dispatch:
-    inputs:
-      docker_image:
-        description: 'The Meilisearch Docker image used'
-        required: false
-        default: nightly
   schedule:
     - cron: "0 6 * * MON" # Every Monday at 6:00AM
 
@@ -16,28 +11,13 @@ env:
   MEILI_NO_ANALYTICS: 'true'
 
 jobs:
-  define-docker-image:
-    runs-on: ubuntu-latest
-    outputs:
-      docker-image: ${{ steps.define-image.outputs.docker-image }}
-    steps:
-      - uses: actions/checkout@v3
-      - name: Define the Docker image we need to use
-        id: define-image
-        run: |
-          event=${{ github.event.action }}
-          echo "docker-image=nightly" >> $GITHUB_OUTPUT
-          if [[ $event == 'workflow_dispatch' ]]; then
-            echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
-          fi
 
   meilisearch-js-tests:
-    needs: define-docker-image
     name: JS SDK tests
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -67,12 +47,11 @@ jobs:
         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:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -94,12 +73,11 @@ jobs:
         run: yarn build
 
   meilisearch-php-tests:
-    needs: define-docker-image
     name: PHP SDK tests
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -125,12 +103,11 @@ jobs:
           composer remove --dev guzzlehttp/guzzle http-interop/http-factory-guzzle
 
   meilisearch-python-tests:
-    needs: define-docker-image
     name: Python SDK tests
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -150,12 +127,11 @@ jobs:
         run: pipenv run pytest
 
   meilisearch-go-tests:
-    needs: define-docker-image
     name: Go SDK tests
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -163,7 +139,7 @@ jobs:
           - '7700:7700'
     steps:
       - name: Set up Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v3
         with:
           go-version: stable
       - uses: actions/checkout@v3
@@ -180,12 +156,11 @@ jobs:
         run: go test -v ./...
 
   meilisearch-ruby-tests:
-    needs: define-docker-image
     name: Ruby SDK tests
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -205,12 +180,11 @@ jobs:
         run: bundle exec rspec
 
   meilisearch-rust-tests:
-    needs: define-docker-image
     name: Rust SDK tests
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}

.github/workflows/test-suite.yml

@@ -43,7 +43,7 @@ jobs:
           toolchain: nightly
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.2.1
       - 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@v2.4.0
+        uses: Swatinem/rust-cache@v2.2.1
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -105,29 +105,6 @@ jobs:
           command: test
           args: --workspace --locked --release --all-features
 
-  test-disabled-tokenization:
-    name: Test disabled tokenization
-    runs-on: ubuntu-latest
-    container:
-      image: ubuntu:18.04
-    if: github.event_name == 'schedule'
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install needed dependencies
-        run: |
-          apt-get update
-          apt-get install --assume-yes build-essential curl
-      - uses: actions-rs/toolchain@v1 
-        with: 
-          toolchain: stable 
-          override: true 
-      - name: Run cargo tree without default features and check lindera is not present
-        run: |
-          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
-                
   # We run tests in debug also, to make sure that the debug_assertions are hit
   test-debug:
     name: Run tests in debug
@@ -146,7 +123,7 @@ jobs:
           toolchain: stable
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.2.1
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -165,7 +142,7 @@ jobs:
           override: true
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.2.1
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -184,7 +161,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.2.1
       - 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.lock

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

Dockerfile

@@ -1,3 +1,4 @@
+# syntax=docker/dockerfile:1.4
 # Compile
 FROM    rust:alpine3.16 AS compiler
 
@@ -11,7 +12,7 @@ ARG     GIT_TAG
 ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
-COPY    . .
+COPY    --link . .
 RUN     set -eux; \
         apkArch="$(apk --print-arch)"; \
         if [ "$apkArch" = "aarch64" ]; then \
@@ -30,7 +31,7 @@ RUN     apk update --quiet \
 
 # add meilisearch to the `/bin` so you can run it from anywhere and it's easy
 # to find.
-COPY    --from=compiler /meilisearch/target/release/meilisearch /bin/meilisearch
+COPY    --from=compiler --link /meilisearch/target/release/meilisearch /bin/meilisearch
 # To stay compatible with the older version of the container (pre v0.27.0) we're
 # going to symlink the meilisearch binary in the path to `/meilisearch`
 RUN     ln -s /bin/meilisearch /meilisearch

assets/prometheus-basic-scraper.yml

@@ -1,19 +0,0 @@
-global:
-  scrape_interval:     15s # By default, scrape targets every 15 seconds.
-
-  # Attach these labels to any time series or alerts when communicating with
-  # external systems (federation, remote storage, Alertmanager).
-  external_labels:
-    monitor: 'codelab-monitor'
-
-# A scrape configuration containing exactly one endpoint to scrape:
-# Here it's Prometheus itself.
-scrape_configs:
-  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
-  - job_name: 'meilisearch'
-
-    # Override the global default and scrape targets from this job every 5 seconds.
-    scrape_interval: 5s
-
-    static_configs:
-      - targets: ['localhost:7700']

config.toml

@@ -1,131 +1,131 @@
 # This file shows the default configuration of Meilisearch.
 # All variables are defined here: https://www.meilisearch.com/docs/learn/configuration/instance_options#environment-variables
 
+db_path = "./data.ms"
 # Designates the location where database files will be created and retrieved.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#database-path
-db_path = "./data.ms"
 
+env = "development"
 # Configures the instance's environment. Value must be either `production` or `development`.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#environment
-env = "development"
 
-# The address on which the HTTP server will listen.
 http_addr = "localhost:7700"
+# The address on which the HTTP server will listen.
 
+# master_key = "YOUR_MASTER_KEY_VALUE"
 # Sets the instance's master key, automatically protecting all routes except GET /health.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#master-key
-# master_key = "YOUR_MASTER_KEY_VALUE"
 
+# no_analytics = true
 # Deactivates Meilisearch's built-in telemetry when provided.
 # 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.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#disable-analytics
-# no_analytics = true
 
+http_payload_size_limit = "100 MB"
 # Sets the maximum size of accepted payloads.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#payload-limit-size
-http_payload_size_limit = "100 MB"
 
+log_level = "INFO"
 # Defines how much detail should be present in Meilisearch's logs.
 # Meilisearch currently supports six log levels, listed in order of increasing verbosity:  `OFF`, `ERROR`, `WARN`, `INFO`, `DEBUG`, `TRACE`
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#log-level
-log_level = "INFO"
 
+# max_indexing_memory = "2 GiB"
 # Sets the maximum amount of RAM Meilisearch can use when indexing.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#max-indexing-memory
-# max_indexing_memory = "2 GiB"
 
+# max_indexing_threads = 4
 # Sets the maximum number of threads Meilisearch can use during indexing.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#max-indexing-threads
-# max_indexing_threads = 4
 
 #############
 ### DUMPS ###
 #############
 
+dump_dir = "dumps/"
 # Sets the directory where Meilisearch will create dump files.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#dump-directory
-dump_dir = "dumps/"
 
+# import_dump = "./path/to/my/file.dump"
 # Imports the dump file located at the specified path. Path must point to a .dump file.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#import-dump
-# import_dump = "./path/to/my/file.dump"
 
+ignore_missing_dump = false
 # Prevents Meilisearch from throwing an error when `import_dump` does not point to a valid dump file.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-missing-dump
-ignore_missing_dump = false
 
+ignore_dump_if_db_exists = false
 # Prevents a Meilisearch instance with an existing database from throwing an error when using `import_dump`.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-dump-if-db-exists
-ignore_dump_if_db_exists = false
 
 
 #################
 ### SNAPSHOTS ###
 #################
 
+schedule_snapshot = false
 # Enables scheduled snapshots when true, disable when false (the default).
 # If the value is given as an integer, then enables the scheduled snapshot with the passed value as the interval
 # between each snapshot, in seconds.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#schedule-snapshot-creation
-schedule_snapshot = false
 
+snapshot_dir = "snapshots/"
 # Sets the directory where Meilisearch will store snapshots.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#snapshot-destination
-snapshot_dir = "snapshots/"
 
+# import_snapshot = "./path/to/my/snapshot"
 # Launches Meilisearch after importing a previously-generated snapshot at the given filepath.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#import-snapshot
-# import_snapshot = "./path/to/my/snapshot"
 
+ignore_missing_snapshot = false
 # Prevents a Meilisearch instance from throwing an error when `import_snapshot` does not point to a valid snapshot file.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-missing-snapshot
-ignore_missing_snapshot = false
 
+ignore_snapshot_if_db_exists = false
 # Prevents a Meilisearch instance with an existing database from throwing an error when using `import_snapshot`.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-snapshot-if-db-exists
-ignore_snapshot_if_db_exists = false
 
 
 ###########
 ### SSL ###
 ###########
 
+# ssl_auth_path = "./path/to/root"
 # Enables client authentication in the specified path.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-authentication-path
-# ssl_auth_path = "./path/to/root"
 
+# ssl_cert_path = "./path/to/certfile"
 # Sets the server's SSL certificates.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-certificates-path
-# ssl_cert_path = "./path/to/certfile"
 
+# ssl_key_path = "./path/to/private-key"
 # Sets the server's SSL key files.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-key-path
-# ssl_key_path = "./path/to/private-key"
 
+# ssl_ocsp_path = "./path/to/ocsp-file"
 # Sets the server's OCSP file.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-ocsp-path
-# ssl_ocsp_path = "./path/to/ocsp-file"
 
+ssl_require_auth = false
 # Makes SSL authentication mandatory.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-require-auth
-ssl_require_auth = false
 
+ssl_resumption = false
 # Activates SSL session resumption.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-resumption
-ssl_resumption = false
 
+ssl_tickets = false
 # Activates SSL tickets.
 # https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-tickets
-ssl_tickets = false
 
 #############################
 ### Experimental features ###
 #############################
 
+experimental_enable_metrics = false
 # Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
 # Enables the Prometheus metrics on the `GET /metrics` endpoint.
-experimental_enable_metrics = false
 
-# Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
 experimental_reduce_indexing_memory_usage = false
+# Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>

dump/src/reader/compat/v5_to_v6.rs

@@ -358,6 +358,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             faceting: match settings.faceting {
                 v5::Setting::Set(faceting) => v6::Setting::Set(v6::FacetingSettings {
                     max_values_per_facet: faceting.max_values_per_facet.into(),
+                    sort_facet_values_by: v6::Setting::NotSet,
                 }),
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,

index-scheduler/src/index_mapper/mod.rs

@@ -90,17 +90,8 @@ pub enum IndexStatus {
 pub struct IndexStats {
     /// Number of documents in the index.
     pub number_of_documents: u64,
-    /// Size taken up by the index' DB, in bytes.
-    ///
-    /// This includes the size taken by both the used and free pages of the DB, and as the free pages
-    /// are not returned to the disk after a deletion, this number is typically larger than
-    /// `used_database_size` that only includes the size of the used pages.
+    /// Size of the index' DB, in bytes.
     pub database_size: u64,
-    /// Size taken by the used pages of the index' DB, in bytes.
-    ///
-    /// As the DB backend does not return to the disk the pages that are not currently used by the DB,
-    /// this value is typically smaller than `database_size`.
-    pub used_database_size: u64,
     /// Association of every field name with the number of times it occurs in the documents.
     pub field_distribution: FieldDistribution,
     /// Creation date of the index.
@@ -116,10 +107,10 @@ impl IndexStats {
     ///
     /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
     pub fn new(index: &Index, rtxn: &RoTxn) -> Result<Self> {
+        let database_size = index.on_disk_size()?;
         Ok(IndexStats {
             number_of_documents: index.number_of_documents(rtxn)?,
-            database_size: index.on_disk_size()?,
-            used_database_size: index.used_size()?,
+            database_size,
             field_distribution: index.field_distribution(rtxn)?,
             created_at: index.created_at(rtxn)?,
             updated_at: index.updated_at(rtxn)?,

index-scheduler/src/lib.rs

@@ -31,7 +31,7 @@ mod uuid_codec;
 pub type Result<T> = std::result::Result<T, Error>;
 pub type TaskId = u32;
 
-use std::collections::{BTreeMap, HashMap};
+use std::collections::HashMap;
 use std::ops::{Bound, RangeBounds};
 use std::path::{Path, PathBuf};
 use std::sync::atomic::AtomicBool;
@@ -573,16 +573,10 @@ impl IndexScheduler {
         &self.index_mapper.indexer_config
     }
 
-    /// Return the real database size (i.e.: The size **with** the free pages)
     pub fn size(&self) -> Result<u64> {
         Ok(self.env.real_disk_size()?)
     }
 
-    /// Return the used database size (i.e.: The size **without** the free pages)
-    pub fn used_size(&self) -> Result<u64> {
-        Ok(self.env.non_free_pages_size()?)
-    }
-
     /// Return the index corresponding to the name.
     ///
     /// * If the index wasn't opened before, the index will be opened.
@@ -762,38 +756,6 @@ impl IndexScheduler {
         Ok(tasks)
     }
 
-    /// The returned structure contains:
-    /// 1. The name of the property being observed can be `statuses`, `types`, or `indexes`.
-    /// 2. The name of the specific data related to the property can be `enqueued` for the `statuses`, `settingsUpdate` for the `types`, or the name of the index for the `indexes`, for example.
-    /// 3. The number of times the properties appeared.
-    pub fn get_stats(&self) -> Result<BTreeMap<String, BTreeMap<String, u64>>> {
-        let rtxn = self.read_txn()?;
-
-        let mut res = BTreeMap::new();
-
-        res.insert(
-            "statuses".to_string(),
-            enum_iterator::all::<Status>()
-                .map(|s| Ok((s.to_string(), self.get_status(&rtxn, s)?.len())))
-                .collect::<Result<BTreeMap<String, u64>>>()?,
-        );
-        res.insert(
-            "types".to_string(),
-            enum_iterator::all::<Kind>()
-                .map(|s| Ok((s.to_string(), self.get_kind(&rtxn, s)?.len())))
-                .collect::<Result<BTreeMap<String, u64>>>()?,
-        );
-        res.insert(
-            "indexes".to_string(),
-            self.index_tasks
-                .iter(&rtxn)?
-                .map(|res| Ok(res.map(|(name, bitmap)| (name.to_string(), bitmap.len()))?))
-                .collect::<Result<BTreeMap<String, u64>>>()?,
-        );
-
-        Ok(res)
-    }
-
     /// Return true iff there is at least one task associated with this index
     /// that is processing.
     pub fn is_index_processing(&self, index: &str) -> Result<bool> {

index-scheduler/src/utils.rs

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

meilisearch-auth/src/lib.rs

@@ -45,11 +45,6 @@ impl AuthController {
         self.store.size()
     }
 
-    /// Return the used size of the `AuthController` database in bytes.
-    pub fn used_size(&self) -> Result<u64> {
-        self.store.used_size()
-    }
-
     pub fn create_key(&self, create_key: CreateApiKey) -> Result<Key> {
         match self.store.get_api_key(create_key.uid)? {
             Some(_) => Err(AuthControllerError::ApiKeyAlreadyExists(create_key.uid.to_string())),

meilisearch-auth/src/store.rs

@@ -75,11 +75,6 @@ impl HeedAuthStore {
         Ok(self.env.real_disk_size()?)
     }
 
