Temporary use the charabia git repository to get the latest fixes

4053: Fix the stats of the documents deletion by filter r=Kerollmops a=irevoire

# Pull Request

The issue was that the operation « DocumentDeletionByFilter » was not declared as an index operation. That means the index stats were not reprocessed after the application of the operation.

## Related issue
Fixes #4018

## What does this PR do?
- Move the `DocumentDeletionByFilter` internal operation into the category of the `IndexOperation`. This means that the stats will automatically be re-processed after a batch is processed.
- Update a test to ensure that the stats are valid after each operation

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Thank you so much for contributing to Meilisearch!


Co-authored-by: Tamo <tamo@meilisearch.com>

.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@2.7.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/debian/meilisearch.deb
@@ -53,5 +53,6 @@ jobs:
         uses: mislav/bump-homebrew-formula-action@v2
         with:
           formula-name: meilisearch
+          formula-path: Formula/m/meilisearch.rb
         env:
           COMMITTER_TOKEN: ${{ secrets.HOMEBREW_COMMITTER_TOKEN }}

.github/workflows/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@2.7.0
       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@2.7.0
       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@2.7.0
         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@2.7.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch

.github/workflows/test-suite.yml

@@ -30,20 +30,20 @@ jobs:
         run: |
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
-      - name: Run test with Rust stable
+      - name: Setup test with Rust stable
         if: github.event_name != 'schedule'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
           override: true
-      - name: Run test with Rust nightly
-        if: github.event_name == 'schedule'
+      - name: Setup test with Rust nightly
+        if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -65,7 +65,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -78,12 +78,12 @@ jobs:
           args: --locked --release --all
 
   test-all-features:
-    name: Tests all features on cron schedule only
+    name: Tests all features
     runs-on: ubuntu-latest
     container:
       # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
       image: ubuntu:18.04
-    if: github.event_name == 'schedule'
+    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
@@ -110,24 +110,24 @@ jobs:
     runs-on: ubuntu-latest
     container:
       image: ubuntu:18.04
-    if: github.event_name == 'schedule'
+    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     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 
+      - 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 +146,7 @@ jobs:
           toolchain: stable
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -161,11 +161,11 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.69.0
+          toolchain: 1.71.1
           override: true
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -184,7 +184,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.1
       - name: Run cargo fmt
         # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
         # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate

Cargo.toml

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

PROFILING.md

@@ -0,0 +1,19 @@
+# Profiling Meilisearch
+
+Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options.
+
+![An example profiling with Puffin viewer](assets/profiling-example.png)
+
+## Profiling the Indexing Process
+
+When you enable the `profile-with-puffin` feature of Meilisearch, a Puffin HTTP server will run on Meilisearch and listen on the default _0.0.0.0:8585_ address. This server will record a "frame" whenever it executes the `IndexScheduler::tick` method.
+
+Once your Meilisearch is running and awaits new indexation operations, you must [install and run the `puffin_viewer` tool](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) to see the profiling results. I advise you to run the viewer with the `RUST_LOG=puffin_http::client=debug` environment variable to see the client trying to connect to your server.
+
+Another piece of advice on the Puffin viewer UI interface is to consider the _Merge children with same ID_ option. It can hide the exact actual timings at which events were sent. Please turn it off when you see strange gaps on the Flamegraph. It can help.
+
+## Profiling the Search Process
+
+We still need to take the time to profile the search side of the engine with Puffin. It would require time to profile the filtering phase, query parsing, creation, and execution. We could even profile the Actix HTTP server.
+
+The only issue we see is the framing system. Puffin requires a global frame-based profiling phase, which collides with Meilisearch's ability to accept and answer multiple requests on different threads simultaneously.

README.md

@@ -1,16 +1,20 @@
 <p align="center">
-  <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
-  <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-light-mode-only" target="_blank">
+    <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
+  </a>
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-dark-mode-only" target="_blank">
+    <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
+  </a>
 </p>
 
 <h4 align="center">
-  <a href="https://www.meilisearch.com">Website</a> |
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Website</a> |
   <a href="https://roadmap.meilisearch.com/tabs/1-under-consideration">Roadmap</a> |
-  <a href="https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch">Meilisearch Cloud</a> |
-  <a href="https://blog.meilisearch.com">Blog</a> |
-  <a href="https://www.meilisearch.com/docs">Documentation</a> |
-  <a href="https://www.meilisearch.com/docs/faq">FAQ</a> |
-  <a href="https://discord.meilisearch.com">Discord</a>
+  <a href="https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Meilisearch Cloud</a> |
+  <a href="https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Blog</a> |
+  <a href="https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Documentation</a> |
+  <a href="https://www.meilisearch.com/docs/faq?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">FAQ</a> |
+  <a href="https://discord.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Discord</a>
 </h4>
 
 <p align="center">
@@ -24,40 +28,40 @@
 Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
 
 <p align="center" name="demo">
-  <a href="https://where2watch.meilisearch.com/#gh-light-mode-only" target="_blank">
+  <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
     <img src="assets/demo-light.gif#gh-light-mode-only" alt="A bright colored application for finding movies screening near the user">
   </a>
-  <a href="https://where2watch.meilisearch.com/#gh-dark-mode-only" target="_blank">
+  <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-dark-mode-only" target="_blank">
     <img src="assets/demo-dark.gif#gh-dark-mode-only" alt="A dark colored application for finding movies screening near the user">
   </a>
 </p>
 
-🔥 [**Try it!**](https://where2watch.meilisearch.com/) 🔥
+🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
 
 ## ✨ Features
 
 - **Search-as-you-type:** find search results in less than 50 milliseconds
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
-- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
-- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting):** sort results based on price, date, or pretty much anything else your users need
-- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy#synonyms):** configure synonyms to include more relevant content in your search results
-- **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch):** filter and sort documents based on geographic data
-- **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
-- **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys):** control which users can access what data with API keys that allow fine-grained permissions handling
-- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens):** personalize search results for any number of application tenants
+- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
+- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
+- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
+- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#synonyms):** configure synonyms to include more relevant content in your search results
+- **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
+- **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
+- **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
+- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
 - **Highly Customizable:** customize Meilisearch to your specific needs or use our out-of-the-box and hassle-free presets
-- **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview):** integrate Meilisearch in your technical stack with our plugins and SDKs
+- **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** integrate Meilisearch in your technical stack with our plugins and SDKs
 - **Easy to install, deploy, and maintain**
 
 ## 📖 Documentation
 
-You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/).
+You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
 
 ## 🚀 Getting started
 
-For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start) guide.
+For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
 
-You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting) for an introduction to some of Meilisearch's most popular features.
+You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) for an introduction to some of Meilisearch's most popular features.
 
 ## ⚡ Supercharge your Meilisearch experience
 
@@ -67,29 +71,29 @@ Say goodbye to server deployment and manual updates with [Meilisearch Cloud](htt
 
 Install one of our SDKs in your project for seamless integration between Meilisearch and your favorite language or framework!
 
-Take a look at the complete [Meilisearch integration list](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks).
+Take a look at the complete [Meilisearch integration list](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=sdks-link).
 
-[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks)
+[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=sdks-logos)
 
 ## ⚙️ Advanced usage
 
-Experienced users will want to keep our [API Reference](https://www.meilisearch.com/docs/reference/api/overview) close at hand.
+Experienced users will want to keep our [API Reference](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) close at hand.
 
-We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering), [sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting), [geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens).
+We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
 
-Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes).
+Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
 
 ## 📊 Telemetry
 
-Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry#how-to-disable-data-collection) whenever you want.
+Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
 
-To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
+To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
 
-If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry) of our documentation.
+If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) of our documentation.
 
 ## 📫 Get in touch!
 
-Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/)
+Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
 🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 

benchmarks/Cargo.toml

@@ -14,7 +14,7 @@ license.workspace = true
 anyhow = "1.0.70"
 csv = "1.2.1"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.36", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
 
 [dev-dependencies]

dump/src/lib.rs

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

dump/src/reader/compat/v5_to_v6.rs

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

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

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

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

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

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

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

filter-parser/Cargo.toml

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

filter-parser/src/error.rs

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

filter-parser/src/lib.rs

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

filter-parser/src/value.rs

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

fuzzers/Cargo.toml

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

index-scheduler/Cargo.toml

@@ -22,6 +22,7 @@ log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
+puffin = "0.16.0"
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }

index-scheduler/src/batch.rs

@@ -67,10 +67,6 @@ pub(crate) enum Batch {
         op: IndexOperation,
         must_create_index: bool,
     },
-    IndexDocumentDeletionByFilter {
-        index_uid: String,
-        task: Task,
-    },
     IndexCreation {
         index_uid: String,
         primary_key: Option<String>,
@@ -114,6 +110,10 @@ pub(crate) enum IndexOperation {
         documents: Vec<Vec<String>>,
         tasks: Vec<Task>,
     },
+    IndexDocumentDeletionByFilter {
+        index_uid: String,
+        task: Task,
+    },
     DocumentClear {
         index_uid: String,
         tasks: Vec<Task>,
@@ -155,7 +155,6 @@ impl Batch {
             | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
-            | Batch::IndexDocumentDeletionByFilter { task, .. }
             | Batch::IndexUpdate { task, .. } => vec![task.uid],
             Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
                 tasks.iter().map(|task| task.uid).collect()
@@ -167,6 +166,7 @@ impl Batch {
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     tasks.iter().map(|task| task.uid).collect()
                 }
+                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
@@ -194,8 +194,7 @@ impl Batch {
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid, .. }
-            | IndexDocumentDeletionByFilter { index_uid, .. } => Some(index_uid),
+            | IndexDeletion { index_uid, .. } => Some(index_uid),
         }
     }
 }
@@ -205,6 +204,7 @@ impl IndexOperation {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
             | IndexOperation::DocumentDeletion { index_uid, .. }
+            | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -239,9 +239,12 @@ impl IndexScheduler {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 match &task.kind {
                     KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
-                        Ok(Some(Batch::IndexDocumentDeletionByFilter {
-                            index_uid: index_uid.clone(),
-                            task,
+                        Ok(Some(Batch::IndexOperation {
+                            op: IndexOperation::IndexDocumentDeletionByFilter {
+                                index_uid: index_uid.clone(),
+                                task,
+                            },
+                            must_create_index: false,
                         }))
                     }
                     _ => unreachable!(),
@@ -471,6 +474,8 @@ impl IndexScheduler {
         #[cfg(test)]
         self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
 
