Use the minWordSizeForTypos index 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
 
@@ -22,7 +17,7 @@ jobs:
     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: ${{ env.MEILI_NO_ANALYTICS }}
@@ -56,7 +51,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -82,7 +77,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -112,7 +107,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -136,7 +131,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -144,7 +139,7 @@ jobs:
           - '7700:7700'
     steps:
       - name: Set up Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v3
         with:
           go-version: stable
       - uses: actions/checkout@v3
@@ -165,7 +160,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
+        image: getmeili/meilisearch:nightly
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -189,7 +184,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ 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

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>

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> {

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

@@ -239,8 +239,11 @@ InvalidSearchMatchingStrategy         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchOffset                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
+InvalidFacetSearchQuery               , InvalidRequest       , BAD_REQUEST ;
+InvalidFacetSearchName                , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchFacet                    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
@@ -330,6 +333,7 @@ impl ErrorCode for milli::Error {
                     UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
                     UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
                     UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
+                    UserError::InvalidSearchFacet { .. } => Code::InvalidSearchFacet,
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::SortError(_) => Code::InvalidSearchSort,

meilisearch/src/analytics/mock_analytics.rs

@@ -38,6 +38,18 @@ impl MultiSearchAggregator {
     pub fn succeed(&mut self) {}
 }
 
+#[derive(Default)]
+pub struct FacetSearchAggregator;
+
+#[allow(dead_code)]
+impl FacetSearchAggregator {
+    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
+        Self::default()
+    }
+
+    pub fn succeed(&mut self, _: &dyn Any) {}
+}
+
 impl MockAnalytics {
     #[allow(clippy::new_ret_no_self)]
     pub fn new(opt: &Opt) -> Arc<dyn Analytics> {
@@ -56,6 +68,7 @@ impl Analytics for MockAnalytics {
     fn get_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
+    fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
     fn add_documents(
         &self,
         _documents_query: &UpdateDocumentsQuery,

meilisearch/src/analytics/mod.rs

@@ -25,6 +25,8 @@ pub type SegmentAnalytics = mock_analytics::MockAnalytics;
 pub type SearchAggregator = mock_analytics::SearchAggregator;
 #[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
+pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
 // if we are in release mode and the feature analytics was enabled
 // we use the real analytics
@@ -34,6 +36,8 @@ pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
 pub type SearchAggregator = segment_analytics::SearchAggregator;
 #[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
 
 /// The Meilisearch config dir:
 /// `~/.config/Meilisearch` on *NIX or *BSD.
@@ -88,6 +92,9 @@ pub trait Analytics: Sync + Send {
     /// This method should be called to aggregate a post array of searches
     fn post_multi_search(&self, aggregate: MultiSearchAggregator);
 
+    /// This method should be called to aggregate post facet values searches
+    fn post_facet_search(&self, aggregate: FacetSearchAggregator);
+
     // this method should be called to aggregate a add documents request
     fn add_documents(
         &self,

meilisearch/src/analytics/segment_analytics.rs

@@ -1,5 +1,6 @@
 use std::collections::{BinaryHeap, HashMap, HashSet};
 use std::fs;
+use std::mem::take;
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::time::{Duration, Instant};
@@ -29,11 +30,13 @@ use super::{
 use crate::analytics::Analytics;
 use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
+use crate::routes::indexes::facet_search::FacetSearchQuery;
 use crate::routes::tasks::TasksFilterQuery;
 use crate::routes::{create_all_stats, Stats};
 use crate::search::{
-    SearchQuery, SearchQueryWithIndex, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
-    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
+    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
 };
 use crate::Opt;
 
@@ -71,6 +74,7 @@ pub enum AnalyticsMsg {
     AggregateGetSearch(SearchAggregator),
     AggregatePostSearch(SearchAggregator),
     AggregatePostMultiSearch(MultiSearchAggregator),
+    AggregatePostFacetSearch(FacetSearchAggregator),
     AggregateAddDocuments(DocumentsAggregator),
     AggregateDeleteDocuments(DocumentsDeletionAggregator),
     AggregateUpdateDocuments(DocumentsAggregator),
@@ -139,6 +143,7 @@ impl SegmentAnalytics {
             batcher,
             post_search_aggregator: SearchAggregator::default(),
             post_multi_search_aggregator: MultiSearchAggregator::default(),
+            post_facet_search_aggregator: FacetSearchAggregator::default(),
             get_search_aggregator: SearchAggregator::default(),
             add_documents_aggregator: DocumentsAggregator::default(),
             delete_documents_aggregator: DocumentsDeletionAggregator::default(),
@@ -182,6 +187,10 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
     }
 