-    /// Return the number of bytes actually used in the database
-    pub fn used_size(&self) -> Result<u64> {
-        Ok(self.env.non_free_pages_size()?)
-    }
-
     pub fn set_drop_on_close(&mut self, v: bool) {
         self.should_close_on_drop = v;
     }

meilisearch-types/src/error.rs

@@ -175,121 +175,122 @@ macro_rules! make_error_codes {
 
 // An exhaustive list of all the error codes used by meilisearch.
 make_error_codes! {
-ApiKeyAlreadyExists                   , InvalidRequest       , CONFLICT ;
-ApiKeyNotFound                        , InvalidRequest       , NOT_FOUND ;
-BadParameter                          , InvalidRequest       , BAD_REQUEST;
-BadRequest                            , InvalidRequest       , BAD_REQUEST;
-DatabaseSizeLimitReached              , Internal             , INTERNAL_SERVER_ERROR;
-DocumentNotFound                      , InvalidRequest       , NOT_FOUND;
-DumpAlreadyProcessing                 , InvalidRequest       , CONFLICT;
-DumpNotFound                          , InvalidRequest       , NOT_FOUND;
-DumpProcessFailed                     , Internal             , INTERNAL_SERVER_ERROR;
-DuplicateIndexFound                   , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyActions                , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyCreatedAt              , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyExpiresAt              , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyIndexes                , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyKey                    , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyUid                    , InvalidRequest       , BAD_REQUEST;
-ImmutableApiKeyUpdatedAt              , InvalidRequest       , BAD_REQUEST;
-ImmutableIndexCreatedAt               , InvalidRequest       , BAD_REQUEST;
-ImmutableIndexUid                     , InvalidRequest       , BAD_REQUEST;
-ImmutableIndexUpdatedAt               , InvalidRequest       , BAD_REQUEST;
-IndexAlreadyExists                    , InvalidRequest       , CONFLICT ;
-IndexCreationFailed                   , Internal             , INTERNAL_SERVER_ERROR;
-IndexNotFound                         , InvalidRequest       , NOT_FOUND;
-IndexPrimaryKeyAlreadyExists          , InvalidRequest       , BAD_REQUEST ;
-IndexPrimaryKeyMultipleCandidatesFound, InvalidRequest       , BAD_REQUEST;
-IndexPrimaryKeyNoCandidateFound       , InvalidRequest       , BAD_REQUEST ;
-Internal                              , Internal             , INTERNAL_SERVER_ERROR ;
-InvalidApiKey                         , Auth                 , FORBIDDEN ;
-InvalidApiKeyActions                  , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyDescription              , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyExpiresAt                , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyIndexes                  , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyLimit                    , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyName                     , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyOffset                   , InvalidRequest       , BAD_REQUEST ;
-InvalidApiKeyUid                      , InvalidRequest       , BAD_REQUEST ;
-InvalidContentType                    , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
-InvalidDocumentCsvDelimiter           , InvalidRequest       , BAD_REQUEST ;
-InvalidDocumentFields                 , InvalidRequest       , BAD_REQUEST ;
-MissingDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
-InvalidDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
-InvalidDocumentGeoField               , InvalidRequest       , BAD_REQUEST ;
-InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
-InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
-InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
-InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
-InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
-InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
-InvalidIndexUid                       , InvalidRequest       , BAD_REQUEST ;
-InvalidRestrictSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchAttributesToCrop         , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchAttributesToHighlight    , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchHighlightPreTag          , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchHitsPerPage              , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchLimit                    , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchMatchingStrategy         , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchOffset                   , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsFilterableAttributes   , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsPagination             , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsRankingRules           , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsSortableAttributes     , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsStopWords              , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsSynonyms               , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsTypoTolerance          , InvalidRequest       , BAD_REQUEST ;
-InvalidState                          , Internal             , INTERNAL_SERVER_ERROR ;
-InvalidStoreFile                      , Internal             , INTERNAL_SERVER_ERROR ;
-InvalidSwapDuplicateIndexFound        , InvalidRequest       , BAD_REQUEST ;
-InvalidSwapIndexes                    , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskAfterEnqueuedAt            , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskAfterFinishedAt            , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskAfterStartedAt             , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskBeforeEnqueuedAt           , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskBeforeFinishedAt           , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskBeforeStartedAt            , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskCanceledBy                 , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskFrom                       , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskLimit                      , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskStatuses                   , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskTypes                      , InvalidRequest       , BAD_REQUEST ;
-InvalidTaskUids                       , InvalidRequest       , BAD_REQUEST  ;
-IoError                               , System               , UNPROCESSABLE_ENTITY;
-MalformedPayload                      , InvalidRequest       , BAD_REQUEST ;
-MaxFieldsLimitExceeded                , InvalidRequest       , BAD_REQUEST ;
-MissingApiKeyActions                  , InvalidRequest       , BAD_REQUEST ;
-MissingApiKeyExpiresAt                , InvalidRequest       , BAD_REQUEST ;
-MissingApiKeyIndexes                  , InvalidRequest       , BAD_REQUEST ;
-MissingAuthorizationHeader            , Auth                 , UNAUTHORIZED ;
-MissingContentType                    , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
-MissingDocumentId                     , InvalidRequest       , BAD_REQUEST ;
-MissingIndexUid                       , InvalidRequest       , BAD_REQUEST ;
-MissingMasterKey                      , Auth                 , UNAUTHORIZED ;
-MissingPayload                        , InvalidRequest       , BAD_REQUEST ;
-MissingSwapIndexes                    , InvalidRequest       , BAD_REQUEST ;
-MissingTaskFilters                    , InvalidRequest       , BAD_REQUEST ;
-NoSpaceLeftOnDevice                   , System               , UNPROCESSABLE_ENTITY;
-PayloadTooLarge                       , InvalidRequest       , PAYLOAD_TOO_LARGE ;
-TaskNotFound                          , InvalidRequest       , NOT_FOUND ;
-TooManyOpenFiles                      , System               , UNPROCESSABLE_ENTITY ;
-UnretrievableDocument                 , Internal             , BAD_REQUEST ;
-UnretrievableErrorCode                , InvalidRequest       , BAD_REQUEST ;
-UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE
+ApiKeyAlreadyExists                         , InvalidRequest       , CONFLICT ;
+ApiKeyNotFound                              , InvalidRequest       , NOT_FOUND ;
+BadParameter                                , InvalidRequest       , BAD_REQUEST;
+BadRequest                                  , InvalidRequest       , BAD_REQUEST;
+DatabaseSizeLimitReached                    , Internal             , INTERNAL_SERVER_ERROR;
+DocumentNotFound                            , InvalidRequest       , NOT_FOUND;
+DumpAlreadyProcessing                       , InvalidRequest       , CONFLICT;
+DumpNotFound                                , InvalidRequest       , NOT_FOUND;
+DumpProcessFailed                           , Internal             , INTERNAL_SERVER_ERROR;
+DuplicateIndexFound                         , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyActions                      , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyCreatedAt                    , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyExpiresAt                    , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyIndexes                      , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyKey                          , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyUid                          , InvalidRequest       , BAD_REQUEST;
+ImmutableApiKeyUpdatedAt                    , InvalidRequest       , BAD_REQUEST;
+ImmutableIndexCreatedAt                     , InvalidRequest       , BAD_REQUEST;
+ImmutableIndexUid                           , InvalidRequest       , BAD_REQUEST;
+ImmutableIndexUpdatedAt                     , InvalidRequest       , BAD_REQUEST;
+IndexAlreadyExists                          , InvalidRequest       , CONFLICT ;
+IndexCreationFailed                         , Internal             , INTERNAL_SERVER_ERROR;
+IndexNotFound                               , InvalidRequest       , NOT_FOUND;
+IndexPrimaryKeyAlreadyExists                , InvalidRequest       , BAD_REQUEST ;
+IndexPrimaryKeyMultipleCandidatesFound      , InvalidRequest       , BAD_REQUEST;
+IndexPrimaryKeyNoCandidateFound             , InvalidRequest       , BAD_REQUEST ;
+Internal                                    , Internal             , INTERNAL_SERVER_ERROR ;
+InvalidApiKey                               , Auth                 , FORBIDDEN ;
+InvalidApiKeyActions                        , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyDescription                    , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyExpiresAt                      , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyIndexes                        , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyLimit                          , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyName                           , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyOffset                         , InvalidRequest       , BAD_REQUEST ;
+InvalidApiKeyUid                            , InvalidRequest       , BAD_REQUEST ;
+InvalidContentType                          , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
+InvalidDocumentCsvDelimiter                 , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentFields                       , InvalidRequest       , BAD_REQUEST ;
+MissingDocumentFilter                       , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentFilter                       , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentGeoField                     , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentId                           , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentLimit                        , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentOffset                       , InvalidRequest       , BAD_REQUEST ;
+InvalidIndexLimit                           , InvalidRequest       , BAD_REQUEST ;
+InvalidIndexOffset                          , InvalidRequest       , BAD_REQUEST ;
+InvalidIndexPrimaryKey                      , InvalidRequest       , BAD_REQUEST ;
+InvalidIndexUid                             , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchAttributesToCrop               , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchAttributesToHighlight          , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchAttributesToRetrieve           , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchCropLength                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchCropMarker                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchFacets                         , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchFilter                         , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchHighlightPostTag               , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchHighlightPreTag                , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchHitsPerPage                    , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchLimit                          , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchMatchingStrategy               , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchOffset                         , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchPage                           , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchQ                              , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchShowMatchesPosition            , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchSort                           , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsDisplayedAttributes          , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsDistinctAttribute            , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsFilterableAttributes         , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsPagination                   , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsRankingRules                 , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsSearchableAttributes         , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsSortableAttributes           , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsStopWords                    , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsSynonyms                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsTypoTolerance                , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsFaceting                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsFacetingMaxValuesPerFacet    , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsFacetingSortFacetValuesBy    , InvalidRequest       , BAD_REQUEST ;
+InvalidState                                , Internal             , INTERNAL_SERVER_ERROR ;
+InvalidStoreFile                            , Internal             , INTERNAL_SERVER_ERROR ;
+InvalidSwapDuplicateIndexFound              , InvalidRequest       , BAD_REQUEST ;
+InvalidSwapIndexes                          , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskAfterEnqueuedAt                  , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskAfterFinishedAt                  , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskAfterStartedAt                   , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskBeforeEnqueuedAt                 , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskBeforeFinishedAt                 , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskBeforeStartedAt                  , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskCanceledBy                       , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskFrom                             , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskLimit                            , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskStatuses                         , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskTypes                            , InvalidRequest       , BAD_REQUEST ;
+InvalidTaskUids                             , InvalidRequest       , BAD_REQUEST  ;
+IoError                                     , System               , UNPROCESSABLE_ENTITY;
+MalformedPayload                            , InvalidRequest       , BAD_REQUEST ;
+MaxFieldsLimitExceeded                      , InvalidRequest       , BAD_REQUEST ;
+MissingApiKeyActions                        , InvalidRequest       , BAD_REQUEST ;
+MissingApiKeyExpiresAt                      , InvalidRequest       , BAD_REQUEST ;
+MissingApiKeyIndexes                        , InvalidRequest       , BAD_REQUEST ;
+MissingAuthorizationHeader                  , Auth                 , UNAUTHORIZED ;
+MissingContentType                          , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
+MissingDocumentId                           , InvalidRequest       , BAD_REQUEST ;
+MissingIndexUid                             , InvalidRequest       , BAD_REQUEST ;
+MissingMasterKey                            , Auth                 , UNAUTHORIZED ;
+MissingPayload                              , InvalidRequest       , BAD_REQUEST ;
+MissingSwapIndexes                          , InvalidRequest       , BAD_REQUEST ;
+MissingTaskFilters                          , InvalidRequest       , BAD_REQUEST ;
+NoSpaceLeftOnDevice                         , System               , UNPROCESSABLE_ENTITY;
+PayloadTooLarge                             , InvalidRequest       , PAYLOAD_TOO_LARGE ;
+TaskNotFound                                , InvalidRequest       , NOT_FOUND ;
+TooManyOpenFiles                            , System               , UNPROCESSABLE_ENTITY ;
+UnretrievableDocument                       , Internal             , BAD_REQUEST ;
+UnretrievableErrorCode                      , InvalidRequest       , BAD_REQUEST ;
+UnsupportedMediaType                        , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE
 }
 
 impl ErrorCode for JoinError {

meilisearch-types/src/facet_values_sort.rs

@@ -0,0 +1,33 @@
+use deserr::Deserr;
+use milli::OrderBy;
+use serde::{Deserialize, Serialize};
+
+#[derive(Debug, Default, Copy, Clone, PartialEq, Eq, Serialize, Deserialize, Deserr)]
+#[serde(rename_all = "camelCase")]
+#[deserr(rename_all = camelCase)]
+pub enum FacetValuesSort {
+    /// Facet values are sorted in alphabetical order, ascending from A to Z.
+    #[default]
+    Alpha,
+    /// Facet values are sorted by decreasing count.
+    /// The count is the number of records containing this facet value in the results of the query.
+    Count,
+}
+
+impl From<FacetValuesSort> for OrderBy {
+    fn from(val: FacetValuesSort) -> Self {
+        match val {
+            FacetValuesSort::Alpha => OrderBy::Lexicographic,
+            FacetValuesSort::Count => OrderBy::Count,
+        }
+    }
+}
+
+impl From<OrderBy> for FacetValuesSort {
+    fn from(val: OrderBy) -> Self {
+        match val {
+            OrderBy::Lexicographic => FacetValuesSort::Alpha,
+            OrderBy::Count => FacetValuesSort::Count,
+        }
+    }
+}

meilisearch-types/src/lib.rs

@@ -2,6 +2,7 @@ pub mod compression;
 pub mod deserr;
 pub mod document_formats;
 pub mod error;
+pub mod facet_values_sort;
 pub mod index_uid;
 pub mod index_uid_pattern;
 pub mod keys;

meilisearch-types/src/settings.rs

@@ -14,6 +14,7 @@ use serde::{Deserialize, Serialize, Serializer};
 
 use crate::deserr::DeserrJsonError;
 use crate::error::deserr_codes::*;
+use crate::facet_values_sort::FacetValuesSort;
 
 /// The maximimum number of results that the engine
 /// will be able to return in one search call.
@@ -97,11 +98,14 @@ pub struct TypoSettings {
 
 #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq, Deserr)]
 #[serde(deny_unknown_fields, rename_all = "camelCase")]
-#[deserr(rename_all = camelCase, deny_unknown_fields)]
+#[deserr(deny_unknown_fields, rename_all = camelCase, where_predicate = __Deserr_E: deserr::MergeWithError<DeserrJsonError<InvalidSettingsFaceting>> + deserr::MergeWithError<DeserrJsonError<InvalidSettingsFacetingMaxValuesPerFacet>> + deserr::MergeWithError<DeserrJsonError<InvalidSettingsFacetingSortFacetValuesBy>>)]
 pub struct FacetingSettings {
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default)]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsFacetingMaxValuesPerFacet>)]
     pub max_values_per_facet: Setting<usize>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsFacetingSortFacetValuesBy>)]
+    pub sort_facet_values_by: Setting<BTreeMap<String, FacetValuesSort>>,
 }
 
