Disable autobatching of additions and deletions

3623: Update mini-dashboard to version v0.2.7 r=curquiza a=bidoubiwa

## Changes

* Retrieve the API Key from the url parameters (#416) `@qdequele`

## 🐛 Bug Fixes

* Fix show more button not displaying all fields (#419) `@bidoubiwa`

Thanks again to `@bidoubiwa,`     and `@qdequele!` 🎉


Co-authored-by: Charlotte Vermandel <charlottevermandel@gmail.com>

.github/scripts/check-release.sh

@@ -3,7 +3,7 @@
 # check_tag $current_tag $file_tag $file_name
 function check_tag {
   if [[ "$1" != "$2" ]]; then
-      echo "Error: the current tag does not match the version in $3: found $2 - expected $1"
+      echo "Error: the current tag does not match the version in Cargo.toml: found $2 - expected $1"
       ret=1
   fi
 }
@@ -11,12 +11,8 @@ function check_tag {
 ret=0
 current_tag=${GITHUB_REF#'refs/tags/v'}
 
-toml_files='*/Cargo.toml'
-for toml_file in $toml_files;
-do
-    file_tag="$(grep '^version = ' $toml_file | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')"
-    check_tag $current_tag $file_tag $toml_file
-done
+file_tag="$(grep '^version = ' Cargo.toml | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')"
+check_tag $current_tag $file_tag
 
 lock_file='Cargo.lock'
 lock_tag=$(grep -A 1 'name = "meilisearch-auth"' $lock_file | grep version | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')

.github/uffizzi/Dockerfile

@@ -0,0 +1,19 @@
+# Run
+FROM    uffizzi/ttyd:alpine
+
+ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
+ENV     MEILI_SERVER_PROVIDER docker
+ENV     MEILI_NO_ANALYTICS true
+
+RUN     apk update --quiet \
+        && apk add -q --no-cache libgcc tini curl
+
+COPY    target/x86_64-unknown-linux-musl/release/meilisearch /bin/meilisearch
+RUN     ln -s /bin/meilisearch /meilisearch
+
+WORKDIR /meili_data
+
+EXPOSE  7700/tcp
+
+ENTRYPOINT ["tini", "--"]
+CMD     ["ttyd", "/bin/zsh"]

.github/uffizzi/docker-compose.uffizzi.yml

@@ -0,0 +1,26 @@
+version: "3"
+
+x-uffizzi:
+  ingress:
+    service: nginx
+    port: 8081
+
+services:
+  meilisearch:
+    image: "${MEILISEARCH_IMAGE}"
+    restart: unless-stopped
+    ports:
+    - "7681:7681"
+    - "7700:7700"
+    deploy:
+      resources:
+        limits:
+          memory: 500M
+  
+  nginx:
+    image: nginx:alpine
+    restart: unless-stopped
+    ports:
+    - "8081:8081"
+    volumes:
+    - ./.github/uffizzi/nginx:/etc/nginx

.github/uffizzi/nginx/nginx.conf

@@ -0,0 +1,28 @@
+
+events {
+  worker_connections  4096;  ## Default: 1024
+}
+
+http {
+    map $http_upgrade $connection_upgrade {
+        default upgrade;
+        '' close;
+    }
+
+    server {
+        listen 8081;
+
+        location / {
+            proxy_pass http://localhost:7681;
+            proxy_http_version 1.1;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection $connection_upgrade;
+        }
+
+        location /meilisearch/ {
+            # rewrite /meilisearch/(.*) /$1  break;
+            proxy_pass http://localhost:7700/;
+        }
+    }
+}
+

.github/workflows/create-issue-dependencies.yml

@@ -1,6 +1,7 @@
 name: Create issue to upgrade dependencies
 on:
   schedule:
+    # Run the first of the month, every 3 month
     - cron: '0 0 1 */3 *'
   workflow_dispatch:
 