+    fn post_facet_search(&self, aggregate: FacetSearchAggregator) {
+        let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFacetSearch(aggregate));
+    }
+
     fn post_multi_search(&self, aggregate: MultiSearchAggregator) {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostMultiSearch(aggregate));
     }
@@ -354,6 +363,7 @@ pub struct Segment {
     get_search_aggregator: SearchAggregator,
     post_search_aggregator: SearchAggregator,
     post_multi_search_aggregator: MultiSearchAggregator,
+    post_facet_search_aggregator: FacetSearchAggregator,
     add_documents_aggregator: DocumentsAggregator,
     delete_documents_aggregator: DocumentsDeletionAggregator,
     update_documents_aggregator: DocumentsAggregator,
@@ -418,6 +428,7 @@ impl Segment {
                         Some(AnalyticsMsg::AggregateGetSearch(agreg)) => self.get_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostSearch(agreg)) => self.post_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostMultiSearch(agreg)) => self.post_multi_search_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregatePostFacetSearch(agreg)) => self.post_facet_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
@@ -461,55 +472,72 @@ impl Segment {
                 })
                 .await;
         }
-        let get_search = std::mem::take(&mut self.get_search_aggregator)
-            .into_event(&self.user, "Documents Searched GET");
-        let post_search = std::mem::take(&mut self.post_search_aggregator)
-            .into_event(&self.user, "Documents Searched POST");
-        let post_multi_search = std::mem::take(&mut self.post_multi_search_aggregator)
-            .into_event(&self.user, "Documents Searched by Multi-Search POST");
-        let add_documents = std::mem::take(&mut self.add_documents_aggregator)
-            .into_event(&self.user, "Documents Added");
-        let delete_documents = std::mem::take(&mut self.delete_documents_aggregator)
-            .into_event(&self.user, "Documents Deleted");
-        let update_documents = std::mem::take(&mut self.update_documents_aggregator)
-            .into_event(&self.user, "Documents Updated");
-        let get_fetch_documents = std::mem::take(&mut self.get_fetch_documents_aggregator)
-            .into_event(&self.user, "Documents Fetched GET");
-        let post_fetch_documents = std::mem::take(&mut self.post_fetch_documents_aggregator)
-            .into_event(&self.user, "Documents Fetched POST");
-        let get_tasks =
-            std::mem::take(&mut self.get_tasks_aggregator).into_event(&self.user, "Tasks Seen");
-        let health =
-            std::mem::take(&mut self.health_aggregator).into_event(&self.user, "Health Seen");
 
-        if let Some(get_search) = get_search {
+        let Segment {
+            inbox: _,
+            opt: _,
+            batcher: _,
+            user,
+            get_search_aggregator,
+            post_search_aggregator,
+            post_multi_search_aggregator,
+            post_facet_search_aggregator,
+            add_documents_aggregator,
+            delete_documents_aggregator,
+            update_documents_aggregator,
+            get_fetch_documents_aggregator,
+            post_fetch_documents_aggregator,
+            get_tasks_aggregator,
+            health_aggregator,
+        } = self;
+
+        if let Some(get_search) =
+            take(get_search_aggregator).into_event(&user, "Documents Searched GET")
+        {
             let _ = self.batcher.push(get_search).await;
         }
-        if let Some(post_search) = post_search {
+        if let Some(post_search) =
+            take(post_search_aggregator).into_event(&user, "Documents Searched POST")
+        {
             let _ = self.batcher.push(post_search).await;
         }
-        if let Some(post_multi_search) = post_multi_search {
+        if let Some(post_multi_search) = take(post_multi_search_aggregator)
+            .into_event(&user, "Documents Searched by Multi-Search POST")
+        {
             let _ = self.batcher.push(post_multi_search).await;
         }
-        if let Some(add_documents) = add_documents {
+        if let Some(post_facet_search) = take(post_facet_search_aggregator)
+            .into_event(&user, "Documents Searched by Facet-Search POST")
+        {
+            let _ = self.batcher.push(post_facet_search).await;
+        }
+        if let Some(add_documents) =
+            take(add_documents_aggregator).into_event(&user, "Documents Added")
+        {
             let _ = self.batcher.push(add_documents).await;
         }
-        if let Some(delete_documents) = delete_documents {
+        if let Some(delete_documents) =
+            take(delete_documents_aggregator).into_event(&user, "Documents Deleted")
+        {
             let _ = self.batcher.push(delete_documents).await;
         }
-        if let Some(update_documents) = update_documents {
+        if let Some(update_documents) =
+            take(update_documents_aggregator).into_event(&user, "Documents Updated")
+        {
             let _ = self.batcher.push(update_documents).await;
         }
-        if let Some(get_fetch_documents) = get_fetch_documents {
+        if let Some(get_fetch_documents) =
+            take(get_fetch_documents_aggregator).into_event(&user, "Documents Fetched GET") {
             let _ = self.batcher.push(get_fetch_documents).await;
         }
-        if let Some(post_fetch_documents) = post_fetch_documents {
+        if let Some(post_fetch_documents) =
+            take(post_fetch_documents_aggregator).into_event(&user, "Documents Fetched POST") {
             let _ = self.batcher.push(post_fetch_documents).await;
         }
-        if let Some(get_tasks) = get_tasks {
+        if let Some(get_tasks) = take(get_tasks_aggregator).into_event(&user, "Tasks Seen") {
             let _ = self.batcher.push(get_tasks).await;
         }
-        if let Some(health) = health {
+        if let Some(health) = take(health_aggregator).into_event(&user, "Health Seen") {
             let _ = self.batcher.push(health).await;
         }
         let _ = self.batcher.flush().await;
@@ -886,6 +914,144 @@ impl MultiSearchAggregator {
     }
 }
 