 #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq, Deserr)]
@@ -398,12 +402,21 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.faceting {
-        Setting::Set(ref value) => match value.max_values_per_facet {
-            Setting::Set(val) => builder.set_max_values_per_facet(val),
-            Setting::Reset => builder.reset_max_values_per_facet(),
-            Setting::NotSet => (),
-        },
+    match &settings.faceting {
+        Setting::Set(FacetingSettings { max_values_per_facet, sort_facet_values_by }) => {
+            match max_values_per_facet {
+                Setting::Set(val) => builder.set_max_values_per_facet(*val),
+                Setting::Reset => builder.reset_max_values_per_facet(),
+                Setting::NotSet => (),
+            }
+            match sort_facet_values_by {
+                Setting::Set(val) => builder.set_sort_facet_values_by(
+                    val.iter().map(|(name, order)| (name.clone(), (*order).into())).collect(),
+                ),
+                Setting::Reset => builder.reset_sort_facet_values_by(),
+                Setting::NotSet => (),
+            }
+        }
         Setting::Reset => builder.reset_max_values_per_facet(),
         Setting::NotSet => (),
     }
@@ -476,6 +489,13 @@ pub fn settings(
         max_values_per_facet: Setting::Set(
             index.max_values_per_facet(rtxn)?.unwrap_or(DEFAULT_VALUES_PER_FACET),
         ),
+        sort_facet_values_by: Setting::Set(
+            index
+                .sort_facet_values_by(rtxn)?
+                .into_iter()
+                .map(|(name, sort)| (name, sort.into()))
+                .collect(),
+        ),
     };
 
     let pagination = PaginationSettings {

meilisearch-types/src/tasks.rs

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

meilisearch/Cargo.toml

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

meilisearch/src/metrics.rs

@@ -4,32 +4,20 @@ use prometheus::{
     register_int_gauge_vec, HistogramVec, IntCounterVec, IntGauge, IntGaugeVec,
 };
 
-/// Create evenly distributed buckets
-fn create_buckets() -> [f64; 29] {
-    (0..10)
-        .chain((10..100).step_by(10))
-        .chain((100..=1000).step_by(100))
-        .map(|i| i as f64 / 1000.)
-        .collect::<Vec<_>>()
-        .try_into()
-        .unwrap()
-}
+const HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: &[f64; 14] = &[
+    0.0005, 0.0008, 0.00085, 0.0009, 0.00095, 0.001, 0.00105, 0.0011, 0.00115, 0.0012, 0.0015,
+    0.002, 0.003, 1.0,
+];
 
 lazy_static! {
-    pub static ref HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: [f64; 29] = create_buckets();
-    pub static ref MEILISEARCH_HTTP_REQUESTS_TOTAL: IntCounterVec = register_int_counter_vec!(
-        opts!("meilisearch_http_requests_total", "Meilisearch HTTP requests total"),
+    pub static ref HTTP_REQUESTS_TOTAL: IntCounterVec = register_int_counter_vec!(
+        opts!("http_requests_total", "HTTP requests total"),
         &["method", "path"]
     )
     .expect("Can't create a metric");
     pub static ref MEILISEARCH_DB_SIZE_BYTES: IntGauge =
-        register_int_gauge!(opts!("meilisearch_db_size_bytes", "Meilisearch DB Size In Bytes"))
+        register_int_gauge!(opts!("meilisearch_db_size_bytes", "Meilisearch Db Size In Bytes"))
             .expect("Can't create a metric");
-    pub static ref MEILISEARCH_USED_DB_SIZE_BYTES: IntGauge = register_int_gauge!(opts!(
-        "meilisearch_used_db_size_bytes",
-        "Meilisearch Used DB Size In Bytes"
-    ))
-    .expect("Can't create a metric");
     pub static ref MEILISEARCH_INDEX_COUNT: IntGauge =
         register_int_gauge!(opts!("meilisearch_index_count", "Meilisearch Index Count"))
             .expect("Can't create a metric");
@@ -38,16 +26,11 @@ lazy_static! {
         &["index"]
     )
     .expect("Can't create a metric");
-    pub static ref MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS: HistogramVec = register_histogram_vec!(
+    pub static ref HTTP_RESPONSE_TIME_SECONDS: HistogramVec = register_histogram_vec!(
         "http_response_time_seconds",
         "HTTP response times",
         &["method", "path"],
         HTTP_RESPONSE_TIME_CUSTOM_BUCKETS.to_vec()
     )
     .expect("Can't create a metric");
-    pub static ref MEILISEARCH_NB_TASKS: IntGaugeVec = register_int_gauge_vec!(
-        opts!("meilisearch_nb_tasks", "Meilisearch Number of tasks"),
-        &["kind", "value"]
-    )
-    .expect("Can't create a metric");
 }

meilisearch/src/middleware.rs

@@ -52,11 +52,11 @@ where
         if is_registered_resource {
             let request_method = req.method().to_string();
             histogram_timer = Some(
-                crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
+                crate::metrics::HTTP_RESPONSE_TIME_SECONDS
                     .with_label_values(&[&request_method, request_path])
                     .start_timer(),
             );
-            crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
+            crate::metrics::HTTP_REQUESTS_TOTAL
                 .with_label_values(&[&request_method, request_path])
                 .inc();
         }

meilisearch/src/routes/indexes/search.rs

@@ -66,8 +66,6 @@ pub struct SearchQueryGet {
     crop_marker: String,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchMatchingStrategy>)]
     matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrQueryParamError<InvalidRestrictSearchableAttributes>)]
-    pub restrict_searchable_attributes: Option<CS<String>>,
 }
 
 impl From<SearchQueryGet> for SearchQuery {
@@ -98,9 +96,6 @@ impl From<SearchQueryGet> for SearchQuery {
             highlight_post_tag: other.highlight_post_tag,
             crop_marker: other.crop_marker,
             matching_strategy: other.matching_strategy,
-            restrict_searchable_attributes: other
-                .restrict_searchable_attributes
-                .map(|o| o.into_iter().collect()),
         }
     }
 }

meilisearch/src/routes/indexes/settings.rs

@@ -407,6 +407,7 @@ make_setting_route!(
             json!({
                 "faceting": {
                     "max_values_per_facet": setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
+                    "sort_facet_values_by": setting.as_ref().and_then(|s| s.sort_facet_values_by.clone().set()),
                 },
             }),
             Some(req),
@@ -545,6 +546,10 @@ pub async fn update_all(
                     .as_ref()
                     .set()
                     .and_then(|s| s.max_values_per_facet.as_ref().set()),
+                "sort_facet_values_by": new_settings.faceting
+                    .as_ref()
+                    .set()
+                    .and_then(|s| s.sort_facet_values_by.as_ref().set()),
             },
             "pagination": {
                 "max_total_hits": new_settings.pagination

meilisearch/src/routes/metrics.rs

@@ -17,7 +17,7 @@ pub fn configure(config: &mut web::ServiceConfig) {
 
 pub async fn get_metrics(
     index_scheduler: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<IndexScheduler>>,
-    auth_controller: Data<AuthController>,
+    auth_controller: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<AuthController>>,
 ) -> Result<HttpResponse, ResponseError> {
     let auth_filters = index_scheduler.filters();
     if !auth_filters.all_indexes_authorized() {
@@ -28,10 +28,10 @@ pub async fn get_metrics(
         return Err(error);
     }
 
-    let response = create_all_stats((*index_scheduler).clone(), auth_controller, auth_filters)?;
+    let response =
+        create_all_stats((*index_scheduler).clone(), (*auth_controller).clone(), auth_filters)?;
 
     crate::metrics::MEILISEARCH_DB_SIZE_BYTES.set(response.database_size as i64);
-    crate::metrics::MEILISEARCH_USED_DB_SIZE_BYTES.set(response.used_database_size as i64);
     crate::metrics::MEILISEARCH_INDEX_COUNT.set(response.indexes.len() as i64);
 
     for (index, value) in response.indexes.iter() {
@@ -40,14 +40,6 @@ pub async fn get_metrics(
             .set(value.number_of_documents as i64);
     }
 
-    for (kind, value) in index_scheduler.get_stats()? {
-        for (value, count) in value {
-            crate::metrics::MEILISEARCH_NB_TASKS
-                .with_label_values(&[&kind, &value])
-                .set(count as i64);
-        }
-    }
-
     let encoder = TextEncoder::new();
     let mut buffer = vec![];
     encoder.encode(&prometheus::gather(), &mut buffer).expect("Failed to encode metrics");

meilisearch/src/routes/mod.rs

@@ -231,8 +231,6 @@ pub async fn running() -> HttpResponse {
 #[serde(rename_all = "camelCase")]
 pub struct Stats {
     pub database_size: u64,
-    #[serde(skip)]
-    pub used_database_size: u64,
     #[serde(serialize_with = "time::serde::rfc3339::option::serialize")]
     pub last_update: Option<OffsetDateTime>,
     pub indexes: BTreeMap<String, indexes::IndexStats>,
@@ -261,7 +259,6 @@ pub fn create_all_stats(
     let mut last_task: Option<OffsetDateTime> = None;
     let mut indexes = BTreeMap::new();
     let mut database_size = 0;
-    let mut used_database_size = 0;
 
     for index_uid in index_scheduler.index_names()? {
         // Accumulate the size of all indexes, even unauthorized ones, so
@@ -269,7 +266,6 @@ pub fn create_all_stats(
         // See <https://github.com/meilisearch/meilisearch/pull/3541#discussion_r1126747643> for context.
         let stats = index_scheduler.index_stats(&index_uid)?;
         database_size += stats.inner_stats.database_size;
-        used_database_size += stats.inner_stats.used_database_size;
 
         if !filters.is_index_authorized(&index_uid) {
             continue;
@@ -282,14 +278,10 @@ pub fn create_all_stats(
     }
 
     database_size += index_scheduler.size()?;
-    used_database_size += index_scheduler.used_size()?;
     database_size += auth_controller.size()?;
-    used_database_size += auth_controller.used_size()?;
-    let update_file_size = index_scheduler.compute_update_file_size()?;
-    database_size += update_file_size;
-    used_database_size += update_file_size;
+    database_size += index_scheduler.compute_update_file_size()?;
 
-    let stats = Stats { database_size, used_database_size, last_update: last_task, indexes };
+    let stats = Stats { database_size, last_update: last_task, indexes };
     Ok(stats)
 }
 

meilisearch/src/routes/tasks.rs

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

meilisearch/src/search.rs

@@ -5,6 +5,7 @@ use std::time::Instant;
 
 use deserr::Deserr;
 use either::Either;
+use indexmap::IndexMap;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
@@ -68,8 +69,6 @@ pub struct SearchQuery {
     pub crop_marker: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
     pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidRestrictSearchableAttributes>, default)]
-    pub restrict_searchable_attributes: Option<Vec<String>>,
 }
 
 impl SearchQuery {
@@ -121,8 +120,6 @@ pub struct SearchQueryWithIndex {
     pub crop_marker: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
     pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidRestrictSearchableAttributes>, default)]
-    pub restrict_searchable_attributes: Option<Vec<String>>,
 }
 
 impl SearchQueryWithIndex {
@@ -146,7 +143,6 @@ impl SearchQueryWithIndex {
             highlight_post_tag,
             crop_marker,
             matching_strategy,
-            restrict_searchable_attributes,
         } = self;
         (
             index_uid,
@@ -168,7 +164,6 @@ impl SearchQueryWithIndex {
                 highlight_post_tag,
                 crop_marker,
                 matching_strategy,
-                restrict_searchable_attributes,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
@@ -219,7 +214,7 @@ pub struct SearchResult {
     #[serde(flatten)]
     pub hits_info: HitsInfo,
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub facet_distribution: Option<BTreeMap<String, BTreeMap<String, u64>>>,
+    pub facet_distribution: Option<BTreeMap<String, IndexMap<String, u64>>>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub facet_stats: Option<BTreeMap<String, FacetStats>>,
 }
@@ -280,10 +275,6 @@ pub fn perform_search(
         search.query(query);
     }
 
-    if let Some(ref searchable) = query.restrict_searchable_attributes {
-        search.searchable_attributes(searchable);
-    }
-
     let is_finite_pagination = query.is_finite_pagination();
     search.terms_matching_strategy(query.matching_strategy.into());
 
@@ -458,10 +449,30 @@ pub fn perform_search(
                 .unwrap_or(DEFAULT_VALUES_PER_FACET);
             facet_distribution.max_values_per_facet(max_values_by_facet);
 
+            let sort_facet_values_by =
+                index.sort_facet_values_by(&rtxn).map_err(milli::Error::from)?;
+            let default_sort_facet_values_by =
+                sort_facet_values_by.get("*").copied().unwrap_or_default();
+
             if fields.iter().all(|f| f != "*") {
+                let fields: Vec<_> = fields
+                    .into_iter()
+                    .map(|n| {
+                        (
+                            n,
+                            sort_facet_values_by
+                                .get(n)
+                                .copied()
+                                .unwrap_or(default_sort_facet_values_by),
+                        )
+                    })
+                    .collect();
                 facet_distribution.facets(fields);
             }
-            let distribution = facet_distribution.candidates(candidates).execute()?;
+            let distribution = facet_distribution
+                .candidates(candidates)
+                .default_order_by(default_sort_facet_values_by)
+                .execute()?;
             let stats = facet_distribution.compute_stats()?;
             (Some(distribution), Some(stats))
         }

meilisearch/tests/search/mod.rs

@@ -5,7 +5,6 @@ mod errors;
 mod formatted;
 mod multi;
 mod pagination;
-mod restrict_searchable;
 
 use once_cell::sync::Lazy;
 use serde_json::{json, Value};

meilisearch/tests/search/restrict_searchable.rs

@@ -1,263 +0,0 @@
-use once_cell::sync::Lazy;
-use serde_json::{json, Value};
-
-use crate::common::index::Index;
-use crate::common::Server;
-
-async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
-    let index = server.index("test");
-
-    index.add_documents(documents.clone(), None).await;
-    index.wait_task(0).await;
-    index
-}
-
-static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-    {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-    },
-    {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-    },
-    {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-    }])
-});
-
-#[actix_rt::test]
-async fn simple_search_on_title() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["title"]}),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                assert_eq!(response["hits"].as_array().unwrap().len(), 2);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_prefix_search_on_title() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Mar", "restrictSearchableAttributes": ["title"]}),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                assert_eq!(response["hits"].as_array().unwrap().len(), 2);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_title_matching_strategy_all() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search matching strategy all should only return 1 document (ids: 2).
-    index
-        .search(json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["title"], "matchingStrategy": "all"}), |response, code| {
-            assert_eq!(code, 200, "{}", response);
-            assert_eq!(response["hits"].as_array().unwrap().len(), 1);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_unknown_field() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search on unknown field shouldn't return any document.
-    index
-        .search(
-            json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["unknown"]}),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                assert_eq!(response["hits"].as_array().unwrap().len(), 0);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_no_field() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search on no field shouldn't return any document.
-    index
-        .search(
-            json!({"q": "Captain Marvel", "restrictSearchableAttributes": []}),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                assert_eq!(response["hits"].as_array().unwrap().len(), 0);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn word_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // Document 3 should appear before document 2.
-    index
-        .search(
-            json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["title"], "attributesToRetrieve": ["id"]}),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                assert_eq!(
-                    response["hits"],
-                    json!([
-                        {"id": "3"},
-                        {"id": "2"},
-                    ])
-                );
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn word_ranking_rule_order_exact_words() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    index.update_settings_typo_tolerance(json!({"disableOnWords": ["Captain", "Marvel"]})).await;
-    index.wait_task(1).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["title"], "attributesToRetrieve": ["id"]}),
-            |response, code| {
-                assert_eq!(code, 200, "{}", response);
-                assert_eq!(
-                    response["hits"],
-                    json!([
-                        {"id": "3"},
-                        {"id": "2"},
-                    ])
-                );
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn typo_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Capitain Marivel",
-            "desc": "Captain Marvel",
-            "id": "1",
-        },
-        {
-            "title": "Captain Marivel",
-            "desc": "a Shazam ersatz",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["title"], "attributesToRetrieve": ["id"]}), |response, code| {
-            assert_eq!(code, 200, "{}", response);
-            assert_eq!(
-                response["hits"],
-                json!([
-                    {"id": "2"},
-                    {"id": "1"},
-                ])
-            );
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn attributes_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Captain Marvel",
-            "desc": "a Shazam ersatz",
-            "footer": "The story of Captain Marvel",
-            "id": "1",
-        },
-        {
-            "title": "The Avengers",
-            "desc": "Captain Marvel is far from the earth",
-            "footer": "A super hero team",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "restrictSearchableAttributes": ["desc", "footer"], "attributesToRetrieve": ["id"]}), |response, code| {
-            assert_eq!(code, 200, "{}", response);
-            assert_eq!(
-                response["hits"],
-                json!([
-                    {"id": "2"},
-                    {"id": "1"},
-                ])
-            );
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn exactness_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Captain Marvel",
-            "desc": "Captain Marivel",
-            "id": "1",
-        },
-        {
-            "title": "Captain Marvel",
-            "desc": "CaptainMarvel",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToRetrieve": ["id"], "restrictSearchableAttributes": ["desc"]}), |response, code| {
-            assert_eq!(code, 200, "{}", response);
-            assert_eq!(
-                response["hits"],
-                json!([
-                    {"id": "2"},
-                    {"id": "1"},
-                ])
-            );
-        })
-        .await;
-}

meilisearch/tests/tasks/errors.rs

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

milli/Cargo.toml

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

milli/src/heed_codec/mod.rs

@@ -23,9 +23,3 @@ pub use self::roaring_bitmap_length::{
 pub use self::script_language_codec::ScriptLanguageCodec;
 pub use self::str_beu32_codec::{StrBEU16Codec, StrBEU32Codec};
 pub use self::str_str_u8_codec::{U8StrStrCodec, UncheckedU8StrStrCodec};
-
-pub trait BytesDecodeOwned {
-    type DItem;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem>;
-}

milli/src/heed_codec/roaring_bitmap/bo_roaring_bitmap_codec.rs

@@ -2,11 +2,8 @@ use std::borrow::Cow;
 use std::convert::TryInto;
 use std::mem::size_of;
 