+        puffin::profile_function!();
+
         let enqueued = &self.get_status(rtxn, Status::Enqueued)?;
         let to_cancel = self.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
 
@@ -534,7 +539,9 @@ impl IndexScheduler {
         let index_tasks = self.index_tasks(rtxn, index_name)? & enqueued;
 
         // If autobatching is disabled we only take one task at a time.
-        let tasks_limit = if self.autobatching_enabled { usize::MAX } else { 1 };
+        // Otherwise, we take only a maximum of tasks to create batches.
+        let tasks_limit =
+            if self.autobatching_enabled { self.maximum_number_of_batched_tasks } else { 1 };
 
         let enqueued = index_tasks
             .into_iter()
@@ -575,6 +582,9 @@ impl IndexScheduler {
             self.maybe_fail(crate::tests::FailureLocation::PanicInsideProcessBatch)?;
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
+
+        puffin::profile_function!(format!("{:?}", batch));
+
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -891,51 +901,6 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
-            Batch::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
-                let (index_uid, filter) =
-                    if let KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } =
-                        &task.kind
-                    {
-                        (index_uid, filter_expr)
-                    } else {
-                        unreachable!()
-                    };
-                let index = {
-                    let rtxn = self.env.read_txn()?;
-                    self.index_mapper.index(&rtxn, index_uid)?
-                };
-                let deleted_documents = delete_document_by_filter(filter, index);
-                let original_filter = if let Some(Details::DocumentDeletionByFilter {
-                    original_filter,
-                    deleted_documents: _,
-                }) = task.details
-                {
-                    original_filter
-                } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
-                    unreachable!();
-                };
-
-                match deleted_documents {
-                    Ok(deleted_documents) => {
-                        task.status = Status::Succeeded;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(deleted_documents),
-                        });
-                    }
-                    Err(e) => {
-                        task.status = Status::Failed;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(0),
-                        });
-                        task.error = Some(e.into());
-                    }
-                }
-
-                Ok(vec![task])
-            }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 let wtxn = self.env.write_txn()?;
                 if self.index_mapper.exists(&wtxn, &index_uid)? {
@@ -1111,6 +1076,8 @@ impl IndexScheduler {
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
+        puffin::profile_function!();
+
         match operation {
             IndexOperation::DocumentClear { mut tasks, .. } => {
                 let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;
@@ -1292,6 +1259,47 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
+                let filter =
+                    if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
+                        &task.kind
+                    {
+                        filter_expr
+                    } else {
+                        unreachable!()
+                    };
+                let deleted_documents = delete_document_by_filter(index_wtxn, filter, index);
+                let original_filter = if let Some(Details::DocumentDeletionByFilter {
+                    original_filter,
+                    deleted_documents: _,
+                }) = task.details
+                {
+                    original_filter
+                } else {
+                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    unreachable!();
+                };
+
+                match deleted_documents {
+                    Ok(deleted_documents) => {
+                        task.status = Status::Succeeded;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(deleted_documents),
+                        });
+                    }
+                    Err(e) => {
+                        task.status = Status::Failed;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(0),
+                        });
+                        task.error = Some(e.into());
+                    }
+                }
+
+                Ok(vec![task])
+            }
             IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
                 let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config);
@@ -1491,23 +1499,22 @@ impl IndexScheduler {
     }
 }
 
-fn delete_document_by_filter(filter: &serde_json::Value, index: Index) -> Result<u64> {
+fn delete_document_by_filter<'a>(
+    wtxn: &mut RwTxn<'a, '_>,
+    filter: &serde_json::Value,
+    index: &'a Index,
+) -> Result<u64> {
     let filter = Filter::from_json(filter)?;
     Ok(if let Some(filter) = filter {
-        let mut wtxn = index.write_txn()?;
-
-        let candidates = filter.evaluate(&wtxn, &index).map_err(|err| match err {
+        let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
             milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
                 Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
             }
             e => e.into(),
         })?;
-        let mut delete_operation = DeleteDocuments::new(&mut wtxn, &index)?;
+        let mut delete_operation = DeleteDocuments::new(wtxn, index)?;
         delete_operation.delete_documents(&candidates);
-        let deleted_documents =
-            delete_operation.execute().map(|result| result.deleted_documents)?;
-        wtxn.commit()?;
-        deleted_documents
+        delete_operation.execute().map(|result| result.deleted_documents)?
     } else {
         0
     })

index-scheduler/src/insta_snapshot.rs

@@ -15,6 +15,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
 
     let IndexScheduler {
         autobatching_enabled,
+        maximum_number_of_batched_tasks: _,
         must_stop_processing: _,
         processing_tasks,
         file_store,

index-scheduler/src/lib.rs

@@ -253,6 +253,9 @@ pub struct IndexSchedulerOptions {
     /// Set to `true` iff the index scheduler is allowed to automatically
     /// batch tasks together, to process multiple tasks at once.
     pub autobatching_enabled: bool,
+    /// If the autobatcher is allowed to automatically batch tasks
+    /// it will only batch this defined number of tasks at once.
+    pub maximum_number_of_batched_tasks: usize,
     /// The maximum number of tasks stored in the task queue before starting
     /// to auto schedule task deletions.
     pub max_number_of_tasks: usize,
@@ -310,6 +313,9 @@ pub struct IndexScheduler {
     /// Whether auto-batching is enabled or not.
     pub(crate) autobatching_enabled: bool,
 
+    /// The maximum number of tasks that will be batched together.
+    pub(crate) maximum_number_of_batched_tasks: usize,
+
     /// The max number of tasks allowed before the scheduler starts to delete
     /// the finished tasks automatically.
     pub(crate) max_number_of_tasks: usize,
@@ -363,6 +369,7 @@ impl IndexScheduler {
             index_mapper: self.index_mapper.clone(),
             wake_up: self.wake_up.clone(),
             autobatching_enabled: self.autobatching_enabled,
+            maximum_number_of_batched_tasks: self.maximum_number_of_batched_tasks,
             max_number_of_tasks: self.max_number_of_tasks,
             snapshots_path: self.snapshots_path.clone(),
             dumps_path: self.dumps_path.clone(),
@@ -458,6 +465,7 @@ impl IndexScheduler {
             // we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
             wake_up: Arc::new(SignalEvent::auto(true)),
             autobatching_enabled: options.autobatching_enabled,
+            maximum_number_of_batched_tasks: options.maximum_number_of_batched_tasks,
             max_number_of_tasks: options.max_number_of_tasks,
             dumps_path: options.dumps_path,
             snapshots_path: options.snapshots_path,
@@ -790,10 +798,19 @@ impl IndexScheduler {
 
         let mut res = BTreeMap::new();
 
+        let processing_tasks = { self.processing_tasks.read().unwrap().processing.len() };
+
         res.insert(
             "statuses".to_string(),
             enum_iterator::all::<Status>()
-                .map(|s| Ok((s.to_string(), self.get_status(&rtxn, s)?.len())))
+                .map(|s| {
+                    let tasks = self.get_status(&rtxn, s)?.len();
+                    match s {
+                        Status::Enqueued => Ok((s.to_string(), tasks - processing_tasks)),
+                        Status::Processing => Ok((s.to_string(), processing_tasks)),
+                        s => Ok((s.to_string(), tasks)),
+                    }
+                })
                 .collect::<Result<BTreeMap<String, u64>>>()?,
         );
         res.insert(
@@ -1053,6 +1070,8 @@ impl IndexScheduler {
             self.breakpoint(Breakpoint::Start);
         }
 
+        puffin::GlobalProfiler::lock().new_frame();
+
         self.cleanup_task_queue()?;
 
         let rtxn = self.env.read_txn().map_err(Error::HeedTransaction)?;
@@ -1578,6 +1597,7 @@ mod tests {
                 index_count: 5,
                 indexer_config,
                 autobatching_enabled: true,
+                maximum_number_of_batched_tasks: usize::MAX,
                 max_number_of_tasks: 1_000_000,
                 instance_features: Default::default(),
             };
@@ -4129,4 +4149,154 @@ mod tests {
         snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "everything_has_been_processed");
         drop(rtxn);
     }
+
+    #[test]
+    fn basic_get_stats() {
+        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
+
+        let kind = index_creation_task("catto", "mouse");
+        let _task = index_scheduler.register(kind).unwrap();
+        let kind = index_creation_task("doggo", "sheep");
+        let _task = index_scheduler.register(kind).unwrap();
+        let kind = index_creation_task("whalo", "fish");
+        let _task = index_scheduler.register(kind).unwrap();
+
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 3,
+            "failed": 0,
+            "processing": 0,
+            "succeeded": 0
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+
+        handle.advance_till([Start, BatchCreated]);
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 2,
+            "failed": 0,
+            "processing": 1,
+            "succeeded": 0
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+
+        handle.advance_till([
+            InsideProcessBatch,
+            InsideProcessBatch,
+            ProcessBatchSucceeded,
+            AfterProcessing,
+            Start,
+            BatchCreated,
+        ]);
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 1,
+            "failed": 0,
+            "processing": 1,
+            "succeeded": 1
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+
+        // now we make one more batch, the started_at field of the new tasks will be past `second_start_time`
+        handle.advance_till([
+            InsideProcessBatch,
+            InsideProcessBatch,
+            ProcessBatchSucceeded,
+            AfterProcessing,
+            Start,
+            BatchCreated,
+        ]);
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 0,
+            "failed": 0,
+            "processing": 1,
+            "succeeded": 2
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+    }
 }