+#[derive(Default)]
+pub struct FacetSearchAggregator {
+    timestamp: Option<OffsetDateTime>,
+
+    // context
+    user_agents: HashSet<String>,
+
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // The set of all facetNames that were used
+    facet_names: HashSet<String>,
+
+    // As there been any other parameter than the facetName or facetQuery ones?
+    additional_search_parameters_provided: bool,
+}
+
+impl FacetSearchAggregator {
+    pub fn from_query(query: &FacetSearchQuery, request: &HttpRequest) -> Self {
+        let FacetSearchQuery {
+            facet_query: _,
+            facet_name,
+            q,
+            offset,
+            limit,
+            page,
+            hits_per_page,
+            attributes_to_retrieve,
+            attributes_to_crop,
+            crop_length,
+            attributes_to_highlight,
+            show_matches_position,
+            filter,
+            sort,
+            facets,
+            highlight_pre_tag,
+            highlight_post_tag,
+            crop_marker,
+            matching_strategy,
+        } = query;
+
+        let mut ret = Self::default();
+        ret.timestamp = Some(OffsetDateTime::now_utc());
+
+        ret.total_received = 1;
+        ret.user_agents = extract_user_agents(request).into_iter().collect();
+        ret.facet_names = Some(facet_name.clone()).into_iter().collect();
+
+        ret.additional_search_parameters_provided = q.is_some()
+            || *offset != DEFAULT_SEARCH_OFFSET()
+            || *limit != DEFAULT_SEARCH_LIMIT()
+            || page.is_some()
+            || hits_per_page.is_some()
+            || attributes_to_retrieve.is_some()
+            || attributes_to_crop.is_some()
+            || *crop_length != DEFAULT_CROP_LENGTH()
+            || attributes_to_highlight.is_some()
+            || *show_matches_position
+            || filter.is_some()
+            || sort.is_some()
+            || facets.is_some()
+            || *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG()
+            || *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG()
+            || *crop_marker != DEFAULT_CROP_MARKER()
+            || *matching_strategy != MatchingStrategy::default();
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &FacetSearchResult) {
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+        self.time_spent.push(result.processing_time_ms as usize);
+    }
+
+    /// Aggregate one [SearchAggregator] into another.
+    pub fn aggregate(&mut self, mut other: Self) {
+        if self.timestamp.is_none() {
+            self.timestamp = other.timestamp;
+        }
+
+        // context
+        for user_agent in other.user_agents.into_iter() {
+            self.user_agents.insert(user_agent);
+        }
+
+        // request
+        self.total_received = self.total_received.saturating_add(other.total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(other.total_succeeded);
+        self.time_spent.append(&mut other.time_spent);
+
+        // facet_names
+        for facet_name in other.facet_names.into_iter() {
+            self.facet_names.insert(facet_name);
+        }
+
+        // additional_search_parameters_provided
+        self.additional_search_parameters_provided = self.additional_search_parameters_provided
+            | other.additional_search_parameters_provided;
+    }
+
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
+        if self.total_received == 0 {
+            None
+        } else {
+            // the index of the 99th percentage of value
+            let percentile_99th = 0.99 * (self.total_succeeded as f64 - 1.) + 1.;
+            // we get all the values in a sorted manner
+            let time_spent = self.time_spent.into_sorted_vec();
+            // We are only interested by the slowest value of the 99th fastest results
+            let time_spent = time_spent.get(percentile_99th as usize);
+
+            let properties = json!({
+                "user-agent": self.user_agents,
+                "requests": {
+                    "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
+                    "total_succeeded": self.total_succeeded,
+                    "total_failed": self.total_received.saturating_sub(self.total_succeeded), // just to be sure we never panics
+                    "total_received": self.total_received,
+                },
+                "facets": {
+                    "total_distinct_facet_count": self.facet_names.len(),
+                },
+                "additional_search_parameters_provided": self.additional_search_parameters_provided,
+            });
+
+            Some(Track {
+                timestamp: self.timestamp,
+                user: user.clone(),
+                event: event_name.to_string(),
+                properties,
+                ..Default::default()
+            })
+        }
+    }
+}
+
 #[derive(Default)]
 pub struct DocumentsAggregator {
     timestamp: Option<OffsetDateTime>,