-use heed::BytesDecode;
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct BoRoaringBitmapCodec;
 
 impl BoRoaringBitmapCodec {
@@ -16,7 +13,7 @@ impl BoRoaringBitmapCodec {
     }
 }
 
-impl BytesDecode<'_> for BoRoaringBitmapCodec {
+impl heed::BytesDecode<'_> for BoRoaringBitmapCodec {
     type DItem = RoaringBitmap;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
@@ -31,14 +28,6 @@ impl BytesDecode<'_> for BoRoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for BoRoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}
-
 impl heed::BytesEncode<'_> for BoRoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -5,8 +5,6 @@ use std::mem::size_of;
 use byteorder::{NativeEndian, ReadBytesExt, WriteBytesExt};
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 /// This is the limit where using a byteorder became less size efficient
 /// than using a direct roaring encoding, it is also the point where we are able
 /// to determine the encoding used only by using the array of bytes length.
@@ -51,7 +49,7 @@ impl CboRoaringBitmapCodec {
         } else {
             // Otherwise, it means we used the classic RoaringBitmapCodec and
             // that the header takes threshold integers.
-            RoaringBitmap::deserialize_unchecked_from(bytes)
+            RoaringBitmap::deserialize_from(bytes)
         }
     }
 
@@ -71,7 +69,7 @@ impl CboRoaringBitmapCodec {
                     vec.push(integer);
                 }
             } else {
-                roaring |= RoaringBitmap::deserialize_unchecked_from(bytes.as_ref())?;
+                roaring |= RoaringBitmap::deserialize_from(bytes.as_ref())?;
             }
         }
 
@@ -105,14 +103,6 @@ impl heed::BytesDecode<'_> for CboRoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for CboRoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::deserialize_from(bytes).ok()
-    }
-}
-
 impl heed::BytesEncode<'_> for CboRoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap/roaring_bitmap_codec.rs

@@ -2,22 +2,12 @@ use std::borrow::Cow;
 
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct RoaringBitmapCodec;
 
 impl heed::BytesDecode<'_> for RoaringBitmapCodec {
     type DItem = RoaringBitmap;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmap::deserialize_unchecked_from(bytes).ok()
-    }
-}
-
-impl BytesDecodeOwned for RoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
         RoaringBitmap::deserialize_from(bytes).ok()
     }
 }

milli/src/heed_codec/roaring_bitmap_length/bo_roaring_bitmap_len_codec.rs

@@ -1,23 +1,11 @@
 use std::mem;
 
-use heed::BytesDecode;
-
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct BoRoaringBitmapLenCodec;
 
-impl BytesDecode<'_> for BoRoaringBitmapLenCodec {
+impl heed::BytesDecode<'_> for BoRoaringBitmapLenCodec {
     type DItem = u64;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
         Some((bytes.len() / mem::size_of::<u32>()) as u64)
     }
 }
-
-impl BytesDecodeOwned for BoRoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}

milli/src/heed_codec/roaring_bitmap_length/cbo_roaring_bitmap_len_codec.rs

@@ -1,14 +1,11 @@
 use std::mem;
 
-use heed::BytesDecode;
-
 use super::{BoRoaringBitmapLenCodec, RoaringBitmapLenCodec};
 use crate::heed_codec::roaring_bitmap::cbo_roaring_bitmap_codec::THRESHOLD;
-use crate::heed_codec::BytesDecodeOwned;
 
 pub struct CboRoaringBitmapLenCodec;
 
-impl BytesDecode<'_> for CboRoaringBitmapLenCodec {
+impl heed::BytesDecode<'_> for CboRoaringBitmapLenCodec {
     type DItem = u64;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
@@ -23,11 +20,3 @@ impl BytesDecode<'_> for CboRoaringBitmapLenCodec {
         }
     }
 }
-
-impl BytesDecodeOwned for CboRoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}

milli/src/heed_codec/roaring_bitmap_length/roaring_bitmap_len_codec.rs

@@ -3,8 +3,6 @@ use std::mem;
 
 use byteorder::{LittleEndian, ReadBytesExt};
 
-use crate::heed_codec::BytesDecodeOwned;
-
 const SERIAL_COOKIE_NO_RUNCONTAINER: u32 = 12346;
 const SERIAL_COOKIE: u16 = 12347;
 
@@ -61,14 +59,6 @@ impl heed::BytesDecode<'_> for RoaringBitmapLenCodec {
     }
 }
 
-impl BytesDecodeOwned for RoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmapLenCodec::deserialize_from_slice(bytes).ok()
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use heed::BytesEncode;

milli/src/index.rs

@@ -21,9 +21,10 @@ use crate::heed_codec::facet::{
 };
 use crate::heed_codec::{ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
 use crate::{
-    default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
-    FacetDistribution, FieldDistribution, FieldId, FieldIdWordCountCodec, GeoPoint, ObkvCodec,
-    Result, RoaringBitmapCodec, RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16, BEU32,
+    default_criteria, BEU32StrCodec, BoRoaringBitmapCodec, CboRoaringBitmapCodec, Criterion,
+    DocumentId, ExternalDocumentsIds, FacetDistribution, FieldDistribution, FieldId,
+    FieldIdWordCountCodec, GeoPoint, ObkvCodec, OrderBy, Result, RoaringBitmapCodec,
+    RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16, BEU32,
 };
 
 pub const DEFAULT_MIN_WORD_LEN_ONE_TYPO: u8 = 5;
@@ -61,6 +62,7 @@ pub mod main_key {
     pub const EXACT_WORDS: &str = "exact-words";
     pub const EXACT_ATTRIBUTES: &str = "exact-attributes";
     pub const MAX_VALUES_PER_FACET: &str = "max-values-per-facet";
+    pub const SORT_FACET_VALUES_BY: &str = "sort-facet-values-by";
     pub const PAGINATION_MAX_TOTAL_HITS: &str = "pagination-max-total-hits";
 }
 
@@ -110,6 +112,9 @@ pub struct Index {
     /// A prefix of word and all the documents ids containing this prefix, from attributes for which typos are not allowed.
     pub exact_word_prefix_docids: Database<Str, RoaringBitmapCodec>,
 
+    /// Maps a word and a document id (u32) to all the positions where the given word appears.
+    pub docid_word_positions: Database<BEU32StrCodec, BoRoaringBitmapCodec>,
+
     /// Maps the proximity between a pair of words with all the docids where this relation appears.
     pub word_pair_proximity_docids: Database<U8StrStrCodec, CboRoaringBitmapCodec>,
     /// Maps the proximity between a pair of word and prefix with all the docids where this relation appears.
@@ -173,6 +178,7 @@ impl Index {
         let word_prefix_docids = env.create_database(&mut wtxn, Some(WORD_PREFIX_DOCIDS))?;
         let exact_word_prefix_docids =
             env.create_database(&mut wtxn, Some(EXACT_WORD_PREFIX_DOCIDS))?;
+        let docid_word_positions = env.create_database(&mut wtxn, Some(DOCID_WORD_POSITIONS))?;
         let word_pair_proximity_docids =
             env.create_database(&mut wtxn, Some(WORD_PAIR_PROXIMITY_DOCIDS))?;
         let script_language_docids =
@@ -215,6 +221,7 @@ impl Index {
             exact_word_docids,
             word_prefix_docids,
             exact_word_prefix_docids,
+            docid_word_positions,
             word_pair_proximity_docids,
             script_language_docids,
             word_prefix_pair_proximity_docids,
@@ -1228,6 +1235,31 @@ impl Index {
         self.main.delete::<_, Str>(txn, main_key::MAX_VALUES_PER_FACET)
     }
 
+    pub fn sort_facet_values_by(&self, txn: &RoTxn) -> heed::Result<HashMap<String, OrderBy>> {
+        let mut orders = self
+            .main
+            .get::<_, Str, SerdeJson<HashMap<String, OrderBy>>>(
+                txn,
+                main_key::SORT_FACET_VALUES_BY,
+            )?
+            .unwrap_or_default();
+        // Insert the default ordering if it is not already overwritten by the user.
+        orders.entry("*".to_string()).or_insert(OrderBy::Lexicographic);
+        Ok(orders)
+    }
+
+    pub(crate) fn put_sort_facet_values_by(
+        &self,
+        txn: &mut RwTxn,
+        val: &HashMap<String, OrderBy>,
+    ) -> heed::Result<()> {
+        self.main.put::<_, Str, SerdeJson<_>>(txn, main_key::SORT_FACET_VALUES_BY, &val)
+    }
+
+    pub(crate) fn delete_sort_facet_values_by(&self, txn: &mut RwTxn) -> heed::Result<bool> {
+        self.main.delete::<_, Str>(txn, main_key::SORT_FACET_VALUES_BY)
+    }
+
     pub fn pagination_max_total_hits(&self, txn: &RoTxn) -> heed::Result<Option<usize>> {
         self.main.get::<_, Str, OwnedType<usize>>(txn, main_key::PAGINATION_MAX_TOTAL_HITS)
     }
@@ -1466,9 +1498,9 @@ pub(crate) mod tests {
 
         db_snap!(index, field_distribution,
             @r###"
-        age              1     
-        id               2     
-        name             2     
+        age              1
+        id               2
+        name             2
         "###
         );
 
@@ -1486,9 +1518,9 @@ pub(crate) mod tests {
 
         db_snap!(index, field_distribution,
             @r###"
-        age              1     
-        id               2     
-        name             2     
+        age              1
+        id               2
+        name             2
         "###
         );
 
@@ -1502,9 +1534,9 @@ pub(crate) mod tests {
 
         db_snap!(index, field_distribution,
             @r###"
-        has_dog          1     
-        id               2     
-        name             2     
+        has_dog          1
+        id               2
+        name             2
         "###
         );
     }

milli/src/lib.rs

@@ -5,6 +5,52 @@
 #[global_allocator]
 pub static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
+// #[cfg(test)]
+// pub mod allocator {
+//     use std::alloc::{GlobalAlloc, System};
+//     use std::sync::atomic::{self, AtomicI64};
+
+//     #[global_allocator]
+//     pub static ALLOC: CountingAlloc = CountingAlloc {
+//         max_resident: AtomicI64::new(0),
+//         resident: AtomicI64::new(0),
+//         allocated: AtomicI64::new(0),
+//     };
+
+//     pub struct CountingAlloc {
+//         pub max_resident: AtomicI64,
+//         pub resident: AtomicI64,
+//         pub allocated: AtomicI64,
+//     }
+//     unsafe impl GlobalAlloc for CountingAlloc {
+//         unsafe fn alloc(&self, layout: std::alloc::Layout) -> *mut u8 {
+//             self.allocated.fetch_add(layout.size() as i64, atomic::Ordering::SeqCst);
+//             let old_resident =
+//                 self.resident.fetch_add(layout.size() as i64, atomic::Ordering::SeqCst);
+
+//             let resident = old_resident + layout.size() as i64;
+//             self.max_resident.fetch_max(resident, atomic::Ordering::SeqCst);
+
+//             // if layout.size() > 1_000_000 {
+//             //     eprintln!(
+//             //         "allocating {} with new resident size: {resident}",
+//             //         layout.size() / 1_000_000
+//             //     );
+//             //     // let trace = std::backtrace::Backtrace::capture();
+//             //     // let t = trace.to_string();
+//             //     // eprintln!("{t}");
+//             // }
+
+//             System.alloc(layout)
+//         }
+
+//         unsafe fn dealloc(&self, ptr: *mut u8, layout: std::alloc::Layout) {
+//             self.resident.fetch_sub(layout.size() as i64, atomic::Ordering::Relaxed);
+//             System.dealloc(ptr, layout)
+//         }
+//     }
+// }
+
 #[macro_use]
 pub mod documents;
 
@@ -53,8 +99,8 @@ pub use self::heed_codec::{
 };
 pub use self::index::Index;
 pub use self::search::{
-    FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, Search,
-    SearchResult, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
+    FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, OrderBy,
+    Search, SearchResult, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
 };
 
 pub type Result<T> = std::result::Result<T, error::Error>;

milli/src/search/facet/facet_distribution.rs

@@ -1,19 +1,22 @@
-use std::collections::{BTreeMap, HashSet};
+use std::collections::{BTreeMap, HashMap, HashSet};
 use std::ops::ControlFlow;
 use std::{fmt, mem};
 
 use heed::types::ByteSlice;
 use heed::BytesDecode;
+use indexmap::IndexMap;
 use roaring::RoaringBitmap;
+use serde::{Deserialize, Serialize};
 
 use crate::error::UserError;
 use crate::facet::FacetType;
 use crate::heed_codec::facet::{
-    FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
-    OrderedF64Codec,
+    FacetGroupKeyCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec, OrderedF64Codec,
 };
 use crate::heed_codec::{ByteSliceRefCodec, StrRefCodec};
-use crate::search::facet::facet_distribution_iter;
+use crate::search::facet::facet_distribution_iter::{
+    count_iterate_over_facet_distribution, lexicographically_iterate_over_facet_distribution,
+};
 use crate::{FieldId, Index, Result};
 
 /// The default number of values by facets that will
@@ -24,10 +27,21 @@ pub const DEFAULT_VALUES_PER_FACET: usize = 100;
 /// the system to choose between one algorithm or another.
 const CANDIDATES_THRESHOLD: u64 = 3000;
 
