Fix clippy

Make the search and the indexing work
Be able to set and reset settings
2025-07-18 12:20:48 +00:00 · 2023-07-24 18:42:26 +02:00 · 2023-07-24 18:35:20 +02:00 · 2023-07-24 17:00:18 +02:00 · 2023-07-20 11:15:10 +02:00 · 2023-07-19 09:44:01 +00:00
49 changed files with 1597 additions and 193 deletions
--- a/.github/workflows/test-suite.yml
+++ b/.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
+      - name: Setup test with Rust nightly
        if: github.event_name == 'schedule'
        uses: actions-rs/toolchain@v1
        with:
          toolchain: nightly
          override: true
      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
      - 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@v2.5.0
      - name: Run cargo check without any default features
        uses: actions-rs/cargo@v1
        with:
@ -117,17 +117,17 @@ jobs:
        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@v2.5.0
      - name: Run tests in debug
        uses: actions-rs/cargo@v1
        with:
@ -165,7 +165,7 @@ jobs:
          override: true
          components: clippy
      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
      - 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@v2.5.0
      - 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
--- a/Cargo.lock
+++ b/Cargo.lock
@ -1973,6 +1973,7 @@ dependencies = [
 "meilisearch-types",
 "nelson",
 "page_size 0.5.0",
+ "puffin",
 "roaring",
 "serde",
 "serde_json",
@ -2498,6 +2499,12 @@ dependencies = [
 "syn 1.0.109",
 ]

+[[package]]
+name = "lz4_flex"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b8c72594ac26bfd34f2d99dfced2edfaddfe8a476e3ff2ca0eb293d925c4f83"
+
 [[package]]
 name = "manifest-dir-macros"
 version = "0.1.17"
@ -2587,6 +2594,8 @@ dependencies = [
 "pin-project-lite",
 "platform-dirs",
 "prometheus",
+ "puffin",
+ "puffin_http",
 "rand",
 "rayon",
 "regex",
@ -2731,6 +2740,7 @@ dependencies = [
 "obkv",
 "once_cell",
 "ordered-float",
+ "puffin",
 "rand",
 "rand_pcg",
 "rayon",
@ -3213,9 +3223,9 @@ dependencies = [

 [[package]]
 name = "proc-macro2"
-version = "1.0.59"
+version = "1.0.64"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6aeca18b86b413c660b781aa319e4e2648a3e6f9eadc9b47e9038e6fe9f3451b"
+checksum = "78803b62cbf1f46fde80d7c0e803111524b9877184cfe7c3033659490ac7a7da"
 dependencies = [
 "unicode-ident",
 ]
@ -3256,6 +3266,35 @@ version = "2.28.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "106dd99e98437432fed6519dedecfade6a06a73bb7b2a1e019fdd2bee5778d94"

+[[package]]
+name = "puffin"
+version = "0.16.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76425abd4e1a0ad4bd6995dd974b52f414fca9974171df8e3708b3e660d05a21"
+dependencies = [
+ "anyhow",
+ "bincode",
+ "byteorder",
+ "cfg-if",
+ "instant",
+ "lz4_flex",
+ "once_cell",
+ "parking_lot",
+ "serde",
+]
+
+[[package]]
+name = "puffin_http"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13bffc600c35913d282ae1e96a6ffcdf36dc7a7cdb9310e0ba15914d258c8193"
+dependencies = [
+ "anyhow",
+ "crossbeam-channel",
+ "log",
+ "puffin",
+]
+
 [[package]]
 name = "quote"
 version = "1.0.28"
--- a/PROFILING.md
+++ b/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.
--- a/README.md
+++ b/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">
@ -24,72 +28,72 @@
 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

-Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch). No credit card required.
+Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch). Get started with a 14-day free trial! No credit card required.

 ## 🧰 SDKs & integration tools

 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.

-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.