meili-snap/src/lib.rs

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

meilisearch-types/Cargo.toml

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

meilisearch-types/src/document_formats.rs

@@ -1,4 +1,3 @@
-use std::borrow::Borrow;
 use std::fmt::{self, Debug, Display};
 use std::fs::File;
 use std::io::{self, Seek, Write};
@@ -42,7 +41,7 @@ impl Display for DocumentFormatError {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
             Self::Io(e) => write!(f, "{e}"),
-            Self::MalformedPayload(me, b) => match me.borrow() {
+            Self::MalformedPayload(me, b) => match me {
                 Error::Json(se) => {
                     let mut message = match se.classify() {
                         Category::Data => {

meilisearch-types/src/error.rs

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

meilisearch-types/src/settings.rs

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

meilisearch/Cargo.toml

@@ -39,7 +39,7 @@ byte-unit = { version = "4.0.19", default-features = false, features = [
 bytes = "1.4.0"
 clap = { version = "4.2.1", features = ["derive", "env"] }
 crossbeam-channel = "0.5.8"
-deserr = "0.5.0"
+deserr = { version = "0.6.0", features = ["actix-web"]}
 dump = { path = "../dump" }
 either = "1.8.1"
 env_logger = "0.10.0"
@@ -50,15 +50,15 @@ futures = "0.3.28"
 futures-util = "0.3.28"
 http = "0.2.9"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "1.9.3", features = ["serde-1"] }
+indexmap = { version = "2.0.0", features = ["serde"] }
 is-terminal = "0.4.8"
-itertools = "0.10.5"
+itertools = "0.11.0"
 jsonwebtoken = "8.3.0"
 lazy_static = "1.4.0"
 log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-mimalloc = { version = "0.1.36", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.15.0"
 obkv = "0.2.0"
@@ -69,6 +69,8 @@ permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.9"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
+puffin = "0.16.0"
+puffin_http = { version = "0.13.0", optional = true }
 rand = "0.8.5"
 rayon = "1.7.0"
 regex = "1.7.3"
@@ -85,7 +87,7 @@ sha2 = "0.10.6"
 siphasher = "0.3.10"
 slice-group-by = "0.3.0"
 static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.28.4"
+sysinfo = "0.29.7"
 tar = "0.4.38"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
@@ -131,9 +133,20 @@ vergen = { version = "7.5.1", default-features = false, features = ["git"] }
 zip = { version = "0.6.4", optional = true }
 
 [features]
-default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
+default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard", "profile-with-puffin"]
 analytics = ["segment"]
-mini-dashboard = ["actix-web-static-files", "static-files", "anyhow", "cargo_toml", "hex", "reqwest", "sha-1", "tempfile", "zip"]
+profile-with-puffin = ["dep:puffin_http"]
+mini-dashboard = [
+    "actix-web-static-files",
+    "static-files",
+    "anyhow",
+    "cargo_toml",
+    "hex",
+    "reqwest",
+    "sha-1",
+    "tempfile",
+    "zip",
+]
 chinese = ["meilisearch-types/chinese"]
 hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]

meilisearch/src/analytics/mock_analytics.rs

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

meilisearch/src/analytics/segment_analytics.rs

@@ -285,6 +285,7 @@ impl From<Opt> for Infos {
             db_path,
             experimental_enable_metrics,
             experimental_reduce_indexing_memory_usage,
+            experimental_limit_batched_tasks: _,
             http_addr,
             master_key: _,
             env,

meilisearch/src/lib.rs

@@ -236,6 +236,7 @@ fn open_or_create_database_unchecked(
             enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
             indexer_config: (&opt.indexer_options).try_into()?,
             autobatching_enabled: true,
+            maximum_number_of_batched_tasks: opt.experimental_limit_batched_tasks,
             max_number_of_tasks: 1_000_000,
             index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
             index_count: DEFAULT_INDEX_COUNT,

meilisearch/src/main.rs

@@ -30,6 +30,10 @@ fn setup(opt: &Opt) -> anyhow::Result<()> {
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
+    #[cfg(feature = "profile-with-puffin")]
+    let _server = puffin_http::Server::new(&format!("0.0.0.0:{}", puffin_http::DEFAULT_PORT))?;
+    puffin::set_scopes_on(cfg!(feature = "profile-with-puffin"));
+
     anyhow::ensure!(
         !(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
         "The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"

meilisearch/src/option.rs

@@ -51,6 +51,7 @@ const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
 const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
     "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
+const MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS: &str = "MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS";
 
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
@@ -301,6 +302,11 @@ pub struct Opt {
     #[serde(default)]
     pub experimental_reduce_indexing_memory_usage: bool,
 
+    /// Experimental limit to the number of tasks per batch
+    #[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS, default_value_t = default_limit_batched_tasks())]
+    #[serde(default = "default_limit_batched_tasks")]
+    pub experimental_limit_batched_tasks: usize,
+
     #[serde(flatten)]
     #[clap(flatten)]
     pub indexer_options: IndexerOpts,
@@ -393,7 +399,8 @@ impl Opt {
             #[cfg(all(not(debug_assertions), feature = "analytics"))]
             no_analytics,
             experimental_enable_metrics: enable_metrics_route,
-            experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
+            experimental_reduce_indexing_memory_usage,
+            experimental_limit_batched_tasks,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -437,7 +444,11 @@ impl Opt {
         );
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
-            reduce_indexing_memory_usage.to_string(),
+            experimental_reduce_indexing_memory_usage.to_string(),
+        );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS,
+            experimental_limit_batched_tasks.to_string(),
         );
         indexer_options.export_to_env();
     }
@@ -739,6 +750,10 @@ fn default_dump_dir() -> PathBuf {
     PathBuf::from(DEFAULT_DUMP_DIR)
 }
 
+fn default_limit_batched_tasks() -> usize {
+    usize::MAX
+}
+
 /// Indicates if a snapshot was scheduled, and if yes with which interval.
 #[derive(Debug, Default, Copy, Clone, Deserialize, Serialize)]
 pub enum ScheduleSnapshot {

meilisearch/src/routes/indexes/settings.rs

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

meilisearch/src/routes/swap_indexes.rs

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

meilisearch/src/search.rs

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

meilisearch/tests/documents/delete_documents.rs

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

meilisearch/tests/search/geo.rs

@@ -1,3 +1,4 @@
+use meili_snap::{json_string, snapshot};
 use once_cell::sync::Lazy;
 use serde_json::{json, Value};
 
@@ -60,3 +61,59 @@ async fn geo_sort_with_geo_strings() {
         )
         .await;
 }
+
+#[actix_rt::test]
+async fn geo_bounding_box_with_string_and_number() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = DOCUMENTS.clone();
+    index.update_settings_filterable_attributes(json!(["_geo"])).await;
+    index.update_settings_sortable_attributes(json!(["_geo"])).await;
+    index.add_documents(documents, None).await;
+    index.wait_task(2).await;
+
+    index
+        .search(
+            json!({
+                "filter": "_geoBoundingBox([89, 179], [-89, -179])",
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r###"
+                {
+                  "hits": [
+                    {
+                      "id": 1,
+                      "name": "Taco Truck",
+                      "address": "444 Salsa Street, Burritoville",
+                      "type": "Mexican",
+                      "rating": 9,
+                      "_geo": {
+                        "lat": 34.0522,
+                        "lng": -118.2437
+                      }
+                    },
+                    {
+                      "id": 2,
+                      "name": "La Bella Italia",
+                      "address": "456 Elm Street, Townsville",
+                      "type": "Italian",
+                      "rating": 9,
+                      "_geo": {
+                        "lat": "45.4777599",
+                        "lng": "9.1967508"
+                      }
+                    }
+                  ],
+                  "query": "",
+                  "processingTimeMs": "[time]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 2
+                }
+                "###);
+            },
+        )
+        .await;
+}

meilisearch/tests/search/mod.rs

@@ -1104,3 +1104,59 @@ async fn camelcased_words() {
         })
         .await;
 }
+
+#[actix_rt::test]
+async fn simple_search_with_strange_synonyms() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    index.update_settings(json!({ "synonyms": {"&": ["to"], "to": ["&"]} })).await;
+    let r = index.wait_task(0).await;
+    meili_snap::snapshot!(r["status"], @r###""succeeded""###);
+
+    let documents = DOCUMENTS.clone();
+    index.add_documents(documents, None).await;
+    index.wait_task(1).await;
+
+    index
+        .search(json!({"q": "How to train"}), |response, code| {
+            meili_snap::snapshot!(code, @"200 OK");
+            meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "How to Train Your Dragon: The Hidden World",
+                "id": "166428"
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "How & train"}), |response, code| {
+            meili_snap::snapshot!(code, @"200 OK");
+            meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "How to Train Your Dragon: The Hidden World",
+                "id": "166428"
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "to"}), |response, code| {
+            meili_snap::snapshot!(code, @"200 OK");
+            meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "How to Train Your Dragon: The Hidden World",
+                "id": "166428"
+              }
+            ]
+            "###);
+        })
+        .await;
+}

meilisearch/tests/settings/get_settings.rs

@@ -16,6 +16,9 @@ static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|
         json!(["words", "typo", "proximity", "attribute", "sort", "exactness"]),
     );
     map.insert("stop_words", json!([]));
+    map.insert("non_separator_tokens", json!([]));
+    map.insert("separator_tokens", json!([]));
+    map.insert("dictionary", json!([]));
     map.insert("synonyms", json!({}));
     map.insert(
         "faceting",
@@ -51,7 +54,7 @@ async fn get_settings() {
     let (response, code) = index.settings().await;
     assert_eq!(code, 200);
     let settings = response.as_object().unwrap();
-    assert_eq!(settings.keys().len(), 11);
+    assert_eq!(settings.keys().len(), 14);
     assert_eq!(settings["displayedAttributes"], json!(["*"]));
     assert_eq!(settings["searchableAttributes"], json!(["*"]));
     assert_eq!(settings["filterableAttributes"], json!([]));
@@ -62,6 +65,9 @@ async fn get_settings() {
         json!(["words", "typo", "proximity", "attribute", "sort", "exactness"])
     );
     assert_eq!(settings["stopWords"], json!([]));
+    assert_eq!(settings["nonSeparatorTokens"], json!([]));
+    assert_eq!(settings["separatorTokens"], json!([]));
+    assert_eq!(settings["dictionary"], json!([]));
     assert_eq!(
         settings["faceting"],
         json!({
@@ -272,6 +278,9 @@ test_setting_routes!(
     searchable_attributes put,
     distinct_attribute put,
     stop_words put,
+    separator_tokens put,
+    non_separator_tokens put,
+    dictionary put,
     ranking_rules put,
     synonyms put,
     pagination patch,