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/facet_search.rs

@@ -0,0 +1,133 @@
+use std::collections::{BTreeSet, HashSet};
+
+use actix_web::web::Data;
+use actix_web::{web, HttpRequest, HttpResponse};
+use deserr::actix_web::AwebJson;
+use index_scheduler::IndexScheduler;
+use log::debug;
+use meilisearch_types::deserr::DeserrJsonError;
+use meilisearch_types::error::deserr_codes::*;
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::index_uid::IndexUid;
+use serde_json::Value;
+
+use crate::analytics::{Analytics, FacetSearchAggregator};
+use crate::extractors::authentication::policies::*;
+use crate::extractors::authentication::GuardedData;
+use crate::search::{
+    add_search_rules, perform_facet_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
+    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
+    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+};
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(web::resource("").route(web::post().to(search)));
+}
+
+// TODO improve the error messages
+#[derive(Debug, Clone, Default, PartialEq, Eq, deserr::Deserr)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct FacetSearchQuery {
+    #[deserr(default, error = DeserrJsonError<InvalidFacetSearchQuery>)]
+    pub facet_query: Option<String>,
+    #[deserr(error = DeserrJsonError<InvalidFacetSearchName>)]
+    pub facet_name: String,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
+    pub q: Option<String>,
+    #[deserr(default = DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
+    pub offset: usize,
+    #[deserr(default = DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSearchLimit>)]
+    pub limit: usize,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchPage>)]
+    pub page: Option<usize>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchHitsPerPage>)]
+    pub hits_per_page: Option<usize>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToRetrieve>)]
+    pub attributes_to_retrieve: Option<BTreeSet<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToCrop>)]
+    pub attributes_to_crop: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchCropLength>, default = DEFAULT_CROP_LENGTH())]
+    pub crop_length: usize,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToHighlight>)]
+    pub attributes_to_highlight: Option<HashSet<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchShowMatchesPosition>, default)]
+    pub show_matches_position: bool,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
+    pub filter: Option<Value>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchSort>)]
+    pub sort: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchFacets>)]
+    pub facets: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPreTag>, default = DEFAULT_HIGHLIGHT_PRE_TAG())]
+    pub highlight_pre_tag: String,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchHighlightPostTag>, default = DEFAULT_HIGHLIGHT_POST_TAG())]
+    pub highlight_post_tag: String,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchCropMarker>, default = DEFAULT_CROP_MARKER())]
+    pub crop_marker: String,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
+    pub matching_strategy: MatchingStrategy,
+}
+
+pub async fn search(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebJson<FacetSearchQuery, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let query = params.into_inner();
+    debug!("facet search called with params: {:?}", query);
+
+    let mut aggregate = FacetSearchAggregator::from_query(&query, &req);
+
+    let facet_query = query.facet_query.clone();
+    let facet_name = query.facet_name.clone();
+    let mut search_query = SearchQuery::from(query);
+
+    // Tenant token search_rules.
+    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
+        add_search_rules(&mut search_query, search_rules);
+    }
+
+    let index = index_scheduler.index(&index_uid)?;
+    let search_result = tokio::task::spawn_blocking(move || {
+        perform_facet_search(&index, search_query, facet_query, facet_name)
+    })
+    .await?;
+
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.post_facet_search(aggregate);
+
+    let search_result = search_result?;
+
+    debug!("returns: {:?}", search_result);
+    Ok(HttpResponse::Ok().json(search_result))
+}
+
+impl From<FacetSearchQuery> for SearchQuery {
+    fn from(value: FacetSearchQuery) -> Self {
+        SearchQuery {
+            q: value.q,
+            offset: value.offset,
+            limit: value.limit,
+            page: value.page,
+            hits_per_page: value.hits_per_page,
+            attributes_to_retrieve: value.attributes_to_retrieve,
+            attributes_to_crop: value.attributes_to_crop,
+            crop_length: value.crop_length,
+            attributes_to_highlight: value.attributes_to_highlight,
+            show_matches_position: value.show_matches_position,
+            filter: value.filter,
+            sort: value.sort,
+            facets: value.facets,
+            highlight_pre_tag: value.highlight_pre_tag,
+            highlight_post_tag: value.highlight_post_tag,
+            crop_marker: value.crop_marker,
+            matching_strategy: value.matching_strategy,
+        }
+    }
+}

meilisearch/src/routes/indexes/mod.rs

@@ -24,6 +24,7 @@ use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
 
 pub mod documents;
+pub mod facet_search;
 pub mod search;
 pub mod settings;
 
@@ -44,6 +45,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::resource("/stats").route(web::get().to(SeqHandler(get_index_stats))))
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
+            .service(web::scope("/facet-search").configure(facet_search::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }

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/search.rs

@@ -8,7 +8,9 @@ use either::Either;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
+use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::milli::{FacetValueHit, SearchForFacetValues};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::TokenizerBuilder;
@@ -170,7 +172,7 @@ impl SearchQueryWithIndex {
     }
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Deserr)]
+#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr)]
 #[deserr(rename_all = camelCase)]
 pub enum MatchingStrategy {
     /// Remove query words from last to first
@@ -241,6 +243,14 @@ pub struct FacetStats {
     pub max: f64,
 }
 
+#[derive(Serialize, Debug, Clone, PartialEq)]
+#[serde(rename_all = "camelCase")]
+pub struct FacetSearchResult {
+    pub hits: Vec<FacetValueHit>,
+    pub query: Option<String>,
+    pub processing_time_ms: u128,
+}
+
 /// Incorporate search rules in search query
 pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
     query.filter = match (query.filter.take(), rules.filter) {
@@ -261,14 +271,12 @@ pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
     }
 }
 
-pub fn perform_search(
-    index: &Index,
-    query: SearchQuery,
-) -> Result<SearchResult, MeilisearchHttpError> {
-    let before_search = Instant::now();
-    let rtxn = index.read_txn()?;
-
-    let mut search = index.search(&rtxn);
+fn prepare_search<'t>(
+    index: &'t Index,
+    rtxn: &'t RoTxn,
+    query: &'t SearchQuery,
+) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
+    let mut search = index.search(rtxn);
 
     if let Some(ref query) = query.q {
         search.query(query);
@@ -278,7 +286,7 @@ pub fn perform_search(
     search.terms_matching_strategy(query.matching_strategy.into());
 
     let max_total_hits = index
-        .pagination_max_total_hits(&rtxn)
+        .pagination_max_total_hits(rtxn)
         .map_err(milli::Error::from)?
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
@@ -320,6 +328,19 @@ pub fn perform_search(
         search.sort_criteria(sort);
     }
 