--- a/assets/profiling-example.png
+++ b/assets/profiling-example.png
--- a/dump/src/lib.rs
+++ b/dump/src/lib.rs
@ -261,6 +261,9 @@ 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,
--- a/dump/src/reader/compat/v5_to_v6.rs
+++ b/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 {
--- a/index-scheduler/Cargo.toml
+++ b/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"] }
--- a/index-scheduler/src/batch.rs
+++ b/index-scheduler/src/batch.rs
@ -471,6 +471,8 @@ 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;

@ -575,6 +577,9 @@ 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.
@ -1111,6 +1116,8 @@ 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()?;
--- a/index-scheduler/src/lib.rs
+++ b/index-scheduler/src/lib.rs
@ -1032,6 +1032,8 @@ 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)?;
--- a/meilisearch-types/src/error.rs
+++ b/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 ;
--- a/meilisearch-types/src/settings.rs
+++ b/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(),
@ -459,6 +502,11 @@ 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
@ -520,6 +568,9 @@ 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 +693,9 @@ 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 +717,9 @@ 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,
--- a/meilisearch/Cargo.toml
+++ b/meilisearch/Cargo.toml
@ -67,6 +67,8 @@ 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"
@ -133,6 +135,7 @@ zip = { version = "0.6.4", optional = true }
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
+profile-with-puffin = ["dep:puffin_http"]
 mini-dashboard = [
    "actix-web-static-files",
    "static-files",
--- a/meilisearch/src/main.rs
+++ b/meilisearch/src/main.rs
@ -29,6 +29,10 @@ 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"
--- a/meilisearch/src/routes/indexes/settings.rs
+++ b/meilisearch/src/routes/indexes/settings.rs
@ -309,6 +309,81 @@ 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,
--- a/meilisearch/src/search.rs
+++ b/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);
--- a/meilisearch/tests/dumps/mod.rs
+++ b/meilisearch/tests/dumps/mod.rs
--- a/meilisearch/tests/settings/get_settings.rs
+++ b/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["non_separator_tokens"], json!([]));
+    assert_eq!(settings["separator_tokens"], json!([]));
+    assert_eq!(settings["dictionary"], json!([]));
    assert_eq!(
        settings["faceting"],
        json!({
--- a/meilisearch/tests/settings/mod.rs
+++ b/meilisearch/tests/settings/mod.rs
@ -1,3 +1,4 @@
 mod distinct;
 mod errors;
 mod get_settings;
+mod tokenizer_customization;
--- a/meilisearch/tests/settings/tokenizer_customization.rs
+++ b/meilisearch/tests/settings/tokenizer_customization.rs
@ -0,0 +1,196 @@
+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;
+}
--- a/milli/Cargo.toml
+++ b/milli/Cargo.toml
@ -67,6 +67,9 @@ filter-parser = { path = "../filter-parser" }
 # documents words self-join
 itertools = "0.10.5"

+# profiling
+puffin = "0.16.0"
+
 # logging
 log = "0.4.17"
 logging_timer = "1.1.0"
--- a/milli/src/index.rs
+++ b/milli/src/index.rs
@ -1,5 +1,5 @@
 use std::borrow::Cow;
-use std::collections::{HashMap, HashSet};
+use std::collections::{BTreeSet, HashMap, HashSet};
 use std::fs::File;
 use std::mem::size_of;
 use std::path::Path;
@ -60,6 +60,9 @@ 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 WORDS_FST_KEY: &str = "words-fst";
@ -1048,6 +1051,87 @@ 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(
--- a/milli/src/search/new/mod.rs
+++ b/milli/src/search/new/mod.rs
@ -479,6 +479,20 @@ 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);
--- a/milli/src/update/clear_documents.rs
+++ b/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,
--- a/milli/src/update/delete_documents.rs
+++ b/milli/src/update/delete_documents.rs
@ -110,6 +110,8 @@ 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()?;