meilisearch/tests/settings/mod.rs

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

meilisearch/tests/settings/tokenizer_customization.rs

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

milli/Cargo.toml

@@ -17,10 +17,11 @@ bincode = "1.3.3"
 bstr = "1.4.0"
 bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
 byteorder = "1.4.3"
-charabia = { version = "0.8.2", default-features = false }
+# charabia = { version = "0.8.3", default-features = false }
+charabia = { git = "https://github.com/meilisearch/charabia", branch = "main", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.8"
-deserr = "0.5.0"
+deserr = { version = "0.6.0", features = ["actix-web"]}
 either = { version = "1.8.1", features = ["serde"] }
 flatten-serde-json = { path = "../flatten-serde-json" }
 fst = "0.4.7"
@@ -32,18 +33,18 @@ grenad = { version = "0.4.4", default-features = false, features = [
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.7", default-features = false, features = [
     "lmdb", "read-txn-no-tls"
 ] }
-indexmap = { version = "1.9.3", features = ["serde"] }
+indexmap = { version = "2.0.0", features = ["serde"] }
 instant-distance = { version = "0.6.1", features = ["with-serde"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
-memmap2 = "0.5.10"
+memmap2 = "0.7.1"
 obkv = "0.2.0"
 once_cell = "1.17.1"
 ordered-float = "3.6.0"
 rand_pcg = { version = "0.3.1", features = ["serde1"] }
 rayon = "1.7.0"
 roaring = "0.10.1"
-rstar = { version = "0.10.0", features = ["serde"] }
+rstar = { version = "0.11.0", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
 slice-group-by = "0.3.0"
@@ -63,7 +64,10 @@ uuid = { version = "1.3.1", features = ["v4"] }
 filter-parser = { path = "../filter-parser" }
 
 # documents words self-join
-itertools = "0.10.5"
+itertools = "0.11.0"
+
+# profiling
+puffin = "0.16.0"
 
 # logging
 log = "0.4.17"
@@ -71,7 +75,7 @@ logging_timer = "1.1.0"
 csv = "1.2.1"
 
 [dev-dependencies]
-mimalloc = { version = "0.1.29", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 big_s = "1.0.2"
 insta = "1.29.0"
 maplit = "1.0.2"

milli/src/error.rs

@@ -122,22 +122,28 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
         .field,
         match .valid_fields.is_empty() {
             true => "This index does not have configured sortable attributes.".to_string(),
-            false => format!("Available sortable attributes are: `{}`.",
-                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
+            false => format!("Available sortable attributes are: `{}{}`.",
+                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
+                    .hidden_fields.then_some(", <..hidden-attributes>").unwrap_or(""),
                 ),
         }
     )]
-    InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
+    InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String>, hidden_fields: bool },
     #[error("Attribute `{}` is not facet-searchable. {}",
         .field,
         match .valid_fields.is_empty() {
             true => "This index does not have configured facet-searchable attributes. To make it facet-searchable add it to the `filterableAttributes` index settings.".to_string(),
-            false => format!("Available facet-searchable attributes are: `{}`. To make it facet-searchable add it to the `filterableAttributes` index settings.",
-                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
+            false => format!("Available facet-searchable attributes are: `{}{}`. To make it facet-searchable add it to the `filterableAttributes` index settings.",
+                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
+                    .hidden_fields.then_some(", <..hidden-attributes>").unwrap_or(""),
                 ),
         }
     )]
-    InvalidFacetSearchFacetName { field: String, valid_fields: BTreeSet<String> },
+    InvalidFacetSearchFacetName {
+        field: String,
+        valid_fields: BTreeSet<String>,
+        hidden_fields: bool,
+    },
     #[error("Attribute `{}` is not searchable. Available searchable attributes are: `{}{}`.",
         .field,
         .valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
@@ -340,8 +346,11 @@ fn conditionally_lookup_for_error_message() {
     ];
 
     for (list, suffix) in messages {
-        let err =
-            UserError::InvalidSortableAttribute { field: "name".to_string(), valid_fields: list };
+        let err = UserError::InvalidSortableAttribute {
+            field: "name".to_string(),
+            valid_fields: list,
+            hidden_fields: false,
+        };
 
         assert_eq!(err.to_string(), format!("{} {}", prefix, suffix));
     }

milli/src/index.rs

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

milli/src/lib.rs

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

milli/src/search/mod.rs

@@ -280,9 +280,13 @@ impl<'a> SearchForFacetValues<'a> {
 
         let filterable_fields = index.filterable_fields(rtxn)?;
         if !filterable_fields.contains(&self.facet) {
+            let (valid_fields, hidden_fields) =
+                index.remove_hidden_fields(rtxn, filterable_fields)?;
+
             return Err(UserError::InvalidFacetSearchFacetName {
                 field: self.facet.clone(),
-                valid_fields: filterable_fields.into_iter().collect(),
+                valid_fields,
+                hidden_fields,
             }
             .into());
         }

milli/src/search/new/bucket_sort.rs

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

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

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

milli/src/search/new/mod.rs

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

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

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

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

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

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

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

milli/src/update/clear_documents.rs

@@ -15,6 +15,8 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
     }
 
     pub fn execute(self) -> Result<u64> {
+        puffin::profile_function!();
+
         self.index.set_updated_at(self.wtxn, &OffsetDateTime::now_utc())?;
         let Index {
             env: _env,

milli/src/update/delete_documents.rs

@@ -109,6 +109,8 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
         Some(docid)
     }
     pub fn execute(self) -> Result<DocumentDeletionResult> {
+        puffin::profile_function!();
+
         let DetailedDocumentDeletionResult { deleted_documents, remaining_documents } =
             self.execute_inner()?;
 

milli/src/update/facet/mod.rs

@@ -94,7 +94,7 @@ use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValu
 use crate::heed_codec::ByteSliceRefCodec;
 use crate::update::index_documents::create_sorter;
 use crate::update::merge_btreeset_string;
-use crate::{BEU16StrCodec, Index, Result, BEU16};
+use crate::{BEU16StrCodec, Index, Result, BEU16, MAX_FACET_VALUE_LENGTH};
 
 pub mod bulk;
 pub mod delete;
@@ -191,7 +191,16 @@ impl<'i> FacetsUpdate<'i> {
         for result in database.iter(wtxn)? {
             let (facet_group_key, ()) = result?;
             if let FacetGroupKey { field_id, level: 0, left_bound } = facet_group_key {
-                let normalized_facet = left_bound.normalize(&options);
+                let mut normalized_facet = left_bound.normalize(&options);
+                let normalized_truncated_facet: String;
+                if normalized_facet.len() > MAX_FACET_VALUE_LENGTH {
+                    normalized_truncated_facet = normalized_facet
+                        .char_indices()
+                        .take_while(|(idx, _)| *idx < MAX_FACET_VALUE_LENGTH)
+                        .map(|(_, c)| c)
+                        .collect();
+                    normalized_facet = normalized_truncated_facet.into();
+                }
                 let set = BTreeSet::from_iter(std::iter::once(left_bound));
                 let key = (field_id, normalized_facet.as_ref());
                 let key = BEU16StrCodec::bytes_encode(&key).ok_or(heed::Error::Encoding)?;

milli/src/update/index_documents/enrich.rs

@@ -31,6 +31,8 @@ pub fn enrich_documents_batch<R: Read + Seek>(
     autogenerate_docids: bool,
     reader: DocumentsBatchReader<R>,
 ) -> Result<StdResult<EnrichedDocumentsBatchReader<R>, UserError>> {
+    puffin::profile_function!();
+
     let (mut cursor, mut documents_batch_index) = reader.into_cursor_and_fields_index();
 
     let mut external_ids = tempfile::tempfile().map(grenad::Writer::new)?;

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

@@ -28,8 +28,12 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     searchable_fields: &Option<HashSet<FieldId>>,
     stop_words: Option<&fst::Set<&[u8]>>,
+    allowed_separators: Option<&[&str]>,
+    dictionary: Option<&[&str]>,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<(RoaringBitmap, grenad::Reader<File>, ScriptLanguageDocidsMap)> {
+    puffin::profile_function!();
+
     let max_positions_per_attributes = max_positions_per_attributes
         .map_or(MAX_POSITION_PER_ATTRIBUTE, |max| max.min(MAX_POSITION_PER_ATTRIBUTE));
     let max_memory = indexer.max_memory_by_thread();
@@ -50,6 +54,12 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
     if let Some(stop_words) = stop_words {
         tokenizer_builder.stop_words(stop_words);
     }
+    if let Some(dictionary) = dictionary {
+        tokenizer_builder.words_dict(dictionary);
+    }
+    if let Some(separators) = allowed_separators {
+        tokenizer_builder.separators(separators);
+    }
     let tokenizer = tokenizer_builder.build();
 
     let mut cursor = obkv_documents.into_cursor()?;
@@ -216,9 +226,9 @@ fn process_tokens<'a>(
 ) -> impl Iterator<Item = (usize, Token<'a>)> {
     tokens
         .skip_while(|token| token.is_separator())
-        .scan((0, None), |(offset, prev_kind), token| {
+        .scan((0, None), |(offset, prev_kind), mut token| {
             match token.kind {
-                TokenKind::Word | TokenKind::StopWord | TokenKind::Unknown => {
+                TokenKind::Word | TokenKind::StopWord if !token.lemma().is_empty() => {
                     *offset += match *prev_kind {
                         Some(TokenKind::Separator(SeparatorKind::Hard)) => 8,
                         Some(_) => 1,
@@ -234,7 +244,7 @@ fn process_tokens<'a>(
                 {
                     *prev_kind = Some(token.kind);
                 }
-                _ => (),
+                _ => token.kind = TokenKind::Unknown,
             }
             Some((*offset, token))
         })