+    Ok((search, is_finite_pagination, max_total_hits, offset))
+}
+
+pub fn perform_search(
+    index: &Index,
+    query: SearchQuery,
+) -> Result<SearchResult, MeilisearchHttpError> {
+    let before_search = Instant::now();
+    let rtxn = index.read_txn()?;
+
+    let (search, is_finite_pagination, max_total_hits, offset) =
+        prepare_search(index, &rtxn, &query)?;
+
     let milli::SearchResult { documents_ids, matching_words, candidates, .. } = search.execute()?;
 
     let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
@@ -473,6 +494,30 @@ pub fn perform_search(
     Ok(result)
 }
 
+pub fn perform_facet_search(
+    index: &Index,
+    search_query: SearchQuery,
+    facet_query: Option<String>,
+    facet_name: String,
+) -> Result<FacetSearchResult, MeilisearchHttpError> {
+    let before_search = Instant::now();
+    let rtxn = index.read_txn()?;
+
+    let (search, _, _, _) = prepare_search(index, &rtxn, &search_query)?;
+    let mut facet_search = SearchForFacetValues::new(facet_name, search);
+    if let Some(facet_query) = &facet_query {
+        facet_search.query(facet_query);
+    }
+
+    let hits = facet_search.execute()?;
+
+    Ok(FacetSearchResult {
+        hits,
+        query: facet_query,
+        processing_time_ms: before_search.elapsed().as_millis(),
+    })
+}
+
 fn insert_geo_distance(sorts: &[String], document: &mut Document) {
     lazy_static::lazy_static! {
         static ref GEO_REGEX: Regex =

milli/src/error.rs

@@ -124,6 +124,16 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
         }
     )]
     InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
+    #[error("Attribute `{}` is not filterable. {}",
+        .field,
+        match .valid_fields.is_empty() {
+            true => "This index does not have configured filterable attributes.".to_string(),
+            false => format!("Available filterable attributes are: `{}`.",
+                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
+                ),
+        }
+    )]
+    InvalidSearchFacet { field: String, valid_fields: BTreeSet<String> },
     #[error("{}", HeedError::BadOpenOptions)]
     InvalidLmdbOpenOptions,
     #[error("You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.")]

milli/src/heed_codec/fst_set_codec.rs

@@ -0,0 +1,23 @@
+use std::borrow::Cow;
+
+use fst::Set;
+use heed::{BytesDecode, BytesEncode};
+
+/// A codec for values of type `Set<&[u8]>`.
+pub struct FstSetCodec;
+
+impl<'a> BytesEncode<'a> for FstSetCodec {
+    type EItem = Set<Vec<u8>>;
+
+    fn bytes_encode(item: &'a Self::EItem) -> Option<Cow<'a, [u8]>> {
+        Some(Cow::Borrowed(item.as_fst().as_bytes()))
+    }
+}
+
+impl<'a> BytesDecode<'a> for FstSetCodec {
+    type DItem = Set<&'a [u8]>;
+
+    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
+        Set::new(bytes).ok()
+    }
+}

milli/src/heed_codec/mod.rs

@@ -2,6 +2,7 @@ mod beu32_str_codec;
 mod byte_slice_ref;
 pub mod facet;
 mod field_id_word_count_codec;
+mod fst_set_codec;
 mod obkv_codec;
 mod roaring_bitmap;
 mod roaring_bitmap_length;
@@ -15,6 +16,7 @@ pub use str_ref::StrRefCodec;
 
 pub use self::beu32_str_codec::BEU32StrCodec;
 pub use self::field_id_word_count_codec::FieldIdWordCountCodec;
+pub use self::fst_set_codec::FstSetCodec;
 pub use self::obkv_codec::ObkvCodec;
 pub use self::roaring_bitmap::{BoRoaringBitmapCodec, CboRoaringBitmapCodec, RoaringBitmapCodec};
 pub use self::roaring_bitmap_length::{

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -49,7 +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)
         }
     }
 
@@ -69,7 +69,7 @@ impl CboRoaringBitmapCodec {
                     vec.push(integer);
                 }
             } else {
-                roaring |= RoaringBitmap::deserialize_unchecked_from(bytes.as_ref())?;
+                roaring |= RoaringBitmap::deserialize_from(bytes.as_ref())?;
             }
         }
 

milli/src/heed_codec/roaring_bitmap/roaring_bitmap_codec.rs

@@ -8,7 +8,7 @@ impl heed::BytesDecode<'_> for RoaringBitmapCodec {
     type DItem = RoaringBitmap;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmap::deserialize_unchecked_from(bytes).ok()
+        RoaringBitmap::deserialize_from(bytes).ok()
     }
 }
 