--- a/milli/src/update/index_documents/enrich.rs
+++ b/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)?;
--- a/milli/src/update/index_documents/extract/extract_docid_word_positions.rs
+++ b/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<&Vec<&str>>,
+    dictionary: Option<&Vec<&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 +54,14 @@ 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 {
+        // let dictionary: Vec<_> = dictionary.iter().map(String::as_str).collect();
+        tokenizer_builder.words_dict(dictionary.as_slice());
+    }
+    if let Some(separators) = allowed_separators {
+        // let separators: Vec<_> = separators.iter().map(String::as_str).collect();
+        tokenizer_builder.separators(separators.as_slice());
+    }
    let tokenizer = tokenizer_builder.build();

    let mut cursor = obkv_documents.into_cursor()?;
--- a/milli/src/update/index_documents/extract/extract_facet_number_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/extract_facet_string_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
+++ b/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
@ -34,6 +34,8 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
    indexer: GrenadParameters,
    faceted_fields: &HashSet<FieldId>,
 ) -> Result<ExtractedFacetValues> {
+    puffin::profile_function!();
+
    let max_memory = indexer.max_memory_by_thread();

    let mut fid_docid_facet_numbers_sorter = create_sorter(
--- a/milli/src/update/index_documents/extract/extract_fid_word_count_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/extract_geo_points.rs
+++ b/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,
--- a/milli/src/update/index_documents/extract/extract_vector_points.rs
+++ b/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,
--- a/milli/src/update/index_documents/extract/extract_word_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/extract_word_fid_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/extract_word_position_docids.rs
+++ b/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(
--- a/milli/src/update/index_documents/extract/mod.rs
+++ b/milli/src/update/index_documents/extract/mod.rs
@ -49,9 +49,13 @@ 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<Vec<&str>>,
+    dictionary: Option<Vec<&str>>,
    max_positions_per_attributes: Option<u32>,
    exact_attributes: HashSet<FieldId>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
    original_obkv_chunks
        .par_bridge()
        .map(|original_documents_chunk| {
@ -74,6 +78,8 @@ pub(crate) fn data_from_obkv_documents(
                    geo_fields_ids,
                    vectors_field_id,
                    &stop_words,
+                    &allowed_separators,
+                    &dictionary,
                    max_positions_per_attributes,
                )
            })
@ -238,11 +244,13 @@ 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));
            }
@ -285,6 +293,8 @@ fn send_and_extract_flattened_documents_data(
    geo_fields_ids: Option<(FieldId, FieldId)>,
    vectors_field_id: Option<FieldId>,
    stop_words: &Option<fst::Set<&[u8]>>,
+    allowed_separators: &Option<Vec<&str>>,
+    dictionary: &Option<Vec<&str>>,
    max_positions_per_attributes: Option<u32>,
 ) -> Result<(
    grenad::Reader<CursorClonableMmap>,
@ -340,6 +350,8 @@ fn send_and_extract_flattened_documents_data(
                        indexer,
                        searchable_fields,
                        stop_words.as_ref(),
+                        allowed_separators.as_ref(),
+                        dictionary.as_ref(),
                        max_positions_per_attributes,
                    )?;

--- a/milli/src/update/index_documents/helpers/grenad_helpers.rs
+++ b/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();

--- a/milli/src/update/index_documents/mod.rs
+++ b/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,
+                    dictionary,
                    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;
--- a/milli/src/update/index_documents/transform.rs
+++ b/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)?
--- a/milli/src/update/index_documents/typed_chunk.rs
+++ b/milli/src/update/index_documents/typed_chunk.rs
@ -49,6 +49,66 @@ 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(
@ -57,6 +117,8 @@ 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) => {
@ -336,6 +398,8 @@ 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>();

@ -378,6 +442,8 @@ 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,
--- a/milli/src/update/prefix_word_pairs/mod.rs
+++ b/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,
--- a/milli/src/update/prefix_word_pairs/prefix_word.rs
+++ b/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...");

--- a/milli/src/update/prefix_word_pairs/word_prefix.rs
+++ b/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
--- a/milli/src/update/settings.rs
+++ b/milli/src/update/settings.rs
@ -112,6 +112,9 @@ 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>>>,
    primary_key: Setting<String>,
@ -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;
    }
@ -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.
@ -449,6 +490,60 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
        }
    }