@@ -15,9 +16,13 @@ jobs:
         github_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         title: Upgrade dependencies
         body: |
-          We need to update the dependencies of the Meilisearch repository, and, if possible, the dependencies of all the engine-team repositories that Meilisearch depends on (charabia, heed...).
+          This issue is about updating Meilisearch dependencies:
+          - [ ] Cargo toml dependencies of Meilisearch; but also the main engine-team repositories that Meilisearch depends on (charabia, heed...)
+          - [ ] If new Rust versions have been released, update the Rust version in the Clippy job of this [GitHub Action file](./.github/workflows/rust.yml)
 
-          ⚠️ This issue should only be done at the beginning of the sprint!
+          ⚠️ To avoid last minute bugs, this issue should only be done at the beginning of the sprint!
+
+          The GitHub action dependencies are managed by [Dependabot](./.github/dependabot.yml)
         labels: |
           dependencies
           maintenance

.github/workflows/publish-binaries.yml

@@ -96,14 +96,12 @@ jobs:
 
   publish-macos-apple-silicon:
     name: Publish binary for macOS silicon
-    runs-on: ${{ matrix.os }}
+    runs-on: macos-12
     needs: check-version
     strategy:
-      fail-fast: false
       matrix:
         include:
-          - os: macos-12
-            target: aarch64-apple-darwin
+          - target: aarch64-apple-darwin
             asset_name: meilisearch-macos-apple-silicon
     steps:
       - name: Checkout repository
@@ -132,21 +130,29 @@ jobs:
 
   publish-aarch64:
     name: Publish binary for aarch64
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-latest
     needs: check-version
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
     strategy:
-      fail-fast: false
       matrix:
         include:
-          - build: aarch64
-            os: ubuntu-18.04
-            target: aarch64-unknown-linux-gnu
-            linker: gcc-aarch64-linux-gnu
-            use-cross: true
+          - target: aarch64-unknown-linux-gnu
             asset_name: meilisearch-linux-aarch64
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
+      - name: Install needed dependencies
+        run: |
+          apt-get update -y && apt upgrade -y
+          apt-get install -y curl build-essential gcc-aarch64-linux-gnu
+      - name: Set up Docker for cross compilation
+        run: |
+          apt-get install -y curl apt-transport-https ca-certificates software-properties-common
+          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+          add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
+          apt-get update -y && apt-get install -y docker-ce
       - name: Installing Rust toolchain
         uses: actions-rs/toolchain@v1
         with:
@@ -154,15 +160,7 @@ jobs:
           profile: minimal
           target: ${{ matrix.target }}
           override: true
-      - name: APT update
-        run: |
-          sudo apt update
-      - name: Install target specific tools
-        if: matrix.use-cross
-        run: |
-          sudo apt-get install -y ${{ matrix.linker }}
       - name: Configure target aarch64 GNU
-        if: matrix.target == 'aarch64-unknown-linux-gnu'
         ## Environment variable is not passed using env:
         ## LD gold won't work with MUSL
         # env:
@@ -176,8 +174,10 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: build
-          use-cross: ${{ matrix.use-cross }}
+          use-cross: true
           args: --release --target ${{ matrix.target }}
+        env:
+          CROSS_DOCKER_IN_DOCKER: true
       - name: List target output files
         run: ls -lR ./target
       - name: Upload the binary to release

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

@@ -92,6 +92,7 @@ jobs:
           build-args: |
             COMMIT_SHA=${{ github.sha }}
             COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
+            GIT_TAG=${{ github.ref_name }}
 