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

@@ -20,6 +20,8 @@ pub fn extract_facet_number_docids<R: io::Read + io::Seek>(
     docid_fid_facet_number: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut facet_number_docids_sorter = create_sorter(

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

@@ -18,6 +18,8 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
     docid_fid_facet_string: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut facet_string_docids_sorter = create_sorter(
@@ -44,7 +46,7 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
         if normalised_value.len() > MAX_FACET_VALUE_LENGTH {
             normalised_truncated_value = normalised_value
                 .char_indices()
-                .take_while(|(idx, _)| idx + 4 < MAX_FACET_VALUE_LENGTH)
+                .take_while(|(idx, _)| *idx < MAX_FACET_VALUE_LENGTH)
                 .map(|(_, c)| c)
                 .collect();
             normalised_value = normalised_truncated_value.as_str();

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

@@ -28,12 +28,16 @@ pub struct ExtractedFacetValues {
 ///
 /// Returns the generated grenad reader containing the docid the fid and the orginal value as key
 /// and the normalized value as value extracted from the given chunk of documents.
+/// We need the fid of the geofields to correctly parse them as numbers if they were sent as strings initially.
 #[logging_timer::time]
 pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
     obkv_documents: grenad::Reader<R>,
     indexer: GrenadParameters,
     faceted_fields: &HashSet<FieldId>,
+    geo_fields_ids: Option<(FieldId, FieldId)>,
 ) -> Result<ExtractedFacetValues> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut fid_docid_facet_numbers_sorter = create_sorter(
@@ -82,7 +86,10 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
 
                 let value = from_slice(field_bytes).map_err(InternalError::SerdeJson)?;
 
-                match extract_facet_values(&value) {
+                match extract_facet_values(
+                    &value,
+                    geo_fields_ids.map_or(false, |(lat, lng)| field_id == lat || field_id == lng),
+                ) {
                     FilterableValues::Null => {
                         facet_is_null_docids.entry(field_id).or_default().insert(document);
                     }
@@ -175,12 +182,13 @@ enum FilterableValues {
     Values { numbers: Vec<f64>, strings: Vec<(String, String)> },
 }
 
-fn extract_facet_values(value: &Value) -> FilterableValues {
+fn extract_facet_values(value: &Value, geo_field: bool) -> FilterableValues {
     fn inner_extract_facet_values(
         value: &Value,
         can_recurse: bool,
         output_numbers: &mut Vec<f64>,
         output_strings: &mut Vec<(String, String)>,
+        geo_field: bool,
     ) {
         match value {
             Value::Null => (),
@@ -191,13 +199,30 @@ fn extract_facet_values(value: &Value) -> FilterableValues {
                 }
             }
             Value::String(original) => {
+                // if we're working on a geofield it MUST be something we can parse or else there was an internal error
+                // in the enrich pipeline. But since the enrich pipeline worked, we want to avoid crashing at all costs.
+                if geo_field {
+                    if let Ok(float) = original.parse() {
+                        output_numbers.push(float);
+                    } else {
+                        log::warn!(
+                            "Internal error, could not parse a geofield that has been validated. Please open an issue."
+                        )
+                    }
+                }
                 let normalized = crate::normalize_facet(original);
                 output_strings.push((normalized, original.clone()));
             }
             Value::Array(values) => {
                 if can_recurse {
                     for value in values {
-                        inner_extract_facet_values(value, false, output_numbers, output_strings);
+                        inner_extract_facet_values(
+                            value,
+                            false,
+                            output_numbers,
+                            output_strings,
+                            geo_field,
+                        );
                     }
                 }
             }
@@ -213,7 +238,7 @@ fn extract_facet_values(value: &Value) -> FilterableValues {
         otherwise => {
             let mut numbers = Vec::new();
             let mut strings = Vec::new();
-            inner_extract_facet_values(otherwise, true, &mut numbers, &mut strings);
+            inner_extract_facet_values(otherwise, true, &mut numbers, &mut strings, geo_field);
             FilterableValues::Values { numbers, strings }
         }
     }

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

@@ -22,6 +22,8 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut fid_word_count_docids_sorter = create_sorter(

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

@@ -19,6 +19,8 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
     primary_key_id: FieldId,
     (lat_fid, lng_fid): (FieldId, FieldId),
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let mut writer = create_writer(
         indexer.chunk_compression_type,
         indexer.chunk_compression_level,

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

@@ -19,6 +19,8 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
     primary_key_id: FieldId,
     vectors_fid: FieldId,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let mut writer = create_writer(
         indexer.chunk_compression_type,
         indexer.chunk_compression_level,
@@ -33,7 +35,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
         // lazily get it when needed
         let document_id = || -> Value {
             let document_id = obkv.get(primary_key_id).unwrap();
-            serde_json::from_slice(document_id).unwrap()
+            from_slice(document_id).unwrap()
         };
 
         // first we retrieve the _vectors field
@@ -50,12 +52,14 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                 }
             };
 
-            for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
-                let index = u16::try_from(i).unwrap();
-                let mut key = docid_bytes.to_vec();
-                key.extend_from_slice(&index.to_be_bytes());
-                let bytes = cast_slice(&vector);
-                writer.insert(key, bytes)?;
+            if let Some(vectors) = vectors {
+                for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
+                    let index = u16::try_from(i).unwrap();
+                    let mut key = docid_bytes.to_vec();
+                    key.extend_from_slice(&index.to_be_bytes());
+                    let bytes = cast_slice(&vector);
+                    writer.insert(key, bytes)?;
+                }
             }
         }
         // else => the `_vectors` object was `null`, there is nothing to do

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

@@ -27,6 +27,8 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     exact_attributes: &HashSet<FieldId>,
 ) -> Result<(grenad::Reader<File>, grenad::Reader<File>)> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_docids_sorter = create_sorter(

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

@@ -15,6 +15,8 @@ pub fn extract_word_fid_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_fid_docids_sorter = create_sorter(

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

@@ -21,6 +21,8 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_pair_proximity_docids_sorter = create_sorter(

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

@@ -18,6 +18,8 @@ pub fn extract_word_position_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_position_docids_sorter = create_sorter(

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

@@ -49,13 +49,23 @@ pub(crate) fn data_from_obkv_documents(
     geo_fields_ids: Option<(FieldId, FieldId)>,
     vectors_field_id: Option<FieldId>,
     stop_words: Option<fst::Set<&[u8]>>,
+    allowed_separators: Option<&[&str]>,
+    dictionary: Option<&[&str]>,
     max_positions_per_attributes: Option<u32>,
     exact_attributes: HashSet<FieldId>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
     original_obkv_chunks
         .par_bridge()
         .map(|original_documents_chunk| {
-            send_original_documents_data(original_documents_chunk, lmdb_writer_sx.clone())
+            send_original_documents_data(
+                original_documents_chunk,
+                indexer,
+                lmdb_writer_sx.clone(),
+                vectors_field_id,
+                primary_key_id,
+            )
         })
         .collect::<Result<()>>()?;
 
@@ -72,8 +82,9 @@ pub(crate) fn data_from_obkv_documents(
                     &faceted_fields,
                     primary_key_id,
                     geo_fields_ids,
-                    vectors_field_id,
                     &stop_words,
+                    &allowed_separators,
+                    &dictionary,
                     max_positions_per_attributes,
                 )
             })
@@ -238,11 +249,13 @@ fn spawn_extraction_task<FE, FS, M>(
     M::Output: Send,
 {
     rayon::spawn(move || {
+        puffin::profile_scope!("extract_multiple_chunks", name);
         let chunks: Result<M> =
             chunks.into_par_iter().map(|chunk| extract_fn(chunk, indexer)).collect();
         rayon::spawn(move || match chunks {
             Ok(chunks) => {
                 debug!("merge {} database", name);
+                puffin::profile_scope!("merge_multiple_chunks", name);
                 let reader = chunks.merge(merge_fn, &indexer);
                 let _ = lmdb_writer_sx.send(reader.map(serialize_fn));
             }
@@ -257,11 +270,33 @@ fn spawn_extraction_task<FE, FS, M>(
 /// - documents
 fn send_original_documents_data(
     original_documents_chunk: Result<grenad::Reader<File>>,
+    indexer: GrenadParameters,
     lmdb_writer_sx: Sender<Result<TypedChunk>>,
+    vectors_field_id: Option<FieldId>,
+    primary_key_id: FieldId,
 ) -> Result<()> {
     let original_documents_chunk =
         original_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?;
 
+    if let Some(vectors_field_id) = vectors_field_id {
+        let documents_chunk_cloned = original_documents_chunk.clone();
+        let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
+        rayon::spawn(move || {
+            let result = extract_vector_points(
+                documents_chunk_cloned,
+                indexer,
+                primary_key_id,
+                vectors_field_id,
+            );
+            let _ = match result {
+                Ok(vector_points) => {
+                    lmdb_writer_sx_cloned.send(Ok(TypedChunk::VectorPoints(vector_points)))
+                }
+                Err(error) => lmdb_writer_sx_cloned.send(Err(error)),
+            };
+        });
+    }
+
     // TODO: create a custom internal error
     lmdb_writer_sx.send(Ok(TypedChunk::Documents(original_documents_chunk))).unwrap();
     Ok(())
@@ -283,8 +318,9 @@ fn send_and_extract_flattened_documents_data(
     faceted_fields: &HashSet<FieldId>,
     primary_key_id: FieldId,
     geo_fields_ids: Option<(FieldId, FieldId)>,
-    vectors_field_id: Option<FieldId>,
     stop_words: &Option<fst::Set<&[u8]>>,
+    allowed_separators: &Option<&[&str]>,
+    dictionary: &Option<&[&str]>,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<(
     grenad::Reader<CursorClonableMmap>,
@@ -312,25 +348,6 @@ fn send_and_extract_flattened_documents_data(
         });
     }
 