milli/src/index.rs

@@ -19,11 +19,12 @@ use crate::heed_codec::facet::{
     FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
     FieldIdCodec, OrderedF64Codec,
 };
-use crate::heed_codec::{ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
+use crate::heed_codec::{FstSetCodec, 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, Result, RoaringBitmapCodec, RoaringBitmapLenCodec,
+    Search, U8StrStrCodec, BEU16, BEU32,
 };
 
 pub const DEFAULT_MIN_WORD_LEN_ONE_TYPO: u8 = 5;
@@ -84,6 +85,7 @@ pub mod db_name {
     pub const FACET_ID_IS_NULL_DOCIDS: &str = "facet-id-is-null-docids";
     pub const FACET_ID_IS_EMPTY_DOCIDS: &str = "facet-id-is-empty-docids";
     pub const FACET_ID_STRING_DOCIDS: &str = "facet-id-string-docids";
+    pub const FACET_ID_STRING_FST: &str = "facet-id-string-fst";
     pub const FIELD_ID_DOCID_FACET_F64S: &str = "field-id-docid-facet-f64s";
     pub const FIELD_ID_DOCID_FACET_STRINGS: &str = "field-id-docid-facet-strings";
     pub const DOCUMENTS: &str = "documents";
@@ -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.
@@ -143,6 +148,8 @@ pub struct Index {
     pub facet_id_f64_docids: Database<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>,
     /// Maps the facet field id and ranges of strings with the docids that corresponds to them.
     pub facet_id_string_docids: Database<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>,
+    /// Maps the facet field id of the string facets with an FST containing all the facets values.
+    pub facet_id_string_fst: Database<OwnedType<BEU16>, FstSetCodec>,
 
     /// Maps the document id, the facet field id and the numbers.
     pub field_id_docid_facet_f64s: Database<FieldDocIdFacetF64Codec, Unit>,
@@ -162,7 +169,7 @@ impl Index {
     ) -> Result<Index> {
         use db_name::*;
 
-        options.max_dbs(23);
+        options.max_dbs(24);
         unsafe { options.flag(Flags::MdbAlwaysFreePages) };
 
         let env = options.open(path)?;
@@ -173,6 +180,7 @@ 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 =
@@ -192,13 +200,13 @@ impl Index {
         let facet_id_f64_docids = env.create_database(&mut wtxn, Some(FACET_ID_F64_DOCIDS))?;
         let facet_id_string_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_STRING_DOCIDS))?;
+        let facet_id_string_fst = env.create_database(&mut wtxn, Some(FACET_ID_STRING_FST))?;
         let facet_id_exists_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_EXISTS_DOCIDS))?;
         let facet_id_is_null_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_IS_NULL_DOCIDS))?;
         let facet_id_is_empty_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_IS_EMPTY_DOCIDS))?;
-
         let field_id_docid_facet_f64s =
             env.create_database(&mut wtxn, Some(FIELD_ID_DOCID_FACET_F64S))?;
         let field_id_docid_facet_strings =
@@ -215,6 +223,7 @@ 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,
@@ -226,6 +235,7 @@ impl Index {
             field_id_word_count_docids,
             facet_id_f64_docids,
             facet_id_string_docids,
+            facet_id_string_fst,
             facet_id_exists_docids,
             facet_id_is_null_docids,
             facet_id_is_empty_docids,

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 +99,9 @@ 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, FacetValueHit, Filter, FormatOptions, MatchBounds, MatcherBuilder,
+    MatchingWords, Search, SearchForFacetValues, SearchResult, TermsMatchingStrategy,
+    DEFAULT_VALUES_PER_FACET,
 };
 
 pub type Result<T> = std::result::Result<T, error::Error>;

milli/src/proximity.rs

@@ -2,7 +2,7 @@ use std::cmp;
 
 use crate::{relative_from_absolute_position, Position};
 
-pub const MAX_DISTANCE: u32 = 4;
+pub const MAX_DISTANCE: u32 = 8;
 
 pub fn index_proximity(lhs: u32, rhs: u32) -> u32 {
     if lhs <= rhs {

milli/src/search/mod.rs

@@ -1,14 +1,20 @@
 use std::fmt;
 
+use fst::automaton::{Automaton, Str};
+use fst::{IntoStreamer, Streamer};
 use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
+use log::error;
 use once_cell::sync::Lazy;
 use roaring::bitmap::RoaringBitmap;
 
 pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET};
 pub use self::new::matches::{FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWords};
 use self::new::PartialSearchResult;
+use crate::error::UserError;
+use crate::heed_codec::facet::{FacetGroupKey, FacetGroupValue};
 use crate::{
-    execute_search, AscDesc, DefaultSearchLogger, DocumentId, Index, Result, SearchContext,
+    execute_search, AscDesc, DefaultSearchLogger, DocumentId, FieldIdMapMissingEntry, Index,
+    Result, SearchContext, BEU16,
 };
 
 // Building these factories is not free.
@@ -16,6 +22,9 @@ static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true));
 static LEVDIST1: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(1, true));
 static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true));
 
+/// The maximum number of facets returned by the facet search route.
+const MAX_NUMBER_OF_FACETS: usize = 100;
+
 pub mod facet;
 mod fst_utils;
 pub mod new;
@@ -199,6 +208,174 @@ pub fn build_dfa(word: &str, typos: u8, is_prefix: bool) -> DFA {
     }
 }
 