       # /!\ Don't touch this without checking with Cloud team
       - name: Send CI information to Cloud team

.github/workflows/rust.yml

@@ -2,6 +2,9 @@ name: Rust
 
 on:
   workflow_dispatch:
+  schedule:
+    # Everyday at 5:00am
+    - cron: '0 5 * * *'
   pull_request:
   push:
     # trying and staging branches are for Bors config
@@ -27,10 +30,18 @@ jobs:
       run: |
         apt-get update && apt-get install -y curl
         apt-get install build-essential -y
-    - uses: actions-rs/toolchain@v1
+    - name: Run 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'
+      uses: actions-rs/toolchain@v1
+      with:
+        toolchain: nightly
+        override: true
     # Disable cache due to disk space issues with Windows workers in CI
     # - name: Cache dependencies
     #   uses: Swatinem/rust-cache@v2.2.0
@@ -100,7 +111,7 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: stable
+          toolchain: 1.67.0
           override: true
           components: clippy
       # - name: Cache dependencies

.github/workflows/uffizzi-build.yml

@@ -0,0 +1,120 @@
+name: Uffizzi - Build PR Image
+on:
+  pull_request:
+    types: [opened,synchronize,reopened,closed]
+
+jobs:
+  build-meilisearch:
+    name: Build and push `meilisearch`
+    runs-on: ubuntu-latest
+    outputs:
+      tags: ${{ steps.meta.outputs.tags }}
+    if: ${{ github.event.action != 'closed' }}
+    steps:
+      - name: checkout
+        uses: actions/checkout@v3
+
+      - run: sudo apt-get install musl-tools
+
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+          target: x86_64-unknown-linux-musl
+
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+
+      - name: Run cargo check without any default features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --target x86_64-unknown-linux-musl --release 
+      
+      - name: Remove dockerignore so we can use the target folder in our docker build
+        run: rm -f .dockerignore
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Generate UUID image name
+        id: uuid
+        run: echo "UUID_TAG=$(uuidgen)" >> $GITHUB_ENV
+
+      - name: Docker metadata
+        id: meta
+        uses: docker/metadata-action@v3
+        with:
+          images: registry.uffizzi.com/${{ env.UUID_TAG }}
+          tags: | 
+            type=raw,value=60d
+
+      - name: Build Image
+        uses: docker/build-push-action@v3
+        with:
+          context: ./
+          file: .github/uffizzi/Dockerfile
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          push: true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  render-compose-file:
+    name: Render Docker Compose File
+    # Pass output of this workflow to another triggered by `workflow_run` event.
+    runs-on: ubuntu-latest
+    needs: 
+      - build-meilisearch
+    outputs:
+      compose-file-cache-key:  ${{ env.COMPOSE_FILE_HASH }}
+    steps:
+      - name: Checkout git repo
+        uses: actions/checkout@v3
+      - name: Render Compose File
+        run: |
+          MEILISEARCH_IMAGE=$(echo ${{ needs.build-meilisearch.outputs.tags }})
+          export MEILISEARCH_IMAGE
+          # Render simple template from environment variables.
+          envsubst < .github/uffizzi/docker-compose.uffizzi.yml > docker-compose.rendered.yml
+          cat docker-compose.rendered.yml
+      - name: Upload Rendered Compose File as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec 
+          path: docker-compose.rendered.yml
+          retention-days: 2
+      - name: Serialize PR Event to File
+        run:  |
+          cat << EOF > event.json
+          ${{ toJSON(github.event) }} 
+          
+          EOF
+      - name: Upload PR Event as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec
+          path: event.json
+          retention-days: 2
+
+  delete-preview:
+    name: Call for Preview Deletion
+    runs-on: ubuntu-latest
+    if: ${{ github.event.action == 'closed' }}
+    steps:
+      # If this PR is closing, we will not render a compose file nor pass it to the next workflow.
+      - name: Serialize PR Event to File
+        run:  |
+          cat << EOF > event.json
+          ${{ toJSON(github.event) }} 
+          
+          EOF
+      - name: Upload PR Event as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec
+          path: event.json
+          retention-days: 2