-    if let Some(vectors_field_id) = vectors_field_id {
-        let documents_chunk_cloned = flattened_documents_chunk.clone();
-        let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
-        rayon::spawn(move || {
-            let result = extract_vector_points(
-                documents_chunk_cloned,
-                indexer,
-                primary_key_id,
-                vectors_field_id,
-            );
-            let _ = match result {
-                Ok(vector_points) => {
-                    lmdb_writer_sx_cloned.send(Ok(TypedChunk::VectorPoints(vector_points)))
-                }
-                Err(error) => lmdb_writer_sx_cloned.send(Err(error)),
-            };
-        });
-    }
-
     let (docid_word_positions_chunk, docid_fid_facet_values_chunks): (Result<_>, Result<_>) =
         rayon::join(
             || {
@@ -340,6 +357,8 @@ fn send_and_extract_flattened_documents_data(
                         indexer,
                         searchable_fields,
                         stop_words.as_ref(),
+                        *allowed_separators,
+                        *dictionary,
                         max_positions_per_attributes,
                     )?;
 
@@ -366,6 +385,7 @@ fn send_and_extract_flattened_documents_data(
                     flattened_documents_chunk.clone(),
                     indexer,
                     faceted_fields,
+                    geo_fields_ids,
                 )?;
 
                 // send docid_fid_facet_numbers_chunk to DB writer

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

@@ -214,6 +214,7 @@ pub fn sorter_into_lmdb_database(
     sorter: Sorter<MergeFn>,
     merge: MergeFn,
 ) -> Result<()> {
+    puffin::profile_function!();
     debug!("Writing MTBL sorter...");
     let before = Instant::now();
 

milli/src/update/index_documents/mod.rs

@@ -137,6 +137,8 @@ where
         mut self,
         reader: DocumentsBatchReader<R>,
     ) -> Result<(Self, StdResult<u64, UserError>)> {
+        puffin::profile_function!();
+
         // Early return when there is no document to add
         if reader.is_empty() {
             return Ok((self, Ok(0)));
@@ -175,6 +177,8 @@ where
         mut self,
         to_delete: Vec<String>,
     ) -> Result<(Self, StdResult<u64, UserError>)> {
+        puffin::profile_function!();
+
         // Early return when there is no document to add
         if to_delete.is_empty() {
             return Ok((self, Ok(0)));
@@ -194,6 +198,8 @@ where
 
     #[logging_timer::time("IndexDocuments::{}")]
     pub fn execute(mut self) -> Result<DocumentAdditionResult> {
+        puffin::profile_function!();
+
         if self.added_documents == 0 {
             let number_of_documents = self.index.number_of_documents(self.wtxn)?;
             return Ok(DocumentAdditionResult { indexed_documents: 0, number_of_documents });
@@ -232,6 +238,8 @@ where
         FP: Fn(UpdateIndexingStep) + Sync,
         FA: Fn() -> bool + Sync,
     {
+        puffin::profile_function!();
+
         let TransformOutput {
             primary_key,
             fields_ids_map,
@@ -308,6 +316,12 @@ where
         let vectors_field_id = self.index.fields_ids_map(self.wtxn)?.id("_vectors");
 
         let stop_words = self.index.stop_words(self.wtxn)?;
+        let separators = self.index.allowed_separators(self.wtxn)?;
+        let separators: Option<Vec<_>> =
+            separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
+        let dictionary = self.index.dictionary(self.wtxn)?;
+        let dictionary: Option<Vec<_>> =
+            dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
         let exact_attributes = self.index.exact_attributes_ids(self.wtxn)?;
 
         let pool_params = GrenadParameters {
@@ -322,6 +336,7 @@ where
 
         // Run extraction pipeline in parallel.
         pool.install(|| {
+            puffin::profile_scope!("extract_and_send_grenad_chunks");
             // split obkv file into several chunks
             let original_chunk_iter =
                 grenad_obkv_into_chunks(original_documents, pool_params, documents_chunk_size);
@@ -344,6 +359,8 @@ where
                     geo_fields_ids,
                     vectors_field_id,
                     stop_words,
+                    separators.as_deref(),
+                    dictionary.as_deref(),
                     max_positions_per_attributes,
                     exact_attributes,
                 )
@@ -477,6 +494,8 @@ where
         FP: Fn(UpdateIndexingStep) + Sync,
         FA: Fn() -> bool + Sync,
     {
+        puffin::profile_function!();
+
         // Merged databases are already been indexed, we start from this count;
         let mut databases_seen = MERGED_DATABASE_COUNT;
 
@@ -511,26 +530,36 @@ where
             return Err(Error::InternalError(InternalError::AbortedIndexation));
         }
 
-        let current_prefix_fst = self.index.words_prefixes_fst(self.wtxn)?;
+        let current_prefix_fst;
+        let common_prefix_fst_words_tmp;
+        let common_prefix_fst_words: Vec<_>;
+        let new_prefix_fst_words;
+        let del_prefix_fst_words;
 
-        // We retrieve the common words between the previous and new prefix word fst.
-        let common_prefix_fst_words = fst_stream_into_vec(
-            previous_words_prefixes_fst.op().add(&current_prefix_fst).intersection(),
-        );
-        let common_prefix_fst_words: Vec<_> = common_prefix_fst_words
-            .as_slice()
-            .linear_group_by_key(|x| x.chars().next().unwrap())
-            .collect();
+        {
+            puffin::profile_scope!("compute_prefix_diffs");
 
-        // We retrieve the newly added words between the previous and new prefix word fst.
-        let new_prefix_fst_words = fst_stream_into_vec(
-            current_prefix_fst.op().add(&previous_words_prefixes_fst).difference(),
-        );
+            current_prefix_fst = self.index.words_prefixes_fst(self.wtxn)?;
 
-        // We compute the set of prefixes that are no more part of the prefix fst.
-        let del_prefix_fst_words = fst_stream_into_hashset(
-            previous_words_prefixes_fst.op().add(&current_prefix_fst).difference(),
-        );
+            // We retrieve the common words between the previous and new prefix word fst.
+            common_prefix_fst_words_tmp = fst_stream_into_vec(
+                previous_words_prefixes_fst.op().add(&current_prefix_fst).intersection(),
+            );
+            common_prefix_fst_words = common_prefix_fst_words_tmp
+                .as_slice()
+                .linear_group_by_key(|x| x.chars().next().unwrap())
+                .collect();
+
+            // We retrieve the newly added words between the previous and new prefix word fst.
+            new_prefix_fst_words = fst_stream_into_vec(
+                current_prefix_fst.op().add(&previous_words_prefixes_fst).difference(),
+            );
+
+            // We compute the set of prefixes that are no more part of the prefix fst.
+            del_prefix_fst_words = fst_stream_into_hashset(
+                previous_words_prefixes_fst.op().add(&current_prefix_fst).difference(),
+            );
+        }
 
         databases_seen += 1;
         (self.progress)(UpdateIndexingStep::MergeDataIntoFinalDatabase {
@@ -668,6 +697,8 @@ fn execute_word_prefix_docids(
     common_prefix_fst_words: &[&[String]],
     del_prefix_fst_words: &HashSet<Vec<u8>>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
     let cursor = reader.into_cursor()?;
     let mut builder = WordPrefixDocids::new(txn, word_docids_db, word_prefix_docids_db);
     builder.chunk_compression_type = indexer_config.chunk_compression_type;
@@ -2519,6 +2550,25 @@ mod tests {
         db_snap!(index, word_position_docids, 3, @"74f556b91d161d997a89468b4da1cb8f");
     }
 
+    /// Index multiple different number of vectors in documents.
+    /// Vectors must be of the same length.
+    #[test]
+    fn test_multiple_vectors() {
+        let index = TempIndex::new();
+
+        index.add_documents(documents!([{"id": 0, "_vectors": [[0, 1, 2], [3, 4, 5]] }])).unwrap();
+        index.add_documents(documents!([{"id": 1, "_vectors": [6, 7, 8] }])).unwrap();
+        index
+            .add_documents(
+                documents!([{"id": 2, "_vectors": [[9, 10, 11], [12, 13, 14], [15, 16, 17]] }]),
+            )
+            .unwrap();
+
+        let rtxn = index.read_txn().unwrap();
+        let res = index.search(&rtxn).vector([0.0, 1.0, 2.0]).execute().unwrap();
+        assert_eq!(res.documents_ids.len(), 3);
+    }
+
     #[test]
     fn reproduce_the_bug() {
         /*

milli/src/update/index_documents/transform.rs

@@ -558,6 +558,8 @@ impl<'a, 'i> Transform<'a, 'i> {
     where
         F: Fn(UpdateIndexingStep) + Sync,
     {
+        puffin::profile_function!();
+
         let primary_key = self
             .index
             .primary_key(wtxn)?

milli/src/update/index_documents/typed_chunk.rs

@@ -46,6 +46,66 @@ pub(crate) enum TypedChunk {
     ScriptLanguageDocids(HashMap<(Script, Language), RoaringBitmap>),
 }
 