+/// How should we fetch the facets?
+#[derive(Debug, Default, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+pub enum OrderBy {
+    /// By lexicographic order...
+    #[default]
+    Lexicographic,
+    /// Or by number of docids in common?
+    Count,
+}
+
 pub struct FacetDistribution<'a> {
-    facets: Option<HashSet<String>>,
+    facets: Option<HashMap<String, OrderBy>>,
     candidates: Option<RoaringBitmap>,
     max_values_per_facet: usize,
+    default_order_by: OrderBy,
     rtxn: &'a heed::RoTxn<'a>,
     index: &'a Index,
 }
@@ -38,13 +52,22 @@ impl<'a> FacetDistribution<'a> {
             facets: None,
             candidates: None,
             max_values_per_facet: DEFAULT_VALUES_PER_FACET,
+            default_order_by: OrderBy::default(),
             rtxn,
             index,
         }
     }
 
-    pub fn facets<I: IntoIterator<Item = A>, A: AsRef<str>>(&mut self, names: I) -> &mut Self {
-        self.facets = Some(names.into_iter().map(|s| s.as_ref().to_string()).collect());
+    pub fn facets<I: IntoIterator<Item = (A, OrderBy)>, A: AsRef<str>>(
+        &mut self,
+        names_ordered_by: I,
+    ) -> &mut Self {
+        self.facets = Some(
+            names_ordered_by
+                .into_iter()
+                .map(|(name, order_by)| (name.as_ref().to_string(), order_by))
+                .collect(),
+        );
         self
     }
 
@@ -53,6 +76,11 @@ impl<'a> FacetDistribution<'a> {
         self
     }
 
+    pub fn default_order_by(&mut self, order_by: OrderBy) -> &mut Self {
+        self.default_order_by = order_by;
+        self
+    }
+
     pub fn candidates(&mut self, candidates: RoaringBitmap) -> &mut Self {
         self.candidates = Some(candidates);
         self
@@ -65,7 +93,7 @@ impl<'a> FacetDistribution<'a> {
         field_id: FieldId,
         facet_type: FacetType,
         candidates: &RoaringBitmap,
-        distribution: &mut BTreeMap<String, u64>,
+        distribution: &mut IndexMap<String, u64>,
     ) -> heed::Result<()> {
         match facet_type {
             FacetType::Number => {
@@ -134,9 +162,15 @@ impl<'a> FacetDistribution<'a> {
         &self,
         field_id: FieldId,
         candidates: &RoaringBitmap,
-        distribution: &mut BTreeMap<String, u64>,
+        order_by: OrderBy,
+        distribution: &mut IndexMap<String, u64>,
     ) -> heed::Result<()> {
-        facet_distribution_iter::iterate_over_facet_distribution(
+        let search_function = match order_by {
+            OrderBy::Lexicographic => lexicographically_iterate_over_facet_distribution,
+            OrderBy::Count => count_iterate_over_facet_distribution,
+        };
+
+        search_function(
             self.rtxn,
             self.index
                 .facet_id_f64_docids
@@ -159,9 +193,15 @@ impl<'a> FacetDistribution<'a> {
         &self,
         field_id: FieldId,
         candidates: &RoaringBitmap,
-        distribution: &mut BTreeMap<String, u64>,
+        order_by: OrderBy,
+        distribution: &mut IndexMap<String, u64>,
     ) -> heed::Result<()> {
-        facet_distribution_iter::iterate_over_facet_distribution(
+        let search_function = match order_by {
+            OrderBy::Lexicographic => lexicographically_iterate_over_facet_distribution,
+            OrderBy::Count => count_iterate_over_facet_distribution,
+        };
+
+        search_function(
             self.rtxn,
             self.index
                 .facet_id_string_docids
@@ -189,93 +229,48 @@ impl<'a> FacetDistribution<'a> {
         )
     }
 
-    /// Placeholder search, a.k.a. no candidates were specified. We iterate throught the
-    /// facet values one by one and iterate on the facet level 0 for numbers.
-    fn facet_values_from_raw_facet_database(
+    fn facet_values(
         &self,
         field_id: FieldId,
-    ) -> heed::Result<BTreeMap<String, u64>> {
-        let mut distribution = BTreeMap::new();
-
-        let db = self.index.facet_id_f64_docids;
-        let mut prefix = vec![];
-        prefix.extend_from_slice(&field_id.to_be_bytes());
-        prefix.push(0); // read values from level 0 only
-
-        let iter = db
-            .as_polymorph()
-            .prefix_iter::<_, ByteSlice, ByteSlice>(self.rtxn, prefix.as_slice())?
-            .remap_types::<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>();
-
-        for result in iter {
-            let (key, value) = result?;
-            distribution.insert(key.left_bound.to_string(), value.bitmap.len());
-            if distribution.len() == self.max_values_per_facet {
-                break;
-            }
-        }
-
-        let iter = self
-            .index
-            .facet_id_string_docids
-            .as_polymorph()
-            .prefix_iter::<_, ByteSlice, ByteSlice>(self.rtxn, prefix.as_slice())?
-            .remap_types::<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>();
-
-        for result in iter {
-            let (key, value) = result?;
-
-            let docid = value.bitmap.iter().next().unwrap();
-            let key: (FieldId, _, &'a str) = (field_id, docid, key.left_bound);
-            let original_string =
-                self.index.field_id_docid_facet_strings.get(self.rtxn, &key)?.unwrap().to_owned();
-
-            distribution.insert(original_string, value.bitmap.len());
-            if distribution.len() == self.max_values_per_facet {
-                break;
-            }
-        }
-
-        Ok(distribution)
-    }
-
-    fn facet_values(&self, field_id: FieldId) -> heed::Result<BTreeMap<String, u64>> {
+        order_by: OrderBy,
+    ) -> heed::Result<IndexMap<String, u64>> {
         use FacetType::{Number, String};
 
-        match self.candidates {
-            Some(ref candidates) => {
+        let mut distribution = IndexMap::new();
+        match (order_by, &self.candidates) {
+            (OrderBy::Lexicographic, Some(cnd)) if cnd.len() <= CANDIDATES_THRESHOLD => {
                 // Classic search, candidates were specified, we must return facet values only related
                 // to those candidates. We also enter here for facet strings for performance reasons.
-                let mut distribution = BTreeMap::new();
-                if candidates.len() <= CANDIDATES_THRESHOLD {
-                    self.facet_distribution_from_documents(
-                        field_id,
-                        Number,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                    self.facet_distribution_from_documents(
-                        field_id,
-                        String,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                } else {
-                    self.facet_numbers_distribution_from_facet_levels(
-                        field_id,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                    self.facet_strings_distribution_from_facet_levels(
-                        field_id,
-                        candidates,
-                        &mut distribution,
-                    )?;
-                }
-                Ok(distribution)
+                self.facet_distribution_from_documents(field_id, Number, cnd, &mut distribution)?;
+                self.facet_distribution_from_documents(field_id, String, cnd, &mut distribution)?;
             }
-            None => self.facet_values_from_raw_facet_database(field_id),
-        }
+            _ => {
+                let universe;
+                let candidates;
+                match &self.candidates {
+                    Some(cnd) => candidates = cnd,
+                    None => {
+                        universe = self.index.documents_ids(self.rtxn)?;
+                        candidates = &universe;
+                    }
+                }
+
+                self.facet_numbers_distribution_from_facet_levels(
+                    field_id,
+                    candidates,
+                    order_by,
+                    &mut distribution,
+                )?;
+                self.facet_strings_distribution_from_facet_levels(
+                    field_id,
+                    candidates,
+                    order_by,
+                    &mut distribution,
+                )?;
+            }
+        };
+
+        Ok(distribution)
     }
 
     pub fn compute_stats(&self) -> Result<BTreeMap<String, (f64, f64)>> {
@@ -291,6 +286,7 @@ impl<'a> FacetDistribution<'a> {
             Some(facets) => {
                 let invalid_fields: HashSet<_> = facets
                     .iter()
+                    .map(|(name, _)| name)
                     .filter(|facet| !crate::is_faceted(facet, &filterable_fields))
                     .collect();
                 if !invalid_fields.is_empty() {
@@ -300,7 +296,7 @@ impl<'a> FacetDistribution<'a> {
                     }
                     .into());
                 } else {
-                    facets.clone()
+                    facets.into_iter().map(|(name, _)| name).cloned().collect()
                 }
             }
             None => filterable_fields,
@@ -337,7 +333,7 @@ impl<'a> FacetDistribution<'a> {
         Ok(distribution)
     }
 
-    pub fn execute(&self) -> Result<BTreeMap<String, BTreeMap<String, u64>>> {
+    pub fn execute(&self) -> Result<BTreeMap<String, IndexMap<String, u64>>> {
         let fields_ids_map = self.index.fields_ids_map(self.rtxn)?;
         let filterable_fields = self.index.filterable_fields(self.rtxn)?;
 
@@ -345,6 +341,7 @@ impl<'a> FacetDistribution<'a> {
             Some(ref facets) => {
                 let invalid_fields: HashSet<_> = facets
                     .iter()
+                    .map(|(name, _)| name)
                     .filter(|facet| !crate::is_faceted(facet, &filterable_fields))
                     .collect();
                 if !invalid_fields.is_empty() {
@@ -354,7 +351,7 @@ impl<'a> FacetDistribution<'a> {
                     }
                     .into());
                 } else {
-                    facets.clone()
+                    facets.into_iter().map(|(name, _)| name).cloned().collect()
                 }
             }
             None => filterable_fields,
@@ -363,7 +360,13 @@ impl<'a> FacetDistribution<'a> {
         let mut distribution = BTreeMap::new();
         for (fid, name) in fields_ids_map.iter() {
             if crate::is_faceted(name, &fields) {
-                let values = self.facet_values(fid)?;
+                let order_by = self
+                    .facets
+                    .as_ref()
+                    .map(|facets| facets.get(name).copied())
+                    .flatten()
+                    .unwrap_or(self.default_order_by);
+                let values = self.facet_values(fid, order_by)?;
                 distribution.insert(name.to_string(), values);
             }
         }
@@ -374,13 +377,20 @@ impl<'a> FacetDistribution<'a> {
 
 impl fmt::Debug for FacetDistribution<'_> {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        let FacetDistribution { facets, candidates, max_values_per_facet, rtxn: _, index: _ } =
-            self;
+        let FacetDistribution {
+            facets,
+            candidates,
+            max_values_per_facet,
+            default_order_by,
+            rtxn: _,
+            index: _,
+        } = self;
 
         f.debug_struct("FacetDistribution")
             .field("facets", facets)
             .field("candidates", candidates)
             .field("max_values_per_facet", max_values_per_facet)
+            .field("default_order_by", default_order_by)
             .finish()
     }
 }
@@ -392,7 +402,7 @@ mod tests {
 
     use crate::documents::documents_batch_reader_from_objects;
     use crate::index::tests::TempIndex;
-    use crate::{milli_snap, FacetDistribution};
+    use crate::{milli_snap, FacetDistribution, OrderBy};
 
     #[test]
     fn few_candidates_few_facet_values() {
@@ -417,14 +427,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2, "RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates([0, 1, 2].iter().copied().collect())
             .execute()
             .unwrap();
@@ -432,7 +442,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2, "RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates([1, 2].iter().copied().collect())
             .execute()
             .unwrap();
@@ -443,7 +453,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"  blue": 1, "RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates([2].iter().copied().collect())
             .execute()
             .unwrap();
@@ -451,7 +461,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates([0, 1, 2].iter().copied().collect())
             .max_values_per_facet(1)
             .execute()
@@ -489,14 +499,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 4000, "Red": 6000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .max_values_per_facet(1)
             .execute()
             .unwrap();
@@ -504,7 +514,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 4000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..10_000).collect())
             .execute()
             .unwrap();
@@ -512,7 +522,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 4000, "Red": 6000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..5_000).collect())
             .execute()
             .unwrap();
@@ -520,7 +530,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2000, "Red": 3000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..5_000).collect())
             .execute()
             .unwrap();
@@ -528,7 +538,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2000, "Red": 3000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..5_000).collect())
             .max_values_per_facet(1)
             .execute()
@@ -566,14 +576,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"ac9229ed5964d893af96a7076e2f8af5");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .max_values_per_facet(2)
             .execute()
             .unwrap();
@@ -581,7 +591,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "no_candidates_with_max_2", @r###"{"colour": {"0": 10, "1": 10}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..10_000).collect())
             .execute()
             .unwrap();
@@ -589,7 +599,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_10_000", @"ac9229ed5964d893af96a7076e2f8af5");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..5_000).collect())
             .execute()
             .unwrap();
@@ -626,14 +636,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -641,7 +651,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 999.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();
@@ -678,14 +688,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -693,7 +703,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 1999.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();
@@ -730,14 +740,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -745,7 +755,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 999.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();
@@ -786,14 +796,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -801,7 +811,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 1998.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(std::iter::once("colour"))
+            .facets(std::iter::once(("colour", OrderBy::default())))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();

milli/src/search/facet/facet_distribution_iter.rs

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

milli/src/search/facet/mod.rs

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

milli/src/search/mod.rs

@@ -4,7 +4,7 @@ use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
 use once_cell::sync::Lazy;
 use roaring::bitmap::RoaringBitmap;
 
-pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET};
+pub use self::facet::{FacetDistribution, Filter, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::new::matches::{FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWords};
 use self::new::PartialSearchResult;
 use crate::{
@@ -27,7 +27,6 @@ pub struct Search<'a> {
     offset: usize,
     limit: usize,
     sort_criteria: Option<Vec<AscDesc>>,
-    searchable_attributes: Option<&'a [String]>,
     geo_strategy: new::GeoSortStrategy,
     terms_matching_strategy: TermsMatchingStrategy,
     words_limit: usize,
@@ -44,7 +43,6 @@ impl<'a> Search<'a> {
             offset: 0,
             limit: 20,
             sort_criteria: None,
-            searchable_attributes: None,
             geo_strategy: new::GeoSortStrategy::default(),
             terms_matching_strategy: TermsMatchingStrategy::default(),
             exhaustive_number_hits: false,
@@ -74,11 +72,6 @@ impl<'a> Search<'a> {
         self
     }
 
-    pub fn searchable_attributes(&mut self, searchable: &'a [String]) -> &mut Search<'a> {
-        self.searchable_attributes = Some(searchable);
-        self
-    }
-
     pub fn terms_matching_strategy(&mut self, value: TermsMatchingStrategy) -> &mut Search<'a> {
         self.terms_matching_strategy = value;
         self
@@ -109,11 +102,6 @@ impl<'a> Search<'a> {
 
     pub fn execute(&self) -> Result<SearchResult> {
         let mut ctx = SearchContext::new(self.index, self.rtxn);
-
-        if let Some(searchable_attributes) = self.searchable_attributes {
-            ctx.searchable_attributes(searchable_attributes)?;
-        }
-
         let PartialSearchResult { located_query_terms, candidates, documents_ids } =
             execute_search(
                 &mut ctx,
@@ -148,7 +136,6 @@ impl fmt::Debug for Search<'_> {
             offset,
             limit,
             sort_criteria,
-            searchable_attributes,
             geo_strategy: _,
             terms_matching_strategy,
             words_limit,
@@ -162,7 +149,6 @@ impl fmt::Debug for Search<'_> {
             .field("offset", offset)
             .field("limit", limit)
             .field("sort_criteria", sort_criteria)
-            .field("searchable_attributes", searchable_attributes)
             .field("terms_matching_strategy", terms_matching_strategy)
             .field("exhaustive_number_hits", exhaustive_number_hits)
             .field("words_limit", words_limit)

milli/src/search/new/db_cache.rs

@@ -4,13 +4,12 @@ use std::hash::Hash;
 
 use fxhash::FxHashMap;
 use heed::types::ByteSlice;
-use heed::{BytesEncode, Database, RoTxn};
+use heed::{BytesDecode, BytesEncode, Database, RoTxn};
 use roaring::RoaringBitmap;
 
 use super::interner::Interned;
 use super::Word;
-use crate::heed_codec::{BytesDecodeOwned, StrBEU16Codec};
-use crate::update::{merge_cbo_roaring_bitmaps, MergeFn};
+use crate::heed_codec::StrBEU16Codec;
 use crate::{
     CboRoaringBitmapCodec, CboRoaringBitmapLenCodec, Result, RoaringBitmapCodec, SearchContext,
 };
@@ -23,110 +22,50 @@ use crate::{
 #[derive(Default)]
 pub struct DatabaseCache<'ctx> {
     pub word_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
     pub word_prefix_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
     pub prefix_word_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
-    pub word_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub exact_word_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub exact_word_prefix_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
+    pub word_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub exact_word_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub word_prefix_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub exact_word_prefix_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
 
     pub words_fst: Option<fst::Set<Cow<'ctx, [u8]>>>,
-    pub word_position_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_position_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
+    pub word_position_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
+    pub word_prefix_position_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
     pub word_positions: FxHashMap<Interned<String>, Vec<u16>>,
     pub word_prefix_positions: FxHashMap<Interned<String>, Vec<u16>>,
 