.github/workflows/uffizzi-preview-deploy.yml

@@ -0,0 +1,103 @@
+name: Uffizzi - Deploy Preview
+
+on:
+  workflow_run:
+    workflows:
+      - "Uffizzi - Build PR Image"
+    types:
+      - completed
+
+jobs:
+  cache-compose-file:
+    name: Cache Compose File
+    runs-on: ubuntu-latest
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    outputs:
+      compose-file-cache-key: ${{ env.COMPOSE_FILE_HASH }}
+      pr-number: ${{ env.PR_NUMBER }}
+      expected-url: ${{ env.EXPECTED_URL }}
+    steps:
+      - name: 'Download artifacts'
+        # Fetch output (zip archive) from the workflow run that triggered this workflow.
+        uses: actions/github-script@v6
+        with:
+          script: |
+            let allArtifacts = await github.rest.actions.listWorkflowRunArtifacts({
+               owner: context.repo.owner,
+               repo: context.repo.repo,
+               run_id: context.payload.workflow_run.id,
+            });
+            let matchArtifact = allArtifacts.data.artifacts.filter((artifact) => {
+              return artifact.name == "preview-spec"
+            })[0];
+            let download = await github.rest.actions.downloadArtifact({
+               owner: context.repo.owner,
+               repo: context.repo.repo,
+               artifact_id: matchArtifact.id,
+               archive_format: 'zip',
+            });
+            let fs = require('fs');
+            fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/preview-spec.zip`, Buffer.from(download.data));
+      
+      - name: 'Unzip artifact'
+        run: unzip preview-spec.zip
+      
+      - name: Read Event into ENV
+        run: |
+          echo 'EVENT_JSON<<EOF' >> $GITHUB_ENV
+          cat event.json >> $GITHUB_ENV
+          echo 'EOF' >> $GITHUB_ENV
+      
+      - name: Hash Rendered Compose File
+        id: hash
+        # If the previous workflow was triggered by a PR close event, we will not have a compose file artifact.
+        if: ${{ fromJSON(env.EVENT_JSON).action != 'closed' }}
+        run: echo "COMPOSE_FILE_HASH=$(md5sum docker-compose.rendered.yml | awk '{ print $1 }')" >> $GITHUB_ENV
+      
+      - name: Cache Rendered Compose File
+        if: ${{ fromJSON(env.EVENT_JSON).action != 'closed' }}
+        uses: actions/cache@v3
+        with:
+          path: docker-compose.rendered.yml
+          key: ${{ env.COMPOSE_FILE_HASH }}
+
+      - name: Read PR Number From Event Object
+        id: pr
+        run: echo "PR_NUMBER=${{ fromJSON(env.EVENT_JSON).number }}" >> $GITHUB_ENV
+      
+      - name: DEBUG - Print Job Outputs
+        if: ${{ runner.debug }}
+        run: |
+          echo "PR number: ${{ env.PR_NUMBER }}"
+          echo "Compose file hash: ${{ env.COMPOSE_FILE_HASH }}"
+          cat event.json
+
+      - name: Add expected URL env var
+        if: ${{ runner.debug }}
+        run: |
+          REPO=$(echo ${{ github.repository }} | sed 's/\./+/g')
+          echo "EXPECTED_URL=${{ inputs.server }}/github.com/$REPO/pull/${{ env.PR_NUMBER }}" >> $GITHUB_ENV
+
+  deploy-uffizzi-preview:
+    name: Use Remote Workflow to Preview on Uffizzi
+    needs:
+      - cache-compose-file
+    uses: UffizziCloud/preview-action/.github/workflows/reusable.yaml@v2
+    with:
+      # If this workflow was triggered by a PR close event, cache-key will be an empty string
+      # and this reusable workflow will delete the preview deployment.
+      compose-file-cache-key: ${{ needs.cache-compose-file.outputs.compose-file-cache-key }}
+      compose-file-cache-path: docker-compose.rendered.yml
+      server: https://app.uffizzi.com
+      pr-number: ${{ needs.cache-compose-file.outputs.pr-number }}
+      description: |
+        The meilisearch preview environment contains a web terminal from where you can run the
+        `meilisearch` command. You should be able to access this instance of meilisearch running in
+        the preview from the link Meilisearch Endpoint link given below.
+         
+        Web Terminal Endpoint : <uffizzi-url>
+        Meilisearch Endpoint : <uffizzi-url>/meilisearch
+    permissions:
+      contents: read
+      pull-requests: write
+      id-token: write