+impl TypedChunk {
+    pub fn to_debug_string(&self) -> String {
+        match self {
+            TypedChunk::FieldIdDocidFacetStrings(grenad) => {
+                format!("FieldIdDocidFacetStrings {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdDocidFacetNumbers(grenad) => {
+                format!("FieldIdDocidFacetNumbers {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::Documents(grenad) => {
+                format!("Documents {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdWordcountDocids(grenad) => {
+                format!("FieldIdWordcountDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::NewDocumentsIds(grenad) => {
+                format!("NewDocumentsIds {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::WordDocids { word_docids_reader, exact_word_docids_reader } => format!(
+                "WordDocids {{ word_docids_reader: {}, exact_word_docids_reader: {} }}",
+                word_docids_reader.len(),
+                exact_word_docids_reader.len()
+            ),
+            TypedChunk::WordPositionDocids(grenad) => {
+                format!("WordPositionDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::WordFidDocids(grenad) => {
+                format!("WordFidDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::WordPairProximityDocids(grenad) => {
+                format!("WordPairProximityDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetStringDocids(grenad) => {
+                format!("FieldIdFacetStringDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetNumberDocids(grenad) => {
+                format!("FieldIdFacetNumberDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetExistsDocids(grenad) => {
+                format!("FieldIdFacetExistsDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetIsNullDocids(grenad) => {
+                format!("FieldIdFacetIsNullDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetIsEmptyDocids(grenad) => {
+                format!("FieldIdFacetIsEmptyDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::GeoPoints(grenad) => {
+                format!("GeoPoints {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::VectorPoints(grenad) => {
+                format!("VectorPoints {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::ScriptLanguageDocids(grenad) => {
+                format!("ScriptLanguageDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+        }
+    }
+}
+
 /// Write typed chunk in the corresponding LMDB database of the provided index.
 /// Return new documents seen.
 pub(crate) fn write_typed_chunk_into_index(
@@ -54,6 +114,8 @@ pub(crate) fn write_typed_chunk_into_index(
     wtxn: &mut RwTxn,
     index_is_empty: bool,
 ) -> Result<(RoaringBitmap, bool)> {
+    puffin::profile_function!(typed_chunk.to_debug_string());
+
     let mut is_merged_database = false;
     match typed_chunk {
         TypedChunk::Documents(obkv_documents_iter) => {
@@ -350,6 +412,8 @@ where
     FS: for<'a> Fn(&'a [u8], &'a mut Vec<u8>) -> Result<&'a [u8]>,
     FM: Fn(&[u8], &[u8], &mut Vec<u8>) -> Result<()>,
 {
+    puffin::profile_function!(format!("number of entries: {}", data.len()));
+
     let mut buffer = Vec::new();
     let database = database.remap_types::<ByteSlice, ByteSlice>();
 
@@ -392,6 +456,8 @@ where
     FS: for<'a> Fn(&'a [u8], &'a mut Vec<u8>) -> Result<&'a [u8]>,
     FM: Fn(&[u8], &[u8], &mut Vec<u8>) -> Result<()>,
 {
+    puffin::profile_function!(format!("number of entries: {}", data.len()));
+
     if !index_is_empty {
         return write_entries_into_database(
             data,

milli/src/update/prefix_word_pairs/mod.rs

@@ -50,6 +50,8 @@ impl<'t, 'u, 'i> PrefixWordPairsProximityDocids<'t, 'u, 'i> {
         common_prefix_fst_words: &[&'a [String]],
         del_prefix_fst_words: &HashSet<Vec<u8>>,
     ) -> Result<()> {
+        puffin::profile_function!();
+
         index_word_prefix_database(
             self.wtxn,
             self.index.word_pair_proximity_docids,

milli/src/update/prefix_word_pairs/prefix_word.rs

@@ -27,6 +27,8 @@ pub fn index_prefix_word_database(
     chunk_compression_type: CompressionType,
     chunk_compression_level: Option<u32>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
     let max_proximity = max_proximity - 1;
     debug!("Computing and writing the word prefix pair proximity docids into LMDB on disk...");
 

milli/src/update/prefix_word_pairs/word_prefix.rs

@@ -191,6 +191,7 @@ pub fn index_word_prefix_database(
     chunk_compression_type: CompressionType,
     chunk_compression_level: Option<u32>,
 ) -> Result<()> {
+    puffin::profile_function!();
     debug!("Computing and writing the word prefix pair proximity docids into LMDB on disk...");
 
     // Make a prefix trie from the common prefixes that are shorter than self.max_prefix_length

milli/src/update/settings.rs

@@ -1,4 +1,4 @@
-use std::collections::{BTreeSet, HashMap, HashSet};
+use std::collections::{BTreeMap, BTreeSet, HashMap, HashSet};
 use std::result::Result as StdResult;
 
 use charabia::{Normalize, Tokenizer, TokenizerBuilder};
@@ -112,8 +112,11 @@ pub struct Settings<'a, 't, 'u, 'i> {
     sortable_fields: Setting<HashSet<String>>,
     criteria: Setting<Vec<Criterion>>,
     stop_words: Setting<BTreeSet<String>>,
+    non_separator_tokens: Setting<BTreeSet<String>>,
+    separator_tokens: Setting<BTreeSet<String>>,
+    dictionary: Setting<BTreeSet<String>>,
     distinct_field: Setting<String>,
-    synonyms: Setting<HashMap<String, Vec<String>>>,
+    synonyms: Setting<BTreeMap<String, Vec<String>>>,
     primary_key: Setting<String>,
     authorize_typos: Setting<bool>,
     min_word_len_two_typos: Setting<u8>,
@@ -141,6 +144,9 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
             sortable_fields: Setting::NotSet,
             criteria: Setting::NotSet,
             stop_words: Setting::NotSet,
+            non_separator_tokens: Setting::NotSet,
+            separator_tokens: Setting::NotSet,
+            dictionary: Setting::NotSet,
             distinct_field: Setting::NotSet,
             synonyms: Setting::NotSet,
             primary_key: Setting::NotSet,
@@ -205,6 +211,39 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
             if stop_words.is_empty() { Setting::Reset } else { Setting::Set(stop_words) }
     }
 
+    pub fn reset_non_separator_tokens(&mut self) {
+        self.non_separator_tokens = Setting::Reset;
+    }
+
+    pub fn set_non_separator_tokens(&mut self, non_separator_tokens: BTreeSet<String>) {
+        self.non_separator_tokens = if non_separator_tokens.is_empty() {
+            Setting::Reset
+        } else {
+            Setting::Set(non_separator_tokens)
+        }
+    }
+
+    pub fn reset_separator_tokens(&mut self) {
+        self.separator_tokens = Setting::Reset;
+    }
+
+    pub fn set_separator_tokens(&mut self, separator_tokens: BTreeSet<String>) {
+        self.separator_tokens = if separator_tokens.is_empty() {
+            Setting::Reset
+        } else {
+            Setting::Set(separator_tokens)
+        }
+    }
+
+    pub fn reset_dictionary(&mut self) {
+        self.dictionary = Setting::Reset;
+    }
+
+    pub fn set_dictionary(&mut self, dictionary: BTreeSet<String>) {
+        self.dictionary =
+            if dictionary.is_empty() { Setting::Reset } else { Setting::Set(dictionary) }
+    }
+
     pub fn reset_distinct_field(&mut self) {
         self.distinct_field = Setting::Reset;
     }
@@ -217,7 +256,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         self.synonyms = Setting::Reset;
     }
 
-    pub fn set_synonyms(&mut self, synonyms: HashMap<String, Vec<String>>) {
+    pub fn set_synonyms(&mut self, synonyms: BTreeMap<String, Vec<String>>) {
         self.synonyms = if synonyms.is_empty() { Setting::Reset } else { Setting::Set(synonyms) }
     }
 
@@ -303,6 +342,8 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         FP: Fn(UpdateIndexingStep) + Sync,
         FA: Fn() -> bool + Sync,
     {
+        puffin::profile_function!();
+
         let fields_ids_map = self.index.fields_ids_map(self.wtxn)?;
         // if the settings are set before any document update, we don't need to do anything, and
         // will set the primary key during the first document addition.
@@ -450,14 +491,89 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         }
     }
 
+    fn update_non_separator_tokens(&mut self) -> Result<bool> {
+        let changes = match self.non_separator_tokens {
+            Setting::Set(ref non_separator_tokens) => {
+                let current = self.index.non_separator_tokens(self.wtxn)?;
+
+                // Does the new list differ from the previous one?
+                if current.map_or(true, |current| &current != non_separator_tokens) {
+                    self.index.put_non_separator_tokens(self.wtxn, non_separator_tokens)?;
+                    true
+                } else {
+                    false
+                }
+            }
+            Setting::Reset => self.index.delete_non_separator_tokens(self.wtxn)?,
+            Setting::NotSet => false,
+        };
+
+        // the synonyms must be updated if non separator tokens have been updated.
+        if changes && self.synonyms == Setting::NotSet {
+            self.synonyms = Setting::Set(self.index.user_defined_synonyms(self.wtxn)?);
+        }
+
+        Ok(changes)
+    }
+
+    fn update_separator_tokens(&mut self) -> Result<bool> {
+        let changes = match self.separator_tokens {
+            Setting::Set(ref separator_tokens) => {
+                let current = self.index.separator_tokens(self.wtxn)?;
+
+                // Does the new list differ from the previous one?
+                if current.map_or(true, |current| &current != separator_tokens) {
+                    self.index.put_separator_tokens(self.wtxn, separator_tokens)?;
+                    true
+                } else {
+                    false
+                }
+            }
+            Setting::Reset => self.index.delete_separator_tokens(self.wtxn)?,
+            Setting::NotSet => false,
+        };
+
+        // the synonyms must be updated if separator tokens have been updated.
+        if changes && self.synonyms == Setting::NotSet {
+            self.synonyms = Setting::Set(self.index.user_defined_synonyms(self.wtxn)?);
+        }
+
+        Ok(changes)
+    }
+
+    fn update_dictionary(&mut self) -> Result<bool> {
+        let changes = match self.dictionary {
+            Setting::Set(ref dictionary) => {
+                let current = self.index.dictionary(self.wtxn)?;
+
+                // Does the new list differ from the previous one?
+                if current.map_or(true, |current| &current != dictionary) {
+                    self.index.put_dictionary(self.wtxn, dictionary)?;
+                    true
+                } else {
+                    false
+                }
+            }
+            Setting::Reset => self.index.delete_dictionary(self.wtxn)?,
+            Setting::NotSet => false,
+        };
+
+        // the synonyms must be updated if dictionary has been updated.
+        if changes && self.synonyms == Setting::NotSet {
+            self.synonyms = Setting::Set(self.index.user_defined_synonyms(self.wtxn)?);
+        }
+
+        Ok(changes)
+    }
+
     fn update_synonyms(&mut self) -> Result<bool> {
         match self.synonyms {
-            Setting::Set(ref synonyms) => {
+            Setting::Set(ref user_synonyms) => {
                 fn normalize(tokenizer: &Tokenizer, text: &str) -> Vec<String> {
                     tokenizer
                         .tokenize(text)
                         .filter_map(|token| {
-                            if token.is_word() {
+                            if token.is_word() && !token.lemma().is_empty() {
                                 Some(token.lemma().to_string())
                             } else {
                                 None
@@ -471,19 +587,39 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
                 if let Some(ref stop_words) = stop_words {
                     builder.stop_words(stop_words);
                 }
+
+                let separators = self.index.allowed_separators(self.wtxn)?;
+                let separators: Option<Vec<_>> =
+                    separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
+                if let Some(ref separators) = separators {
+                    builder.separators(separators);
+                }
+
+                let dictionary = self.index.dictionary(self.wtxn)?;
+                let dictionary: Option<Vec<_>> =
+                    dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
+                if let Some(ref dictionary) = dictionary {
+                    builder.words_dict(dictionary);
+                }
+
                 let tokenizer = builder.build();
 
                 let mut new_synonyms = HashMap::new();
-                for (word, synonyms) in synonyms {
+                for (word, synonyms) in user_synonyms {
                     // Normalize both the word and associated synonyms.
                     let normalized_word = normalize(&tokenizer, word);
-                    let normalized_synonyms =
-                        synonyms.iter().map(|synonym| normalize(&tokenizer, synonym));
+                    let normalized_synonyms: Vec<_> = synonyms
+                        .iter()
+                        .map(|synonym| normalize(&tokenizer, synonym))
+                        .filter(|synonym| !synonym.is_empty())
+                        .collect();
 