+pub struct SearchForFacetValues<'a> {
+    query: Option<String>,
+    facet: String,
+    search_query: Search<'a>,
+}
+
+impl<'a> SearchForFacetValues<'a> {
+    pub fn new(facet: String, search_query: Search<'a>) -> SearchForFacetValues<'a> {
+        SearchForFacetValues { query: None, facet, search_query }
+    }
+
+    pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
+        self.query = Some(query.into());
+        self
+    }
+
+    pub fn execute(&self) -> Result<Vec<FacetValueHit>> {
+        let index = self.search_query.index;
+        let rtxn = self.search_query.rtxn;
+
+        let filterable_fields = index.filterable_fields(rtxn)?;
+        if !filterable_fields.contains(&self.facet) {
+            return Err(UserError::InvalidSearchFacet {
+                field: self.facet.clone(),
+                valid_fields: filterable_fields.into_iter().collect(),
+            }
+            .into());
+        }
+
+        let fields_ids_map = index.fields_ids_map(rtxn)?;
+        let fid = match fields_ids_map.id(&self.facet) {
+            Some(fid) => fid,
+            None => {
+                return Err(FieldIdMapMissingEntry::FieldName {
+                    field_name: self.facet.clone(),
+                    process: "search for facet values",
+                }
+                .into());
+            }
+        };
+
+        let fst = match self.search_query.index.facet_id_string_fst.get(rtxn, &BEU16::new(fid))? {
+            Some(fst) => fst,
+            None => return Ok(vec![]),
+        };
+
+        let search_candidates = self.search_query.execute()?.candidates;
+
+        match self.query.as_ref() {
+            Some(query) => {
+                let authorize_typos = self.search_query.index.authorize_typos(rtxn)?;
+                let field_authorizes_typos =
+                    !self.search_query.index.exact_attributes_ids(rtxn)?.contains(&fid);
+
+                if authorize_typos && field_authorizes_typos {
+                    let mut results = vec![];
+
+                    let exact_words_fst = self.search_query.index.exact_words(rtxn)?;
+                    if exact_words_fst.map_or(false, |fst| fst.contains(query)) {
+                        let key =
+                            FacetGroupKey { field_id: fid, level: 0, left_bound: query.as_ref() };
+                        if let Some(FacetGroupValue { bitmap, .. }) =
+                            index.facet_id_string_docids.get(rtxn, &key)?
+                        {
+                            let count = search_candidates.intersection_len(&bitmap);
+                            if count != 0 {
+                                results.push(FacetValueHit { value: query.to_string(), count });
+                            }
+                        }
+                    } else {
+                        let one_typo = self.search_query.index.min_word_len_one_typo(rtxn)?;
+                        let two_typos = self.search_query.index.min_word_len_two_typos(rtxn)?;
+
+                        let is_prefix = true;
+                        let automaton = if query.len() < one_typo as usize {
+                            build_dfa(query, 0, is_prefix)
+                        } else if query.len() < two_typos as usize {
+                            build_dfa(query, 1, is_prefix)
+                        } else {
+                            build_dfa(query, 2, is_prefix)
+                        };
+
+                        let mut stream = fst.search(automaton).into_stream();
+                        let mut length = 0;
+                        while let Some(facet_value) = stream.next() {
+                            let value = std::str::from_utf8(facet_value)?;
+                            let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
+                            let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
+                                Some(FacetGroupValue { bitmap, .. }) => bitmap,
+                                None => {
+                                    error!(
+                                        "the facet value is missing from the facet database: {key:?}"
+                                    );
+                                    continue;
+                                }
+                            };
+                            let count = search_candidates.intersection_len(&docids);
+                            if count != 0 {
+                                results.push(FacetValueHit { value: value.to_string(), count });
+                                length += 1;
+                            }
+                            if length >= MAX_NUMBER_OF_FACETS {
+                                break;
+                            }
+                        }
+                    }
+
+                    Ok(results)
+                } else {
+                    let automaton = Str::new(query).starts_with();
+                    let mut stream = fst.search(automaton).into_stream();
+                    let mut results = vec![];
+                    let mut length = 0;
+                    while let Some(facet_value) = stream.next() {
+                        let value = std::str::from_utf8(facet_value)?;
+                        let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
+                        let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
+                            Some(FacetGroupValue { bitmap, .. }) => bitmap,
+                            None => {
+                                error!(
+                                    "the facet value is missing from the facet database: {key:?}"
+                                );
+                                continue;
+                            }
+                        };
+                        let count = search_candidates.intersection_len(&docids);
+                        if count != 0 {
+                            results.push(FacetValueHit { value: value.to_string(), count });
+                            length += 1;
+                        }
+                        if length >= MAX_NUMBER_OF_FACETS {
+                            break;
+                        }
+                    }
+
+                    Ok(results)
+                }
+            }
+            None => {
+                let mut results = vec![];
+                let mut length = 0;
+                let prefix = FacetGroupKey { field_id: fid, level: 0, left_bound: "" };
+                for result in index.facet_id_string_docids.prefix_iter(rtxn, &prefix)? {
+                    let (FacetGroupKey { left_bound, .. }, FacetGroupValue { bitmap, .. }) =
+                        result?;
+                    let count = search_candidates.intersection_len(&bitmap);
+                    if count != 0 {
+                        results.push(FacetValueHit { value: left_bound.to_string(), count });
+                        length += 1;
+                    }
+                    if length >= MAX_NUMBER_OF_FACETS {
+                        break;
+                    }
+                }
+                Ok(results)
+            }
+        }
+    }
+}
+
+#[derive(Debug, Clone, serde::Serialize, PartialEq)]
+pub struct FacetValueHit {
+    /// The original facet value
+    pub value: String,
+    /// The number of documents associated to this facet
+    pub count: u64,
+}
+
 #[cfg(test)]
 mod test {
     #[allow(unused_imports)]