.github/workflows/update-cargo-toml-version.yml

@@ -1,4 +1,4 @@
-name: Update Meilisearch version in all Cargo.toml files
+name: Update Meilisearch version in Cargo.toml
 
 on:
   workflow_dispatch:
@@ -14,7 +14,7 @@ env:
 
 jobs:
   update-version-cargo-toml:
-    name: Update version in Cargo.toml files
+    name: Update version in Cargo.toml
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
@@ -25,23 +25,23 @@ jobs:
           override: true
       - name: Install sd
         run: cargo install sd
-      - name: Update Cargo.toml files
+      - name: Update Cargo.toml file
         run: |
           raw_new_version=$(echo $NEW_VERSION | cut -d 'v' -f 2)
           new_string="version = \"$raw_new_version\""
-          sd '^version = "\d+.\d+.\w+"$' "$new_string" */Cargo.toml
+          sd '^version = "\d+.\d+.\w+"$' "$new_string" Cargo.toml
       - name: Build Meilisearch to update Cargo.lock
         run: cargo build
       - name: Commit and push the changes to the ${{ env.NEW_BRANCH }} branch
         uses: EndBug/add-and-commit@v9
         with:
-          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml files"
+          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml"
           new_branch: ${{ env.NEW_BRANCH }}
       - name: Create the PR pointing to ${{ github.ref_name }}
         run: |
           gh pr create \
-            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml files" \
-            --body '⚠️ This PR is automatically generated. Check the new version is the expected one before merging.' \
+            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml" \
+            --body '⚠️ This PR is automatically generated. Check the new version is the expected one and Cargo.lock has been updated before merging.' \
             --label 'skip changelog' \
             --milestone $NEW_VERSION \
             --base $GITHUB_REF_NAME

.gitignore

@@ -1,3 +1,5 @@
+.idea/
+.vscode/
 /target
 **/*.csv
 **/*.json_lines

CONTRIBUTING.md

@@ -52,6 +52,23 @@ cargo test
 
 This command will be triggered to each PR as a requirement for merging it.
 