-    pub word_fid_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_fid_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
+    pub word_fid_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
+    pub word_prefix_fid_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
     pub word_fids: FxHashMap<Interned<String>, Vec<u16>>,
     pub word_prefix_fids: FxHashMap<Interned<String>, Vec<u16>>,
 }
 impl<'ctx> DatabaseCache<'ctx> {
-    fn get_value<'v, K1, KC, DC>(
+    fn get_value<'v, K1, KC>(
         txn: &'ctx RoTxn,
         cache_key: K1,
         db_key: &'v KC::EItem,
-        cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
+        cache: &mut FxHashMap<K1, Option<&'ctx [u8]>>,
         db: Database<KC, ByteSlice>,
-    ) -> Result<Option<DC::DItem>>
+    ) -> Result<Option<&'ctx [u8]>>
     where
         K1: Copy + Eq + Hash,
         KC: BytesEncode<'v>,
-        DC: BytesDecodeOwned,
     {
-        match cache.entry(cache_key) {
-            Entry::Occupied(_) => {}
+        let bitmap_ptr = match cache.entry(cache_key) {
+            Entry::Occupied(bitmap_ptr) => *bitmap_ptr.get(),
             Entry::Vacant(entry) => {
-                let bitmap_ptr = db.get(txn, db_key)?.map(Cow::Borrowed);
-                entry.insert(bitmap_ptr);
-            }
-        }
-
-        match cache.get(&cache_key).unwrap() {
-            Some(Cow::Borrowed(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            Some(Cow::Owned(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            None => Ok(None),
-        }
-    }
-
-    fn get_value_from_keys<'v, K1, KC, DC>(
-        txn: &'ctx RoTxn,
-        cache_key: K1,
-        db_keys: &'v [KC::EItem],
-        cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
-        db: Database<KC, ByteSlice>,
-        merger: MergeFn,
-    ) -> Result<Option<DC::DItem>>
-    where
-        K1: Copy + Eq + Hash,
-        KC: BytesEncode<'v>,
-        DC: BytesDecodeOwned,
-        KC::EItem: Sized,
-    {
-        match cache.entry(cache_key) {
-            Entry::Occupied(_) => {}
-            Entry::Vacant(entry) => {
-                let bitmap_ptr: Option<Cow<'ctx, [u8]>> = match db_keys {
-                    [] => None,
-                    [key] => db.get(txn, key)?.map(Cow::Borrowed),
-                    keys => {
-                        let bitmaps = keys
-                            .iter()
-                            .filter_map(|key| db.get(txn, key).transpose())
-                            .map(|v| v.map(Cow::Borrowed))
-                            .collect::<std::result::Result<Vec<Cow<[u8]>>, _>>()?;
-
-                        if bitmaps.is_empty() {
-                            None
-                        } else {
-                            Some(merger(&[], &bitmaps[..])?)
-                        }
-                    }
-                };
-
+                let bitmap_ptr = db.get(txn, db_key)?;
                 entry.insert(bitmap_ptr);
+                bitmap_ptr
             }
         };
-
-        match cache.get(&cache_key).unwrap() {
-            Some(Cow::Borrowed(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            Some(Cow::Owned(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            None => Ok(None),
-        }
+        Ok(bitmap_ptr)
     }
 }
-
 impl<'ctx> SearchContext<'ctx> {
     pub fn get_words_fst(&mut self) -> Result<fst::Set<Cow<'ctx, [u8]>>> {
         if let Some(fst) = self.db_cache.words_fst.clone() {
@@ -160,41 +99,30 @@ impl<'ctx> SearchContext<'ctx> {
 
     /// Retrieve or insert the given value in the `word_docids` database.
     fn get_db_word_docids(&mut self, word: Interned<String>) -> Result<Option<RoaringBitmap>> {
-        match &self.restricted_fids {
-            Some(restricted_fids) => {
-                let interned = self.word_interner.get(word).as_str();
-                let keys: Vec<_> = restricted_fids.iter().map(|fid| (interned, *fid)).collect();
-
-                DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
-                    self.txn,
-                    word,
-                    &keys[..],
-                    &mut self.db_cache.word_docids,
-                    self.index.word_fid_docids.remap_data_type::<ByteSlice>(),
-                    merge_cbo_roaring_bitmaps,
-                )
-            }
-            None => DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
-                self.txn,
-                word,
-                self.word_interner.get(word).as_str(),
-                &mut self.db_cache.word_docids,
-                self.index.word_docids.remap_data_type::<ByteSlice>(),
-            ),
-        }
+        DatabaseCache::get_value(
+            self.txn,
+            word,
+            self.word_interner.get(word).as_str(),
+            &mut self.db_cache.word_docids,
+            self.index.word_docids.remap_data_type::<ByteSlice>(),
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     fn get_db_exact_word_docids(
         &mut self,
         word: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             word,
             self.word_interner.get(word).as_str(),
             &mut self.db_cache.exact_word_docids,
             self.index.exact_word_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn word_prefix_docids(&mut self, prefix: Word) -> Result<Option<RoaringBitmap>> {
@@ -222,41 +150,30 @@ impl<'ctx> SearchContext<'ctx> {
         &mut self,
         prefix: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        match &self.restricted_fids {
-            Some(restricted_fids) => {
-                let interned = self.word_interner.get(prefix).as_str();
-                let keys: Vec<_> = restricted_fids.iter().map(|fid| (interned, *fid)).collect();
-
-                DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
-                    self.txn,
-                    prefix,
-                    &keys[..],
-                    &mut self.db_cache.word_prefix_docids,
-                    self.index.word_prefix_fid_docids.remap_data_type::<ByteSlice>(),
-                    merge_cbo_roaring_bitmaps,
-                )
-            }
-            None => DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
-                self.txn,
-                prefix,
-                self.word_interner.get(prefix).as_str(),
-                &mut self.db_cache.word_prefix_docids,
-                self.index.word_prefix_docids.remap_data_type::<ByteSlice>(),
-            ),
-        }
+        DatabaseCache::get_value(
+            self.txn,
+            prefix,
+            self.word_interner.get(prefix).as_str(),
+            &mut self.db_cache.word_prefix_docids,
+            self.index.word_prefix_docids.remap_data_type::<ByteSlice>(),
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     fn get_db_exact_word_prefix_docids(
         &mut self,
         prefix: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             prefix,
             self.word_interner.get(prefix).as_str(),
             &mut self.db_cache.exact_word_prefix_docids,
             self.index.exact_word_prefix_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_pair_proximity_docids(
@@ -265,7 +182,7 @@ impl<'ctx> SearchContext<'ctx> {
         word2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, word2),
             &(
@@ -275,7 +192,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_pair_proximity_docids,
             self.index.word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_pair_proximity_docids_len(
@@ -284,7 +203,7 @@ impl<'ctx> SearchContext<'ctx> {
         word2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<u64>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapLenCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, word2),
             &(
@@ -294,7 +213,11 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_pair_proximity_docids,
             self.index.word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| {
+            CboRoaringBitmapLenCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into())
+        })
+        .transpose()
     }
 
     pub fn get_db_word_prefix_pair_proximity_docids(
@@ -303,7 +226,7 @@ impl<'ctx> SearchContext<'ctx> {
         prefix2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, prefix2),
             &(
@@ -313,7 +236,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_prefix_pair_proximity_docids,
             self.index.word_prefix_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
     pub fn get_db_prefix_word_pair_proximity_docids(
         &mut self,
@@ -321,7 +246,7 @@ impl<'ctx> SearchContext<'ctx> {
         right: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, left_prefix, right),
             &(
@@ -331,7 +256,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.prefix_word_pair_proximity_docids,
             self.index.prefix_word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_fid_docids(
@@ -339,18 +266,15 @@ impl<'ctx> SearchContext<'ctx> {
         word: Interned<String>,
         fid: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        // if the requested fid isn't in the restricted list, return None.
-        if self.restricted_fids.as_ref().map_or(false, |fids| !fids.contains(&fid)) {
-            return Ok(None);
-        }
-
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word, fid),
             &(self.word_interner.get(word).as_str(), fid),
             &mut self.db_cache.word_fid_docids,
             self.index.word_fid_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_prefix_fid_docids(
@@ -358,18 +282,15 @@ impl<'ctx> SearchContext<'ctx> {
         word_prefix: Interned<String>,
         fid: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        // if the requested fid isn't in the restricted list, return None.
-        if self.restricted_fids.as_ref().map_or(false, |fids| !fids.contains(&fid)) {
-            return Ok(None);
-        }
-
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word_prefix, fid),
             &(self.word_interner.get(word_prefix).as_str(), fid),
             &mut self.db_cache.word_prefix_fid_docids,
             self.index.word_prefix_fid_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_fids(&mut self, word: Interned<String>) -> Result<Vec<u16>> {
@@ -388,7 +309,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, fid), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache.word_fid_docids.insert((word, fid), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_fid_docids.insert((word, fid), Some(value));
                     fids.push(fid);
                 }
                 entry.insert(fids.clone());
@@ -414,9 +335,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, fid), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache
-                        .word_prefix_fid_docids
-                        .insert((word_prefix, fid), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_prefix_fid_docids.insert((word_prefix, fid), Some(value));
                     fids.push(fid);
                 }
                 entry.insert(fids.clone());
@@ -431,13 +350,15 @@ impl<'ctx> SearchContext<'ctx> {
         word: Interned<String>,
         position: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word, position),
             &(self.word_interner.get(word).as_str(), position),
             &mut self.db_cache.word_position_docids,
             self.index.word_position_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_prefix_position_docids(
@@ -445,13 +366,15 @@ impl<'ctx> SearchContext<'ctx> {
         word_prefix: Interned<String>,
         position: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word_prefix, position),
             &(self.word_interner.get(word_prefix).as_str(), position),
             &mut self.db_cache.word_prefix_position_docids,
             self.index.word_prefix_position_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_positions(&mut self, word: Interned<String>) -> Result<Vec<u16>> {
@@ -470,9 +393,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, position), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache
-                        .word_position_docids
-                        .insert((word, position), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_position_docids.insert((word, position), Some(value));
                     positions.push(position);
                 }
                 entry.insert(positions.clone());
@@ -503,7 +424,7 @@ impl<'ctx> SearchContext<'ctx> {
                     // filling other caches to avoid searching for them again
                     self.db_cache
                         .word_prefix_position_docids
-                        .insert((word_prefix, position), Some(Cow::Borrowed(value)));
+                        .insert((word_prefix, position), Some(value));
                     positions.push(position);
                 }
                 entry.insert(positions.clone());