+    fn update_non_separator_tokens(&mut self) -> Result<bool> {
+        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)?;
+                    Ok(true)
+                } else {
+                    Ok(false)
+                }
+            }
+            Setting::Reset => Ok(self.index.delete_non_separator_tokens(self.wtxn)?),
+            Setting::NotSet => Ok(false),
+        }
+    }
+
+    fn update_separator_tokens(&mut self) -> Result<bool> {
+        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)?;
+                    Ok(true)
+                } else {
+                    Ok(false)
+                }
+            }
+            Setting::Reset => Ok(self.index.delete_separator_tokens(self.wtxn)?),
+            Setting::NotSet => Ok(false),
+        }
+    }
+
+    fn update_dictionary(&mut self) -> Result<bool> {
+        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)?;
+                    Ok(true)
+                } else {
+                    Ok(false)
+                }
+            }
+            Setting::Reset => Ok(self.index.delete_dictionary(self.wtxn)?),
+            Setting::NotSet => Ok(false),
+        }
+    }
+
    fn update_synonyms(&mut self) -> Result<bool> {
        match self.synonyms {
            Setting::Set(ref synonyms) => {
@ -754,11 +849,17 @@ 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
@ -1537,6 +1638,9 @@ mod tests {
                    sortable_fields,
                    criteria,
                    stop_words,
+                    non_separator_tokens,
+                    separator_tokens,
+                    dictionary,
                    distinct_field,
                    synonyms,
                    primary_key,
@ -1555,6 +1659,9 @@ 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));
--- a/milli/src/update/word_prefix_docids.rs
+++ b/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(
--- a/milli/src/update/words_prefix_integer_docids.rs
+++ b/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(
--- a/milli/src/update/words_prefixes_fst.rs
+++ b/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];
Author	SHA1	Message	Date
ManyTheFish	d4ff59fcf5	Fix clippy	2023-07-24 18:42:26 +02:00
ManyTheFish	9c485f8563	Make the search and the indexing work	2023-07-24 18:35:20 +02:00
ManyTheFish	d8d12d5979	Be able to set and reset settings	2023-07-24 17:00:18 +02:00
ManyTheFish	0597a97c84	Update tests	2023-07-20 11:15:10 +02:00
meili-bors[bot]	2dfbb6813a	Merge #3913 3913: Expose a Puffin server to profile the indexing process r=Kerollmops a=Kerollmops This PR exposes a puffin HTTP server to expose the internal timing it takes to index documents, delete documents, or update the settings of an index. <img width="1752" alt="Capture d’écran 2023-07-10 à 18 44 58" src="https://github.com/meilisearch/meilisearch/assets/3610253/a3c7a6bf-db5b-42f4-8be1-c4e31c869843"> ## To be done - [x] Move the puffin HTTP server under a feature flag. - [x] Use [the `puffin::set_scopes_on` function](https://docs.rs/puffin/latest/puffin/fn.set_scopes_on.html) to toggle it (by using the feature directly). When this function is called with `false`, [a call to `profile_scope!` talked 1-2ns](https://docs.rs/puffin/latest/puffin/fn.set_scopes_on.html). - [x] Create a _PROFILING.md_ file explaining how to use it. - [x] Explain that merging scopes on the interface is not always useful. - [x] Add more info on the number of batched tasks (using the `puffin::profile_scope!` macro data). - I added more info, but that's more continuous work when we consider we need more info here and there. - [x] Clean up some scopes, and don't touch too much code to inject puffin. - I am not sure that the _index_documents/mod.rs_ function is that complex with the addition of the scope. - [x] Think about what we consider frames. One indexation operation or the wall program. When must we stop the frame, then? - What we consider a frame is one single `IndexScheduler::tick` execution. - We can change that later. Co-authored-by: Kerollmops <clement@meilisearch.com> Co-authored-by: Clément Renault <clement@meilisearch.com>	2023-07-19 09:44:01 +00:00