+#### Snapshot-based tests
+
+We are using [insta](https://insta.rs) to perform snapshot-based testing.
+We recommend using the insta tooling (such as `cargo-insta`) to update the snapshots if they change following a PR.
+
+New tests should use insta where possible rather than manual `assert` statements.
+
+Furthermore, we provide some macros on top of insta, notably a way to use snapshot hashes instead of inline snapshots, saving a lot of space in the repository.
+
+To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally:
+
+```
+export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ...
+```
+
+#### Test troubleshooting
+
 If you get a "Too many open files" error you might want to increase the open file limit using this command:
 
 ```bash
@@ -104,15 +121,19 @@ The full Meilisearch release process is described in [this guide](https://github
 Depending on the developed feature, you might need to provide a prototyped version of Meilisearch to make it easier to test by the users.
 
 The prototype name must follow this convention: `prototype-X-Y` where
-- `X` is the feature name formatted in `kebab-case`
+- `X` is the feature name formatted in `kebab-case`. It should not end with a single number.
 - `Y` is the version of the prototype, starting from `0`.
 
-Example: `prototype-auto-resize-0`.
+✅ Example: `prototype-auto-resize-0`. </br>
+❌ Bad example: `auto-resize-0`: lacks the `prototype` prefix. </br>
+❌ Bad example: `prototype-auto-resize`: lacks the version suffix. </br>
+❌ Bad example: `prototype-auto-resize-0-0`: feature name ends with a single number.
 
 Steps to create a prototype:
 
 1. In your terminal, go to the last commit of your branch (the one you want to provide as a prototype).
 2. Create a tag following the convention: `git tag prototype-X-Y`
+3. Run Meilisearch and check that its launch summary features a line: `Prototype: prototype-X-Y` (you may need to switch branches and back after tagging for this to work).
 3. Push the tag: `git push origin prototype-X-Y`
 4. Check the [Docker CI](https://github.com/meilisearch/meilisearch/actions/workflows/publish-docker-images.yml) is now running.
 
@@ -121,7 +142,7 @@ More information about [how to run Meilisearch with Docker](https://docs.meilise
 
 ⚙️ However, no binaries will be created. If the users do not use Docker, they can go to the `prototype-X-Y` tag in the Meilisearch repository and compile from the source code.
 
-⚠️ When sharing a prototype with users, prevent them from using it in production. Prototypes are only for test purposes.
+⚠️ When sharing a prototype with users, remind them to not use it in production. Prototypes are solely for test purposes.
 
 ### Release assets
 

Cargo.toml

@@ -16,6 +16,15 @@ members = [
     "benchmarks"
 ]
 
+[workspace.package]
+version = "1.1.0"
+authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
+description = "Meilisearch HTTP server"
+homepage = "https://meilisearch.com"
+readme = "README.md"
+edition = "2021"
+license = "MIT"
+
 [profile.release]
 codegen-units = 1
 

Dockerfile

@@ -7,7 +7,8 @@ WORKDIR /meilisearch
 
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
-ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE}
+ARG     GIT_TAG
+ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
 COPY    . .

benchmarks/Cargo.toml

@@ -1,9 +1,15 @@
 [package]
 name = "benchmarks"
-version = "1.0.0"
-edition = "2018"
 publish = false
 
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
 [dependencies]
 anyhow = "1.0.65"
 csv = "1.1.6"

benchmarks/benches/formatting.rs

@@ -29,7 +29,7 @@ fn bench_formatting(c: &mut criterion::Criterion) {
 	            (vec![Rc::new(MatchingWord::new("thedoord".to_string(), 1, true).unwrap())], vec![0, 1, 2]),
 	            (vec![Rc::new(MatchingWord::new("doord".to_string(), 1, true).unwrap())], vec![1, 2]),
         	]
-            ), TokenizerBuilder::default().build()),
+            ).unwrap(), TokenizerBuilder::default().build()),
 		},
     ];
 

config.toml

@@ -45,7 +45,7 @@ log_level = "INFO"
 
 dump_dir = "dumps/"
 # Sets the directory where Meilisearch will create dump files.
-# https://docs.meilisearch.com/learn/configuration/instance_options.html#dumps-destination
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#dump-directory
 