milli/src/search/new/matches/.mod.rs.pending-snap

@@ -1,449 +0,0 @@
-{"run_id":"1683129457-574770000","line":622,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode-3","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":622,"expression":"matcher.format(format_options)"},"snapshot":"<em>Westfália</em>"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Westfáli</em>a"}}
-{"run_id":"1683133106-100492000","line":738,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":839,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":573,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":640,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":600,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":802,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":746,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":648,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":609,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":811,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":582,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":755,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":657,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":820,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":764,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":666,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":773,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":675,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":684,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":782,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":693,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":702,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":711,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":720,"new":null,"old":null}
-{"run_id":"1683133106-100492000","line":622,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode-3","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":622,"expression":"matcher.format(format_options)"},"snapshot":"Westfáliaaaaaa"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Westfáli</em>aaaaaaa"}}
-{"run_id":"1683193451-2793000","line":654,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":616,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":590,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":851,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":814,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":751,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":759,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":662,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":625,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":823,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":599,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":832,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":671,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":768,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":680,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":777,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":689,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":786,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":698,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":795,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":707,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":716,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":725,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":734,"new":null,"old":null}
-{"run_id":"1683193451-2793000","line":637,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode-3","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":637,"expression":"matcher.format(format_options)"},"snapshot":"Westfáliaaaaaa"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Westfáli</em>aaaaaaa"}}
-{"run_id":"1683193542-499542000","line":851,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":751,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":616,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":814,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":590,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":654,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":759,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":662,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":625,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":823,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":599,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":832,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":768,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":671,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":777,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":680,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":786,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":689,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":698,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":795,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":707,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":716,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":725,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":734,"new":null,"old":null}
-{"run_id":"1683193542-499542000","line":637,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode-3","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":637,"expression":"matcher.format(format_options)"},"snapshot":"Westfáliaaaaaa"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Westfáli</em>aaaaaaa"}}
-{"run_id":"1683193590-661809000","line":814,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":851,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":590,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":751,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":616,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":654,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":662,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":759,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":625,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":823,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":599,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":832,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":671,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":768,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":680,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":777,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":689,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":786,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":698,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":795,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":707,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":716,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":725,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":734,"new":null,"old":null}
-{"run_id":"1683193590-661809000","line":637,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode-3","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":637,"expression":"matcher.format(format_options)"},"snapshot":"<em>Westfália</em>"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Westfáli</em>a"}}
-{"run_id":"1683196250-584747000","line":654,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":616,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":851,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":814,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":590,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":751,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":662,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":759,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":625,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":823,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":599,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":671,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":832,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":768,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":680,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":777,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":689,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":786,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":698,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":795,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":707,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":716,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":725,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":734,"new":null,"old":null}
-{"run_id":"1683196250-584747000","line":637,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode-3","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":637,"expression":"matcher.format(format_options)"},"snapshot":"<em>Westfália</em>"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Westfáli</em>a"}}
-{"run_id":"1683196569-36502000","line":851,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":751,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":654,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":590,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":814,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":759,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":662,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":823,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":599,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":768,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":832,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":671,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":777,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":680,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":786,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":689,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":795,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":698,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":707,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":716,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":725,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":734,"new":null,"old":null}
-{"run_id":"1683196569-36502000","line":616,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"highlight_unicode","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":616,"expression":"matcher.format(format_options)"},"snapshot":"<em>Ŵôřlḑ</em>ôle"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"<em>Ŵôřlḑôle</em>"}}
-{"run_id":"1683196614-298348000","line":654,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":814,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":851,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":590,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":616,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":751,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":662,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":759,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":625,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":823,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":599,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":832,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":671,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":768,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":680,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":777,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":689,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":637,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":786,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":698,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":795,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":707,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":716,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":725,"new":null,"old":null}
-{"run_id":"1683196614-298348000","line":734,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":751,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":590,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":654,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":616,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":814,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":851,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":662,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":759,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":625,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":823,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":599,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":671,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":832,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":768,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":680,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":777,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":689,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":786,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":637,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":698,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":795,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":707,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":716,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":725,"new":null,"old":null}
-{"run_id":"1683196758-130465000","line":734,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":616,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":814,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":590,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":654,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":751,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":662,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":625,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":759,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":823,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":599,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":832,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":671,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":768,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":680,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":777,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":689,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":786,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":637,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":698,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":795,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":707,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":716,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":725,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":734,"new":null,"old":null}
-{"run_id":"1683213265-505594000","line":850,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"partial_matches","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":850,"expression":"matcher.format(format_options)"},"snapshot":"_the_ do or die can't be he do and or isn't he"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_"}}
-{"run_id":"1683213465-911114000","line":751,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":654,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":814,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":590,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":616,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":759,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":662,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":625,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":823,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":599,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":832,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":768,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":671,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":777,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":680,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":786,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":689,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":637,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":698,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":795,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":707,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":716,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":725,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":734,"new":null,"old":null}
-{"run_id":"1683213465-911114000","line":850,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"partial_matches","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":850,"expression":"matcher.format(format_options)"},"snapshot":"_the_ do or die can't be he do and or isn't he"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_"}}
-{"run_id":"1683213557-564653000","line":751,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":590,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":814,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":616,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":654,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":759,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":625,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":662,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":823,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":599,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":832,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":768,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":671,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":777,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":680,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":786,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":689,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":637,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":795,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":698,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":707,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":716,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":725,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":734,"new":null,"old":null}
-{"run_id":"1683213557-564653000","line":850,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"partial_matches","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":850,"expression":"matcher.format(format_options)"},"snapshot":"_the_ do or die can't be he do and or isn't he thedoor"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_ _thedoor_"}}
-{"run_id":"1683213999-273520000","line":657,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":754,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":619,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":593,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":817,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":665,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":762,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":628,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":826,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":602,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":674,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":835,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":771,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":683,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":780,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":692,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":701,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":789,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":640,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":710,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":798,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":719,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":728,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":737,"new":null,"old":null}
-{"run_id":"1683213999-273520000","line":853,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"partial_matches","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":853,"expression":"matcher.format(format_options)"},"snapshot":"_the_ do or die can't be he do and or isn't he thedoor"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_ _thedoor_"}}
-{"run_id":"1683710541-379812000","line":754,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":593,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":657,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":817,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":619,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":762,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":665,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":628,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":826,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":602,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":771,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":835,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":674,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":780,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":683,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":789,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":692,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":640,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":798,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":701,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":710,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":719,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":728,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":737,"new":null,"old":null}
-{"run_id":"1683710541-379812000","line":853,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"partial_matches","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":853,"expression":"matcher.format(format_options)"},"snapshot":"_the_ do or die can't be he do and or isn't he _thedoor_"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_ _thedoor_"}}
-{"run_id":"1683710687-182342000","line":619,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":657,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":817,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":593,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":754,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":665,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":628,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":762,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":826,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":602,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":835,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":674,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":771,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":780,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":683,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":640,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":692,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":789,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":701,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":798,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":710,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":719,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":728,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":737,"new":null,"old":null}
-{"run_id":"1683710687-182342000","line":853,"new":{"module_name":"milli__search__new__matches__tests","snapshot_name":"partial_matches","metadata":{"source":"milli/src/search/new/matches/mod.rs","assertion_line":853,"expression":"matcher.format(format_options)"},"snapshot":"_the_ do or die can't be he do and or isn't he _thedoor_"},"old":{"module_name":"milli__search__new__matches__tests","metadata":{},"snapshot":"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_ _thedoor_"}}
-{"run_id":"1684141548-57871000","line":654,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":662,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":671,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":680,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":689,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":698,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":707,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":716,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":725,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":734,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":590,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":599,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":751,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":759,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":768,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":777,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":786,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":795,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":616,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":625,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":637,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":851,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":814,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":823,"new":null,"old":null}
-{"run_id":"1684141548-57871000","line":832,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":654,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":662,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":671,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":680,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":689,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":698,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":707,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":716,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":725,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":734,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":590,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":599,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":751,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":759,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":768,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":777,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":786,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":795,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":616,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":625,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":637,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":851,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":814,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":823,"new":null,"old":null}
-{"run_id":"1684141761-300166000","line":832,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":654,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":662,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":671,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":680,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":689,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":698,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":707,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":716,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":725,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":734,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":590,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":599,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":751,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":759,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":768,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":777,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":786,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":795,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":616,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":625,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":637,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":851,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":814,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":823,"new":null,"old":null}
-{"run_id":"1684227379-943236000","line":832,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":654,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":662,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":671,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":680,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":689,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":698,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":707,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":716,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":725,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":734,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":590,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":599,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":751,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":759,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":768,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":777,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":786,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":795,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":616,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":625,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":637,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":851,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":814,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":823,"new":null,"old":null}
-{"run_id":"1686671229-287954000","line":832,"new":null,"old":null}

milli/src/search/new/mod.rs

@@ -56,7 +56,6 @@ pub struct SearchContext<'ctx> {
     pub phrase_interner: DedupInterner<Phrase>,
     pub term_interner: Interner<QueryTerm>,
     pub phrase_docids: PhraseDocIdsCache,
-    pub restricted_fids: Option<Vec<u16>>,
 }
 
 impl<'ctx> SearchContext<'ctx> {
@@ -69,18 +68,8 @@ impl<'ctx> SearchContext<'ctx> {
             phrase_interner: <_>::default(),
             term_interner: <_>::default(),
             phrase_docids: <_>::default(),
-            restricted_fids: None,
         }
     }
-
-    pub fn searchable_attributes(&mut self, searchable_attributes: &'ctx [String]) -> Result<()> {
-        let fids_map = self.index.fields_ids_map(self.txn)?;
-        let restricted_fids =
-            searchable_attributes.iter().filter_map(|name| fids_map.id(name)).collect();
-        self.restricted_fids = Some(restricted_fids);
-
-        Ok(())
-    }
 }
 
 #[derive(Clone, Copy, PartialEq, PartialOrd, Ord, Eq)]

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

@@ -77,9 +77,13 @@ pub fn located_query_terms_from_tokens(
                 }
             }
             TokenKind::Separator(separator_kind) => {
-                // add penalty for hard separators
-                if let SeparatorKind::Hard = separator_kind {
-                    position = position.wrapping_add(7);
+                match separator_kind {
+                    SeparatorKind::Hard => {
+                        position += 1;
+                    }
+                    SeparatorKind::Soft => {
+                        position += 0;
+                    }
                 }
 
                 phrase = 'phrase: {
@@ -284,36 +288,3 @@ impl PhraseBuilder {
         })
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use charabia::TokenizerBuilder;
-
-    use super::*;
-    use crate::index::tests::TempIndex;
-
-    fn temp_index_with_documents() -> TempIndex {
-        let temp_index = TempIndex::new();
-        temp_index
-            .add_documents(documents!([
-                { "id": 1, "name": "split this world westfali westfalia the Ŵôřlḑôle" },
-                { "id": 2, "name": "Westfália" },
-                { "id": 3, "name": "Ŵôřlḑôle" },
-            ]))
-            .unwrap();
-        temp_index
-    }
-
-    #[test]
-    fn start_with_hard_separator() -> Result<()> {
-        let tokenizer = TokenizerBuilder::new().build();
-        let tokens = tokenizer.tokenize(".");
-        let index = temp_index_with_documents();
-        let rtxn = index.read_txn()?;
-        let mut ctx = SearchContext::new(&index, &rtxn);
-        // panics with `attempt to add with overflow` before <https://github.com/meilisearch/meilisearch/issues/3785>
-        let located_query_terms = located_query_terms_from_tokens(&mut ctx, tokens, None)?;
-        assert!(located_query_terms.is_empty());
-        Ok(())
-    }
-}

milli/src/snapshot_tests.rs

@@ -89,6 +89,7 @@ Create a snapshot test of the given database.
     - `exact_word_docids`
     - `word_prefix_docids`
     - `exact_word_prefix_docids`
+    - `docid_word_positions`
     - `word_pair_proximity_docids`
     - `word_prefix_pair_proximity_docids`
     - `word_position_docids`
@@ -216,6 +217,11 @@ pub fn snap_exact_word_prefix_docids(index: &Index) -> String {
         &format!("{s:<16} {}", display_bitmap(&b))
     })
 }
+pub fn snap_docid_word_positions(index: &Index) -> String {
+    make_db_snap_from_iter!(index, docid_word_positions, |((idx, s), b)| {
+        &format!("{idx:<6} {s:<16} {}", display_bitmap(&b))
+    })
+}
 pub fn snap_word_pair_proximity_docids(index: &Index) -> String {
     make_db_snap_from_iter!(index, word_pair_proximity_docids, |((proximity, word1, word2), b)| {
         &format!("{proximity:<2} {word1:<16} {word2:<16} {}", display_bitmap(&b))
@@ -471,6 +477,9 @@ macro_rules! full_snap_of_db {
     ($index:ident, exact_word_prefix_docids) => {{
         $crate::snapshot_tests::snap_exact_word_prefix_docids(&$index)
     }};
+    ($index:ident, docid_word_positions) => {{
+        $crate::snapshot_tests::snap_docid_word_positions(&$index)
+    }};
     ($index:ident, word_pair_proximity_docids) => {{
         $crate::snapshot_tests::snap_word_pair_proximity_docids(&$index)
     }};

milli/src/update/clear_documents.rs

@@ -23,6 +23,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
             exact_word_docids,
             word_prefix_docids,
             exact_word_prefix_docids,
+            docid_word_positions,
             word_pair_proximity_docids,
             word_prefix_pair_proximity_docids,
             prefix_word_pair_proximity_docids,
@@ -79,6 +80,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
         exact_word_docids.clear(self.wtxn)?;
         word_prefix_docids.clear(self.wtxn)?;
         exact_word_prefix_docids.clear(self.wtxn)?;
+        docid_word_positions.clear(self.wtxn)?;
         word_pair_proximity_docids.clear(self.wtxn)?;
         word_prefix_pair_proximity_docids.clear(self.wtxn)?;
         prefix_word_pair_proximity_docids.clear(self.wtxn)?;
@@ -139,6 +141,7 @@ mod tests {
 
         assert!(index.word_docids.is_empty(&rtxn).unwrap());
         assert!(index.word_prefix_docids.is_empty(&rtxn).unwrap());
+        assert!(index.docid_word_positions.is_empty(&rtxn).unwrap());
         assert!(index.word_pair_proximity_docids.is_empty(&rtxn).unwrap());
         assert!(index.field_id_word_count_docids.is_empty(&rtxn).unwrap());
         assert!(index.word_prefix_pair_proximity_docids.is_empty(&rtxn).unwrap());

milli/src/update/delete_documents.rs

@@ -1,5 +1,5 @@
 use std::collections::btree_map::Entry;
-use std::collections::{BTreeSet, HashMap, HashSet};
+use std::collections::{HashMap, HashSet};
 
 use fst::IntoStreamer;
 use heed::types::{ByteSlice, DecodeIgnore, Str, UnalignedSlice};
@@ -15,7 +15,8 @@ use crate::facet::FacetType;
 use crate::heed_codec::facet::FieldDocIdFacetCodec;
 use crate::heed_codec::CboRoaringBitmapCodec;
 use crate::{
-    ExternalDocumentsIds, FieldId, FieldIdMapMissingEntry, Index, Result, RoaringBitmapCodec, BEU32,
+    ExternalDocumentsIds, FieldId, FieldIdMapMissingEntry, Index, Result, RoaringBitmapCodec,
+    SmallString32, BEU32,
 };
 
 pub struct DeleteDocuments<'t, 'u, 'i> {
@@ -231,6 +232,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             exact_word_docids,
             word_prefix_docids,
             exact_word_prefix_docids,
+            docid_word_positions,
             word_pair_proximity_docids,
             field_id_word_count_docids,
             word_prefix_pair_proximity_docids,
@@ -249,9 +251,23 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             facet_id_is_empty_docids,
             documents,
         } = self.index;
-        // Remove from the documents database
+
+        // Retrieve the words contained in the documents.
+        let mut words = Vec::new();
         for docid in &self.to_delete_docids {
             documents.delete(self.wtxn, &BEU32::new(docid))?;
+
+            // We iterate through the words positions of the document id, retrieve the word and delete the positions.
+            // We create an iterator to be able to get the content and delete the key-value itself.
+            // It's faster to acquire a cursor to get and delete, as we avoid traversing the LMDB B-Tree two times but only once.
+            let mut iter = docid_word_positions.prefix_iter_mut(self.wtxn, &(docid, ""))?;
+            while let Some(result) = iter.next() {
+                let ((_docid, word), _positions) = result?;
+                // This boolean will indicate if we must remove this word from the words FST.
+                words.push((SmallString32::from(word), false));
+                // safety: we don't keep references from inside the LMDB database.
+                unsafe { iter.del_current()? };
+            }
         }
         // We acquire the current external documents ids map...
         // Note that its soft-deleted document ids field will be equal to the `to_delete_docids`
@@ -262,27 +278,42 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
         let new_external_documents_ids = new_external_documents_ids.into_static();
         self.index.put_external_documents_ids(self.wtxn, &new_external_documents_ids)?;
 
-        let mut words_to_keep = BTreeSet::default();
-        let mut words_to_delete = BTreeSet::default();
+        // Maybe we can improve the get performance of the words
+        // if we sort the words first, keeping the LMDB pages in cache.
+        words.sort_unstable();
+
         // We iterate over the words and delete the documents ids
         // from the word docids database.
-        remove_from_word_docids(
-            self.wtxn,
-            word_docids,
-            &self.to_delete_docids,
-            &mut words_to_keep,
-            &mut words_to_delete,
-        )?;
-        remove_from_word_docids(
-            self.wtxn,
-            exact_word_docids,
-            &self.to_delete_docids,
-            &mut words_to_keep,
-            &mut words_to_delete,
-        )?;
+        for (word, must_remove) in &mut words {
+            remove_from_word_docids(
+                self.wtxn,
+                word_docids,
+                word.as_str(),
+                must_remove,
+                &self.to_delete_docids,
+            )?;
+
+            remove_from_word_docids(
+                self.wtxn,
+                exact_word_docids,
+                word.as_str(),
+                must_remove,
+                &self.to_delete_docids,
+            )?;
+        }
 