Clément Renault	8f589a5cce	Introduce a PROFILING.md tutorial to profile Meilisearch	2023-07-18 17:38:13 +02:00
Clément Renault	0b8bbd8750	Toggle the puffin profiling with a feature flag	2023-07-18 17:38:13 +02:00
Kerollmops	eef95de30e	First iteration on exposing puffin profiling	2023-07-18 17:38:13 +02:00
meili-bors[bot]	13a13a4862	Merge #3932 3932: Add UTM tracking to README r=gillian-meilisearch a=Strift # Pull Request Hi `@macraig` `@curquiza` 👋 ## Related issue N/A ## What does this PR do? This PR adds UTM tracking to the links in the README. It add UTM params to: - links in the nav - links to where2watch - links in the Features section - Docs & Getting started links (cc `@guimachiavelli)` - links in the SDKs section - links in the Advanced usage section - links in the Telemetry section - links in the Get in touch section Additionally, this PR adds a link to the Meilisearch logo (there is currently none.) ## On the UTM pattern All links in this PR use the new convention `@gmourier` and I agreed on: - utm_campaign=oss - utm_source=github - utm_medium=meilisearch - utm_content= where the link is in the page It's worth considering updating the tracking link for the Cloud, which is the only one that doesn’t follow the new convention. It is currently using `utm_campaign=oss&utm_source=engine&utm_medium=meilisearch`. Merging analytics from different UTMs is doable on Amplitude, but can't be done in Fathom. Plus, having two different conventions creates knowledge overhead, and is bound to result in corrupt analytics at some point. I suggest we change the Cloud UTM trackers too — the sooner we eat the frog, the better imo. ## 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: Strift <strift@Strifts-MacBook-Pro.local> Co-authored-by: Strift <laurent@meilisearch.com>	2023-07-18 13:42:50 +00:00
Strift	e691c92ed5	Replace UTM link on Cloud	2023-07-18 14:48:00 +02:00
Strift	928ab2f9b1	Add UTM params to contact section links	2023-07-14 18:24:03 +02:00
Strift	7c18a9375f	Add UTM params to telemetry section links	2023-07-14 18:19:46 +02:00
Strift	05a311f9be	Add UTM params to Advanced usage links	2023-07-14 18:17:51 +02:00
Strift	9b1b9b409e	Add UTM params to SDKs logos link	2023-07-14 18:17:28 +02:00
Strift	7f555f23e8	Add UTM params to SDKs section links	2023-07-14 18:15:17 +02:00
Strift	a0bfc9f63a	Add UTM params to docs & getting started links	2023-07-14 18:02:21 +02:00
Strift	3155264381	Add UTM params to features links	2023-07-14 17:51:25 +02:00
Strift	42400c381e	Add UTM on demo link	2023-07-14 17:43:05 +02:00
Strift	08c7dab528	Add UTM on demo gif	2023-07-14 17:40:37 +02:00
Strift	8590687515	Add UTM params to nav links	2023-07-14 17:34:45 +02:00
Strift	8f5d127b1e	Add links on Meilisearch logo	2023-07-14 17:26:06 +02:00
meili-bors[bot]	2b4160ebb9	Merge #3918 3918: Update and fix the Test Suite CI r=dureuill a=Kerollmops This Pull Request renames the _Run test with Rust_ into _Setup test with Rust_ for more clarity and `cargo update -p proc-macro2` to make the project compile with the latest Rust Nightly. Co-authored-by: Kerollmops <clement@meilisearch.com>	2023-07-12 13:18:25 +00:00
Kerollmops	8ba1c8f88f	Update proc-macro2 to compile with the latest nightly	2023-07-12 11:47:27 +02:00
Kerollmops	8e7edf8ea7	Rename the jobs in the CI for clarity	2023-07-12 11:16:01 +02:00
meili-bors[bot]	9daccdf7f0	Merge #3895 3895: Update README.md r=curquiza a=ferdi05 Adding the free-trial option # Pull Request ## Related issue Fixes #<issue_number> ## What does this PR do? - ... ## PR checklist Please check if your PR fulfills the following requirements: - [ ] Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)? - [ ] Have you read the contributing guidelines? - [ ] 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: Ferdinand Boas <ferdinand.boas@gmail.com>	2023-07-10 11:26:47 +00:00