 # import_dump = "./path/to/my/file.dump"
 # Imports the dump file located at the specified path. Path must point to a .dump file.
@@ -118,3 +118,13 @@ ssl_resumption = false
 ssl_tickets = false
 # Activates SSL tickets.
 # https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-tickets
+
+#############################
+### Experimental features ###
+#############################
+
+experimental_enable_metrics = false
+# Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
+# Enables the Prometheus metrics on the `GET /metrics` endpoint.
+
+

dump/Cargo.toml

@@ -1,7 +1,14 @@
 [package]
 name = "dump"
-version = "1.0.0"
-edition = "2021"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+edition.workspace = true
+homepage.workspace = true
+readme.workspace = true
+license.workspace = true
 
 [dependencies]
 anyhow = "1.0.65"

dump/src/lib.rs

@@ -203,12 +203,11 @@ pub(crate) mod test {
 
     use big_s::S;
     use maplit::btreeset;
-    use meilisearch_types::index_uid::IndexUid;
+    use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
     use meilisearch_types::milli::update::Setting;
     use meilisearch_types::milli::{self};
     use meilisearch_types::settings::{Checked, Settings};
-    use meilisearch_types::star_or::StarOr;
     use meilisearch_types::tasks::{Details, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
@@ -341,7 +340,7 @@ pub(crate) mod test {
                 name: Some(S("doggos_key")),
                 uid: Uuid::from_str("9f8a34da-b6b2-42f0-939b-dbd4c3448655").unwrap(),
                 actions: vec![Action::DocumentsAll],
-                indexes: vec![StarOr::Other(IndexUid::from_str("doggos").unwrap())],
+                indexes: vec![IndexUidPattern::from_str("doggos").unwrap()],
                 expires_at: Some(datetime!(4130-03-14 12:21 UTC)),
                 created_at: datetime!(1960-11-15 0:00 UTC),
                 updated_at: datetime!(2022-11-10 0:00 UTC),
@@ -351,7 +350,7 @@ pub(crate) mod test {
                 name: Some(S("master_key")),
                 uid: Uuid::from_str("4622f717-1c00-47bb-a494-39d76a49b591").unwrap(),
                 actions: vec![Action::All],
-                indexes: vec![StarOr::Star],
+                indexes: vec![IndexUidPattern::all()],
                 expires_at: None,
                 created_at: datetime!(0000-01-01 00:01 UTC),
                 updated_at: datetime!(1964-05-04 17:25 UTC),

dump/src/reader/compat/snapshots/dump__reader__compat__v1_to_v2__test__compat_v1_v2-3.snap

@@ -10,6 +10,7 @@ expression: products.settings().unwrap()
     "*"
   ],
   "filterableAttributes": [],
+  "sortableAttributes": [],
   "rankingRules": [
     "typo",
     "words",

dump/src/reader/compat/snapshots/dump__reader__compat__v1_to_v2__test__compat_v1_v2-6.snap

@@ -13,13 +13,17 @@ expression: movies.settings().unwrap()
     "genres",
     "id"
   ],
+  "sortableAttributes": [
+    "genres",
+    "id"
+  ],
   "rankingRules": [
     "typo",
     "words",
     "proximity",
     "attribute",
     "exactness",
-    "asc(release_date)"
+    "release_date:asc"
   ],
   "stopWords": [],
   "synonyms": {},

dump/src/reader/compat/snapshots/dump__reader__compat__v1_to_v2__test__compat_v1_v2-9.snap

@@ -10,6 +10,7 @@ expression: spells.settings().unwrap()
     "*"
   ],
   "filterableAttributes": [],
+  "sortableAttributes": [],
   "rankingRules": [
     "typo",
     "words",

dump/src/reader/compat/v1_to_v2.rs

@@ -1,4 +1,3 @@
-use std::collections::BTreeSet;
 use std::str::FromStr;
 
 use super::v2_to_v3::CompatV2ToV3;
@@ -102,14 +101,15 @@ impl CompatIndexV1ToV2 {
 
 impl From<v1::settings::Settings> for v2::Settings<v2::Unchecked> {
     fn from(source: v1::settings::Settings) -> Self {
-        let displayed_attributes = source
-            .displayed_attributes
-            .map(|opt| opt.map(|displayed_attributes| displayed_attributes.into_iter().collect()));
-        let attributes_for_faceting = source.attributes_for_faceting.map(|opt| {
-            opt.map(|attributes_for_faceting| attributes_for_faceting.into_iter().collect())
-        });
-        let ranking_rules = source.ranking_rules.map(|opt| {
-            opt.map(|ranking_rules| {
+        Self {
+            displayed_attributes: option_to_setting(source.displayed_attributes)
+                .map(|displayed| displayed.into_iter().collect()),