         // We construct an FST set that contains the words to delete from the words FST.
-        let words_to_delete = fst::Set::from_iter(words_to_delete.difference(&words_to_keep))?;
+        let words_to_delete =
+            words.iter().filter_map(
+                |(word, must_remove)| {
+                    if *must_remove {
+                        Some(word.as_str())
+                    } else {
+                        None
+                    }
+                },
+            );
+        let words_to_delete = fst::Set::from_iter(words_to_delete)?;
 
         let new_words_fst = {
             // We retrieve the current words FST from the database.
@@ -501,24 +532,23 @@ fn remove_from_word_prefix_docids(
 fn remove_from_word_docids(
     txn: &mut heed::RwTxn,
     db: &heed::Database<Str, RoaringBitmapCodec>,
+    word: &str,
+    must_remove: &mut bool,
     to_remove: &RoaringBitmap,
-    words_to_keep: &mut BTreeSet<String>,
-    words_to_remove: &mut BTreeSet<String>,
 ) -> Result<()> {
     // We create an iterator to be able to get the content and delete the word docids.
     // It's faster to acquire a cursor to get and delete or put, as we avoid traversing
     // the LMDB B-Tree two times but only once.
-    let mut iter = db.iter_mut(txn)?;
-    while let Some((key, mut docids)) = iter.next().transpose()? {
-        let previous_len = docids.len();
-        docids -= to_remove;
-        if docids.is_empty() {
-            // safety: we don't keep references from inside the LMDB database.
-            unsafe { iter.del_current()? };
-            words_to_remove.insert(key.to_owned());
-        } else {
-            words_to_keep.insert(key.to_owned());
-            if docids.len() != previous_len {
+    let mut iter = db.prefix_iter_mut(txn, word)?;
+    if let Some((key, mut docids)) = iter.next().transpose()? {
+        if key == word {
+            let previous_len = docids.len();
+            docids -= to_remove;
+            if docids.is_empty() {
+                // safety: we don't keep references from inside the LMDB database.
+                unsafe { iter.del_current()? };
+                *must_remove = true;
+            } else if docids.len() != previous_len {
                 let key = key.to_owned();
                 // safety: we don't keep references from inside the LMDB database.
                 unsafe { iter.put_current(&key, &docids)? };
@@ -597,7 +627,7 @@ mod tests {
 
     use super::*;
     use crate::index::tests::TempIndex;
-    use crate::{db_snap, Filter, Search};
+    use crate::{db_snap, Filter};
 
     fn delete_documents<'t>(
         wtxn: &mut RwTxn<'t, '_>,
@@ -1169,52 +1199,4 @@ mod tests {
             DeletionStrategy::AlwaysSoft,
         );
     }
-
-    #[test]
-    fn delete_words_exact_attributes() {
-        let index = TempIndex::new();
-
-        index
-            .update_settings(|settings| {
-                settings.set_primary_key(S("id"));
-                settings.set_searchable_fields(vec![S("text"), S("exact")]);
-                settings.set_exact_attributes(vec![S("exact")].into_iter().collect());
-            })
-            .unwrap();
-
-        index
-            .add_documents(documents!([
-                { "id": 0, "text": "hello" },
-                { "id": 1, "exact": "hello"}
-            ]))
-            .unwrap();
-        db_snap!(index, word_docids, 1, @r###"
-        hello            [0, ]
-        "###);
-        db_snap!(index, exact_word_docids, 1, @r###"
-        hello            [1, ]
-        "###);
-        db_snap!(index, words_fst, 1, @"300000000000000001084cfcfc2ce1000000016000000090ea47f");
-
-        let mut wtxn = index.write_txn().unwrap();
-        let deleted_internal_ids =
-            delete_documents(&mut wtxn, &index, &["1"], DeletionStrategy::AlwaysHard);
-        wtxn.commit().unwrap();
-
-        db_snap!(index, word_docids, 2, @r###"
-        hello            [0, ]
-        "###);
-        db_snap!(index, exact_word_docids, 2, @"");
-        db_snap!(index, words_fst, 2, @"300000000000000001084cfcfc2ce1000000016000000090ea47f");
-
-        insta::assert_snapshot!(format!("{deleted_internal_ids:?}"), @"[1]");
-        let txn = index.read_txn().unwrap();
-        let words = index.words_fst(&txn).unwrap().into_stream().into_strs().unwrap();
-        insta::assert_snapshot!(format!("{words:?}"), @r###"["hello"]"###);
-
-        let mut s = Search::new(&txn, &index);
-        s.query("hello");
-        let crate::SearchResult { documents_ids, .. } = s.execute().unwrap();
-        insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0]");
-    }
 }

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;
+use std::{cmp, io};
 
 use grenad::Sorter;
 
@@ -54,10 +54,11 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
         }
 
         for position in read_u32_ne_bytes(value) {
-            let (field_id, _) = relative_from_absolute_position(position);
+            let (field_id, position) = relative_from_absolute_position(position);
+            let word_count = position as u32 + 1;
 
             let value = document_fid_wordcount.entry(field_id as FieldId).or_insert(0);
-            *value += 1;
+            *value = cmp::max(*value, word_count);
         }
     }
 
@@ -82,7 +83,7 @@ fn drain_document_fid_wordcount_into_sorter(
     let mut key_buffer = Vec::new();
 
     for (fid, count) in document_fid_wordcount.drain() {
-        if count <= 30 {
+        if count <= 10 {
             key_buffer.clear();
             key_buffer.extend_from_slice(&fid.to_be_bytes());
             key_buffer.push(count as u8);

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

@@ -325,6 +325,8 @@ fn send_and_extract_flattened_documents_data(
                 // send docid_word_positions_chunk to DB writer
                 let docid_word_positions_chunk =
                     unsafe { as_cloneable_grenad(&docid_word_positions_chunk)? };
+                let _ = lmdb_writer_sx
+                    .send(Ok(TypedChunk::DocidWordPositions(docid_word_positions_chunk.clone())));
 
                 let _ =
                     lmdb_writer_sx.send(Ok(TypedChunk::ScriptLanguageDocids(script_language_pair)));

milli/src/update/index_documents/helpers/merge_functions.rs

@@ -4,6 +4,7 @@ use std::result::Result as StdResult;
 
 use roaring::RoaringBitmap;
 
+use super::read_u32_ne_bytes;
 use crate::heed_codec::CboRoaringBitmapCodec;
 use crate::update::index_documents::transform::Operation;
 use crate::Result;
@@ -21,6 +22,10 @@ pub fn concat_u32s_array<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Result<Co
     }
 }
 
+pub fn roaring_bitmap_from_u32s_array(slice: &[u8]) -> RoaringBitmap {
+    read_u32_ne_bytes(slice).collect()
+}
+
 pub fn serialize_roaring_bitmap(bitmap: &RoaringBitmap, buffer: &mut Vec<u8>) -> io::Result<()> {
     buffer.clear();
     buffer.reserve(bitmap.serialized_size());

milli/src/update/index_documents/helpers/mod.rs

@@ -14,8 +14,8 @@ pub use grenad_helpers::{
 };
 pub use merge_functions::{
     concat_u32s_array, keep_first, keep_latest_obkv, merge_cbo_roaring_bitmaps,
-    merge_obkvs_and_operations, merge_roaring_bitmaps, merge_two_obkvs, serialize_roaring_bitmap,
-    MergeFn,
+    merge_obkvs_and_operations, merge_roaring_bitmaps, merge_two_obkvs,
+    roaring_bitmap_from_u32s_array, serialize_roaring_bitmap, MergeFn,
 };
 
 use crate::MAX_WORD_LENGTH;

milli/src/update/index_documents/mod.rs

@@ -2471,11 +2471,11 @@ mod tests {
               {
                 "id": 3,
                 "text": "a a a a a a a a a a a a a a a a a
-                a a a a a a a a a a a a a a a a a a a a a a a a a a
-                a a a a a a a a a a a a a a a a a a a a a a a a a a
-                a a a a a a a a a a a a a a a a a a a a a a a a a a
-                a a a a a a a a a a a a a a a a a a a a a a a a a a
-                a a a a a a a a a a a a a a a a a a a a a a a a a a
+                a a a a a a a a a a a a a a a a a a a a a a a a a a 
+                a a a a a a a a a a a a a a a a a a a a a a a a a a 
+                a a a a a a a a a a a a a a a a a a a a a a a a a a 
+                a a a a a a a a a a a a a a a a a a a a a a a a a a 
+                a a a a a a a a a a a a a a a a a a a a a a a a a a 
                 a a a a a a a a a a a a a a a a a a a a a "
              }
             ]))
@@ -2513,5 +2513,6 @@ mod tests {
 
         db_snap!(index, word_fid_docids, 3, @"4c2e2a1832e5802796edc1638136d933");
         db_snap!(index, word_position_docids, 3, @"74f556b91d161d997a89468b4da1cb8f");
+        db_snap!(index, docid_word_positions, 3, @"5287245332627675740b28bd46e1cde1");
     }
 }

milli/src/update/index_documents/typed_chunk.rs

@@ -7,19 +7,24 @@ use std::io;
 use charabia::{Language, Script};
 use grenad::MergerBuilder;
 use heed::types::ByteSlice;
-use heed::RwTxn;
+use heed::{BytesDecode, RwTxn};
 use roaring::RoaringBitmap;
 
 use super::helpers::{
-    self, merge_ignore_values, serialize_roaring_bitmap, valid_lmdb_key, CursorClonableMmap,
+    self, merge_ignore_values, roaring_bitmap_from_u32s_array, serialize_roaring_bitmap,
+    valid_lmdb_key, CursorClonableMmap,
 };
 use super::{ClonableMmap, MergeFn};
 use crate::facet::FacetType;
 use crate::update::facet::FacetsUpdate;
 use crate::update::index_documents::helpers::as_cloneable_grenad;
-use crate::{lat_lng_to_xyz, CboRoaringBitmapCodec, DocumentId, GeoPoint, Index, Result};
+use crate::{
+    lat_lng_to_xyz, BoRoaringBitmapCodec, CboRoaringBitmapCodec, DocumentId, GeoPoint, Index,
+    Result,
+};
 
 pub(crate) enum TypedChunk {
+    DocidWordPositions(grenad::Reader<CursorClonableMmap>),
     FieldIdDocidFacetStrings(grenad::Reader<CursorClonableMmap>),
     FieldIdDocidFacetNumbers(grenad::Reader<CursorClonableMmap>),
     Documents(grenad::Reader<CursorClonableMmap>),
@@ -51,6 +56,29 @@ pub(crate) fn write_typed_chunk_into_index(
 ) -> Result<(RoaringBitmap, bool)> {
     let mut is_merged_database = false;
     match typed_chunk {
+        TypedChunk::DocidWordPositions(docid_word_positions_iter) => {
+            write_entries_into_database(
+                docid_word_positions_iter,
+                &index.docid_word_positions,
+                wtxn,
+                index_is_empty,
+                |value, buffer| {
+                    // ensure that values are unique and ordered
+                    let positions = roaring_bitmap_from_u32s_array(value);
+                    BoRoaringBitmapCodec::serialize_into(&positions, buffer);
+                    Ok(buffer)
+                },
+                |new_values, db_values, buffer| {
+                    let new_values = roaring_bitmap_from_u32s_array(new_values);
+                    let positions = match BoRoaringBitmapCodec::bytes_decode(db_values) {
+                        Some(db_values) => new_values | db_values,
+                        None => new_values, // should not happen
+                    };
+                    BoRoaringBitmapCodec::serialize_into(&positions, buffer);
+                    Ok(())
+                },
+            )?;
+        }
         TypedChunk::Documents(obkv_documents_iter) => {
             let mut cursor = obkv_documents_iter.into_cursor()?;
             while let Some((key, value)) = cursor.move_on_next()? {

milli/src/update/mod.rs

@@ -4,8 +4,7 @@ pub use self::delete_documents::{DeleteDocuments, DeletionStrategy, DocumentDele
 pub use self::facet::bulk::FacetsUpdateBulk;
 pub use self::facet::incremental::FacetsUpdateIncrementalInner;
 pub use self::index_documents::{
-    merge_cbo_roaring_bitmaps, merge_roaring_bitmaps, DocumentAdditionResult, DocumentId,
-    IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, MergeFn,
+    DocumentAdditionResult, DocumentId, IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod,
 };
 pub use self::indexer_config::IndexerConfig;
 pub use self::prefix_word_pairs::{

milli/src/update/settings.rs

@@ -14,7 +14,7 @@ use crate::error::UserError;
 use crate::index::{DEFAULT_MIN_WORD_LEN_ONE_TYPO, DEFAULT_MIN_WORD_LEN_TWO_TYPOS};
 use crate::update::index_documents::IndexDocumentsMethod;
 use crate::update::{IndexDocuments, UpdateIndexingStep};
-use crate::{FieldsIdsMap, Index, Result};
+use crate::{FieldsIdsMap, Index, OrderBy, Result};
 
 #[derive(Debug, Clone, PartialEq, Eq, Copy)]
 pub enum Setting<T> {
@@ -122,6 +122,7 @@ pub struct Settings<'a, 't, 'u, 'i> {
     /// Attributes on which typo tolerance is disabled.
     exact_attributes: Setting<HashSet<String>>,
     max_values_per_facet: Setting<usize>,
+    sort_facet_values_by: Setting<HashMap<String, OrderBy>>,
     pagination_max_total_hits: Setting<usize>,
 }
 
@@ -149,6 +150,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
             min_word_len_one_typo: Setting::NotSet,
             exact_attributes: Setting::NotSet,
             max_values_per_facet: Setting::NotSet,
+            sort_facet_values_by: Setting::NotSet,
             pagination_max_total_hits: Setting::NotSet,
             indexer_config,
         }
@@ -275,6 +277,14 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         self.max_values_per_facet = Setting::Reset;
     }
 
+    pub fn set_sort_facet_values_by(&mut self, value: HashMap<String, OrderBy>) {
+        self.sort_facet_values_by = Setting::Set(value);
+    }
+
+    pub fn reset_sort_facet_values_by(&mut self) {
+        self.sort_facet_values_by = Setting::Reset;
+    }
+
     pub fn set_pagination_max_total_hits(&mut self, value: usize) {
         self.pagination_max_total_hits = Setting::Set(value);
     }
@@ -680,6 +690,20 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         Ok(())
     }
 
+    fn update_sort_facet_values_by(&mut self) -> Result<()> {
+        match self.sort_facet_values_by.as_ref() {
+            Setting::Set(value) => {
+                self.index.put_sort_facet_values_by(self.wtxn, value)?;
+            }
+            Setting::Reset => {
+                self.index.delete_sort_facet_values_by(self.wtxn)?;
+            }
+            Setting::NotSet => (),
+        }
+
+        Ok(())
+    }
+
     fn update_pagination_max_total_hits(&mut self) -> Result<()> {
         match self.pagination_max_total_hits {
             Setting::Set(max) => {
@@ -714,6 +738,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         self.update_min_typo_word_len()?;
         self.update_exact_words()?;
         self.update_max_values_per_facet()?;
+        self.update_sort_facet_values_by()?;
         self.update_pagination_max_total_hits()?;
 
         // If there is new faceted fields we indicate that we must reindex as we must
@@ -1515,6 +1540,7 @@ mod tests {
                     exact_words,
                     exact_attributes,
                     max_values_per_facet,
+                    sort_facet_values_by,
                     pagination_max_total_hits,
                 } = settings;
                 assert!(matches!(searchable_fields, Setting::NotSet));
@@ -1532,6 +1558,7 @@ mod tests {
                 assert!(matches!(exact_words, Setting::NotSet));
                 assert!(matches!(exact_attributes, Setting::NotSet));
                 assert!(matches!(max_values_per_facet, Setting::NotSet));
+                assert!(matches!(sort_facet_values_by, Setting::NotSet));
                 assert!(matches!(pagination_max_total_hits, Setting::NotSet));
             })
             .unwrap();

milli/tests/search/facet_distribution.rs

@@ -5,7 +5,7 @@ use heed::EnvOpenOptions;
 use maplit::hashset;
 use milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
-use milli::{FacetDistribution, Index, Object};
+use milli::{FacetDistribution, Index, Object, OrderBy};
 use serde_json::Deserializer;
 
 #[test]
@@ -63,12 +63,12 @@ fn test_facet_distribution_with_no_facet_values() {
 
     let txn = index.read_txn().unwrap();
     let mut distrib = FacetDistribution::new(&txn, &index);
-    distrib.facets(vec!["genres"]);
+    distrib.facets(vec![("genres", OrderBy::default())]);
     let result = distrib.execute().unwrap();
     assert_eq!(result["genres"].len(), 0);
 
     let mut distrib = FacetDistribution::new(&txn, &index);
-    distrib.facets(vec!["tags"]);
+    distrib.facets(vec![("tags", OrderBy::default())]);
     let result = distrib.execute().unwrap();
     assert_eq!(result["tags"].len(), 2);
 }