milli/src/search/new/ranking_rule_graph/proximity/build.rs

@@ -1,7 +1,6 @@
 #![allow(clippy::too_many_arguments)]
 
 use super::ProximityCondition;
-use crate::proximity::MAX_DISTANCE;
 use crate::search::new::interner::{DedupInterner, Interned};
 use crate::search::new::query_term::LocatedQueryTermSubset;
 use crate::search::new::SearchContext;
@@ -48,7 +47,7 @@ pub fn build_edges(
     }
 
     conditions.push((
-        MAX_DISTANCE - 1 + right_ngram_length as u32,
+        (7 + right_ngram_length) as u32,
         conditions_interner.insert(ProximityCondition::Term { term: right_term.clone() }),
     ));
 

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,
@@ -34,6 +35,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
             script_language_docids,
             facet_id_f64_docids,
             facet_id_string_docids,
+            facet_id_string_fst: _,
             facet_id_exists_docids,
             facet_id_is_null_docids,
             facet_id_is_empty_docids,
@@ -79,6 +81,7 @@ 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 +142,7 @@ 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,
@@ -241,6 +243,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             word_prefix_fid_docids,
             facet_id_f64_docids: _,
             facet_id_string_docids: _,
+            facet_id_string_fst: _,
             field_id_docid_facet_f64s: _,
             field_id_docid_facet_strings: _,
             script_language_docids,
@@ -249,9 +252,23 @@ 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 +279,42 @@ 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 +533,23 @@ 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 +628,7 @@ 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 +1200,4 @@ 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/facet/mod.rs

@@ -78,15 +78,16 @@ pub const FACET_MIN_LEVEL_SIZE: u8 = 5;
 
 use std::fs::File;
 
+use heed::types::DecodeIgnore;
 use log::debug;
 use time::OffsetDateTime;
 
 use self::incremental::FacetsUpdateIncremental;
 use super::FacetsUpdateBulk;
 use crate::facet::FacetType;
-use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec};
+use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValueCodec};
 use crate::heed_codec::ByteSliceRefCodec;
-use crate::{Index, Result};
+use crate::{Index, Result, BEU16};
 
 pub mod bulk;
 pub mod delete;
@@ -157,6 +158,43 @@ impl<'i> FacetsUpdate<'i> {
             );
             incremental_update.execute(wtxn)?;
         }
+
+        // We compute one FST by string facet
+        let mut text_fsts = vec![];
+        let mut current_fst: Option<(u16, fst::SetBuilder<Vec<u8>>)> = None;
+        let database = self.index.facet_id_string_docids.remap_data_type::<DecodeIgnore>();
+        for result in database.iter(wtxn)? {
+            let (facet_group_key, _) = result?;
+            if let FacetGroupKey { field_id, level: 0, left_bound } = facet_group_key {
+                current_fst = match current_fst.take() {
+                    Some((fid, fst_builder)) if fid != field_id => {
+                        let fst = fst_builder.into_set();
+                        text_fsts.push((field_id, fst));
+                        Some((field_id, fst::SetBuilder::memory()))
+                    }
+                    Some((field_id, fst_builder)) => Some((field_id, fst_builder)),
+                    None => Some((field_id, fst::SetBuilder::memory())),
+                };
+
+                if let Some((_, fst_builder)) = current_fst.as_mut() {
+                    fst_builder.insert(left_bound)?;
+                }
+            }
+        }
+
+        if let Some((field_id, fst_builder)) = current_fst {
+            let fst = fst_builder.into_set();
+            text_fsts.push((field_id, fst));
+        }
+
+        // We remove all of the previous FSTs that were in this database
+        self.index.facet_id_string_fst.clear(wtxn)?;
+
+        // We write those FSTs in LMDB now
+        for (field_id, fst) in text_fsts {
+            self.index.facet_id_string_fst.put(wtxn, &BEU16::new(field_id), &fst)?;
+        }
+
         Ok(())
     }
 }

milli/src/update/facets.rs

@@ -1 +0,0 @@
-

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

@@ -91,7 +91,7 @@ fn document_word_positions_into_sorter(
     while !word_positions_heap.is_empty() {
         while let Some(peeked_word_position) = word_positions_heap.pop() {
             ordered_peeked_word_positions.push(peeked_word_position);
-            if ordered_peeked_word_positions.len() == MAX_DISTANCE as usize - 1 {
+            if ordered_peeked_word_positions.len() == 7 {
                 break;
             }
         }

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()? {