                     // Store the normalized synonyms under the normalized word,
                     // merging the possible duplicate words.
-                    let entry = new_synonyms.entry(normalized_word).or_insert_with(Vec::new);
-                    entry.extend(normalized_synonyms);
+                    if !normalized_word.is_empty() && !normalized_synonyms.is_empty() {
+                        let entry = new_synonyms.entry(normalized_word).or_insert_with(Vec::new);
+                        entry.extend(normalized_synonyms.into_iter());
+                    }
                 }
 
                 // Make sure that we don't have duplicate synonyms.
@@ -495,7 +631,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
                 let old_synonyms = self.index.synonyms(self.wtxn)?;
 
                 if new_synonyms != old_synonyms {
-                    self.index.put_synonyms(self.wtxn, &new_synonyms)?;
+                    self.index.put_synonyms(self.wtxn, &new_synonyms, user_synonyms)?;
                     Ok(true)
                 } else {
                     Ok(false)
@@ -755,11 +891,17 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         let faceted_updated = old_faceted_fields != new_faceted_fields;
 
         let stop_words_updated = self.update_stop_words()?;
+        let non_separator_tokens_updated = self.update_non_separator_tokens()?;
+        let separator_tokens_updated = self.update_separator_tokens()?;
+        let dictionary_updated = self.update_dictionary()?;
         let synonyms_updated = self.update_synonyms()?;
         let searchable_updated = self.update_searchable()?;
         let exact_attributes_updated = self.update_exact_attributes()?;
 
         if stop_words_updated
+            || non_separator_tokens_updated
+            || separator_tokens_updated
+            || dictionary_updated
             || faceted_updated
             || synonyms_updated
             || searchable_updated
@@ -776,7 +918,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
 mod tests {
     use big_s::S;
     use heed::types::ByteSlice;
-    use maplit::{btreeset, hashmap, hashset};
+    use maplit::{btreemap, btreeset, hashset};
 
     use super::*;
     use crate::error::Error;
@@ -1242,7 +1384,7 @@ mod tests {
         // In the same transaction provide some synonyms
         index
             .update_settings_using_wtxn(&mut wtxn, |settings| {
-                settings.set_synonyms(hashmap! {
+                settings.set_synonyms(btreemap! {
                     "blini".to_string() => vec!["crepes".to_string()],
                     "super like".to_string() => vec!["love".to_string()],
                     "puppies".to_string() => vec!["dogs".to_string(), "doggos".to_string()]
@@ -1285,6 +1427,43 @@ mod tests {
         assert!(result.documents_ids.is_empty());
     }
 
+    #[test]
+    fn thai_synonyms() {
+        let mut index = TempIndex::new();
+        index.index_documents_config.autogenerate_docids = true;
+
+        let mut wtxn = index.write_txn().unwrap();
+        // Send 3 documents with ids from 1 to 3.
+        index
+            .add_documents_using_wtxn(
+                &mut wtxn,
+                documents!([
+                    { "name": "ยี่ปุ่น" },
+                    { "name": "ญี่ปุ่น" },
+                ]),
+            )
+            .unwrap();
+
+        // In the same transaction provide some synonyms
+        index
+            .update_settings_using_wtxn(&mut wtxn, |settings| {
+                settings.set_synonyms(btreemap! {
+                    "japanese".to_string() => vec![S("ญี่ปุ่น"), S("ยี่ปุ่น")],
+                });
+            })
+            .unwrap();
+        wtxn.commit().unwrap();
+
+        // Ensure synonyms are effectively stored
+        let rtxn = index.read_txn().unwrap();
+        let synonyms = index.synonyms(&rtxn).unwrap();
+        assert!(!synonyms.is_empty()); // at this point the index should return something
+
+        // Check that we can use synonyms
+        let result = index.search(&rtxn).query("japanese").execute().unwrap();
+        assert_eq!(result.documents_ids.len(), 2);
+    }
+
     #[test]
     fn setting_searchable_recomputes_other_settings() {
         let index = TempIndex::new();
@@ -1538,6 +1717,9 @@ mod tests {
                     sortable_fields,
                     criteria,
                     stop_words,
+                    non_separator_tokens,
+                    separator_tokens,
+                    dictionary,
                     distinct_field,
                     synonyms,
                     primary_key,
@@ -1556,6 +1738,9 @@ mod tests {
                 assert!(matches!(sortable_fields, Setting::NotSet));
                 assert!(matches!(criteria, Setting::NotSet));
                 assert!(matches!(stop_words, Setting::NotSet));
+                assert!(matches!(non_separator_tokens, Setting::NotSet));
+                assert!(matches!(separator_tokens, Setting::NotSet));
+                assert!(matches!(dictionary, Setting::NotSet));
                 assert!(matches!(distinct_field, Setting::NotSet));
                 assert!(matches!(synonyms, Setting::NotSet));
                 assert!(matches!(primary_key, Setting::NotSet));

milli/src/update/word_prefix_docids.rs

@@ -45,6 +45,8 @@ impl<'t, 'u, 'i> WordPrefixDocids<'t, 'u, 'i> {
         common_prefix_fst_words: &[&[String]],
         del_prefix_fst_words: &HashSet<Vec<u8>>,
     ) -> Result<()> {
+        puffin::profile_function!();
+
         // It is forbidden to keep a mutable reference into the database
         // and write into it at the same time, therefore we write into another file.
         let mut prefix_docids_sorter = create_sorter(

milli/src/update/words_prefix_integer_docids.rs

@@ -50,6 +50,7 @@ impl<'t, 'u, 'i> WordPrefixIntegerDocids<'t, 'u, 'i> {
         common_prefix_fst_words: &[&[String]],
         del_prefix_fst_words: &HashSet<Vec<u8>>,
     ) -> Result<()> {
+        puffin::profile_function!();
         debug!("Computing and writing the word levels integers docids into LMDB on disk...");
 
         let mut prefix_integer_docids_sorter = create_sorter(

milli/src/update/words_prefixes_fst.rs

@@ -42,6 +42,8 @@ impl<'t, 'u, 'i> WordsPrefixesFst<'t, 'u, 'i> {
 
     #[logging_timer::time("WordsPrefixesFst::{}")]
     pub fn execute(self) -> Result<()> {
+        puffin::profile_function!();
+
         let words_fst = self.index.words_fst(self.wtxn)?;
 
         let mut current_prefix = vec![SmallString32::new(); self.max_prefix_length];

milli/tests/search/mod.rs

@@ -5,7 +5,7 @@ use std::io::Cursor;
 use big_s::S;
 use either::{Either, Left, Right};
 use heed::EnvOpenOptions;
-use maplit::{hashmap, hashset};
+use maplit::{btreemap, hashset};
 use milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
 use milli::{AscDesc, Criterion, DocumentId, Index, Member, Object, TermsMatchingStrategy};
@@ -51,7 +51,7 @@ pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
         S("tag"),
         S("asc_desc_rank"),
     });
-    builder.set_synonyms(hashmap! {
+    builder.set_synonyms(btreemap! {
         S("hello") => vec![S("good morning")],
         S("world") => vec![S("earth")],
         S("america") => vec![S("the united states")],

permissive-json-pointer/src/lib.rs

@@ -186,12 +186,16 @@ fn create_value(value: &Document, mut selectors: HashSet<&str>) -> Document {
                     let array = create_array(array, &sub_selectors);
                     if !array.is_empty() {
                         new_value.insert(key.to_string(), array.into());
+                    } else {
+                        new_value.insert(key.to_string(), Value::Array(vec![]));
                     }
                 }
                 Value::Object(object) => {
                     let object = create_value(object, sub_selectors);
                     if !object.is_empty() {
                         new_value.insert(key.to_string(), object.into());
+                    } else {
+                        new_value.insert(key.to_string(), Value::Object(Map::new()));
                     }
                 }
                 _ => (),
@@ -211,6 +215,8 @@ fn create_array(array: &[Value], selectors: &HashSet<&str>) -> Vec<Value> {
                 let array = create_array(array, selectors);
                 if !array.is_empty() {
                     res.push(array.into());
+                } else {
+                    res.push(Value::Array(vec![]));
                 }
             }
             Value::Object(object) => {
@@ -637,6 +643,24 @@ mod tests {
         );
     }
 
+    #[test]
+    fn empty_array_object_return_empty() {
+        let value: Value = json!({
+            "array": [],
+            "object": {},
+        });
+        let value: &Document = value.as_object().unwrap();
+
+        let res: Value = select_values(value, vec!["array.name", "object.name"]).into();
+        assert_eq!(
+            res,
+            json!({
+                "array": [],
+                "object": {},
+            })
+        );
+    }
+
     #[test]
     fn all_conflict_variation() {
         let value: Value = json!({