Ferdinand Boas	437ee55c57	Update README.md Co-authored-by: Guillaume Mourier <guillaume@meilisearch.com>	2023-07-06 12:15:52 +02:00
Ferdinand Boas	b1717865ea	Update README.md Adding the free-trial option	2023-07-06 11:52:35 +02:00
meili-bors[bot]	176f716292	Merge #3871 3871: Bump Swatinem/rust-cache from 2.4.0 to 2.5.0 r=curquiza a=dependabot[bot] Bumps [Swatinem/rust-cache](https://github.com/swatinem/rust-cache) from 2.4.0 to 2.5.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/swatinem/rust-cache/releases">Swatinem/rust-cache's releases</a>.</em></p> <blockquote> <h2>v2.5.0</h2> <h2>What's Changed</h2> <ul> <li>feat: Rm workspace crates version before caching by <a href="https://github.com/NobodyXu"><code>`@NobodyXu</code></a>` in <a href="https://redirect.github.com/Swatinem/rust-cache/pull/147">Swatinem/rust-cache#147</a></li> <li>feat: Add hash of <code>.cargo/config.toml</code> to key by <a href="https://github.com/NobodyXu"><code>`@NobodyXu</code></a>` in <a href="https://redirect.github.com/Swatinem/rust-cache/pull/149">Swatinem/rust-cache#149</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/NobodyXu"><code>`@NobodyXu</code></a>` made their first contribution in <a href="https://redirect.github.com/Swatinem/rust-cache/pull/147">Swatinem/rust-cache#147</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/Swatinem/rust-cache/compare/v2.4.0...v2.5.0">https://github.com/Swatinem/rust-cache/compare/v2.4.0...v2.5.0</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/Swatinem/rust-cache/blob/master/CHANGELOG.md">Swatinem/rust-cache's changelog</a>.</em></p> <blockquote> <h1>Changelog</h1> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="`2656b87321`"><code>2656b87</code></a> 2.5.0</li> <li><a href="`715970feed`"><code>715970f</code></a> feat: Add hash of <code>.cargo/config.toml</code> to key (<a href="https://redirect.github.com/swatinem/rust-cache/issues/149">#149</a>)</li> <li><a href="`3d4000164d`"><code>3d40001</code></a> feat: Rm workspace crates version before caching (<a href="https://redirect.github.com/swatinem/rust-cache/issues/147">#147</a>)</li> <li>See full diff in <a href="https://github.com/swatinem/rust-cache/compare/v2.4.0...v2.5.0">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=Swatinem/rust-cache&package-manager=github_actions&previous-version=2.4.0&new-version=2.5.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) You can trigger a rebase of this PR by commenting ``@dependabot` rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - ``@dependabot` rebase` will rebase this PR - ``@dependabot` recreate` will recreate this PR, overwriting any edits that have been made to it - ``@dependabot` merge` will merge this PR after your CI passes on it - ``@dependabot` squash and merge` will squash and merge this PR after your CI passes on it - ``@dependabot` cancel merge` will cancel a previously requested merge and block automerging - ``@dependabot` reopen` will reopen this PR if it is closed - ``@dependabot` close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - ``@dependabot` ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - ``@dependabot` ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - ``@dependabot` ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2023-07-04 12:57:38 +00:00
dependabot[bot]	40ad19ba9e	Bump Swatinem/rust-cache from 2.4.0 to 2.5.0 Bumps [Swatinem/rust-cache](https://github.com/swatinem/rust-cache) from 2.4.0 to 2.5.0. - [Release notes](https://github.com/swatinem/rust-cache/releases) - [Changelog](https://github.com/Swatinem/rust-cache/blob/master/CHANGELOG.md) - [Commits](https://github.com/swatinem/rust-cache/compare/v2.4.0...v2.5.0) --- updated-dependencies: - dependency-name: Swatinem/rust-cache dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com>	2023-07-01 17:46:11 +00:00