+            searchable_attributes: option_to_setting(source.searchable_attributes),
+            filterable_attributes: option_to_setting(source.attributes_for_faceting.clone())
+                .map(|filterable| filterable.into_iter().collect()),
+            sortable_attributes: option_to_setting(source.attributes_for_faceting)
+                .map(|sortable| sortable.into_iter().collect()),
+            ranking_rules: option_to_setting(source.ranking_rules).map(|ranking_rules| {
                 ranking_rules
                     .into_iter()
                     .filter_map(|ranking_rule| {
@@ -119,26 +119,33 @@ impl From<v1::settings::Settings> for v2::Settings<v2::Unchecked> {
                                     ranking_rule.into();
                                 criterion.as_ref().map(ToString::to_string)
                             }
-                            Err(()) => Some(ranking_rule),
+                            Err(()) => {
+                                log::warn!(
+                                    "Could not import the following ranking rule: `{}`.",
+                                    ranking_rule
+                                );
+                                None
+                            }
                         }
                     })
                     .collect()
-            })
-        });
-
-        Self {
-            displayed_attributes,
-            searchable_attributes: source.searchable_attributes,
-            filterable_attributes: attributes_for_faceting,
-            ranking_rules,
-            stop_words: source.stop_words,
-            synonyms: source.synonyms,
-            distinct_attribute: source.distinct_attribute,
+            }),
+            stop_words: option_to_setting(source.stop_words),
+            synonyms: option_to_setting(source.synonyms),
+            distinct_attribute: option_to_setting(source.distinct_attribute),
             _kind: std::marker::PhantomData,
         }
     }
 }
 
+fn option_to_setting<T>(opt: Option<Option<T>>) -> v2::Setting<T> {
+    match opt {
+        Some(Some(t)) => v2::Setting::Set(t),
+        None => v2::Setting::NotSet,
+        Some(None) => v2::Setting::Reset,
+    }
+}
+
 impl From<v1::update::UpdateStatus> for Option<v2::updates::UpdateStatus> {
     fn from(source: v1::update::UpdateStatus) -> Self {
         use v1::update::UpdateStatus as UpdateStatusV1;
@@ -251,38 +258,27 @@ impl From<v1::update::UpdateType> for Option<v2::updates::UpdateMeta> {
 
 impl From<v1::settings::SettingsUpdate> for v2::Settings<v2::Unchecked> {
     fn from(source: v1::settings::SettingsUpdate) -> Self {
-        let displayed_attributes: Option<Option<BTreeSet<String>>> =
-            source.displayed_attributes.into();
-
-        let attributes_for_faceting: Option<Option<Vec<String>>> =
-            source.attributes_for_faceting.into();
-
-        let ranking_rules: Option<Option<Vec<v1::settings::RankingRule>>> =
-            source.ranking_rules.into();
+        let ranking_rules = v2::Setting::from(source.ranking_rules);
 
         // go from the concrete types of v1 (RankingRule) to the concrete type of v2 (Criterion),
         // and then back to string as this is what the settings manipulate
-        let ranking_rules = ranking_rules.map(|opt| {
-            opt.map(|ranking_rules| {
-                ranking_rules
-                    .into_iter()
-                    // filter out the WordsPosition ranking rule that exists in v1 but not v2
-                    .filter_map(|ranking_rule| {
-                        Option::<v2::settings::Criterion>::from(ranking_rule)
-                    })
-                    .map(|criterion| criterion.to_string())
-                    .collect()
-            })
+        let ranking_rules = ranking_rules.map(|ranking_rules| {
+            ranking_rules
+                .into_iter()
+                // filter out the WordsPosition ranking rule that exists in v1 but not v2
+                .filter_map(Option::<v2::settings::Criterion>::from)
+                .map(|criterion| criterion.to_string())
+                .collect()
         });
 
         Self {
-            displayed_attributes: displayed_attributes.map(|opt| {
-                opt.map(|displayed_attributes| displayed_attributes.into_iter().collect())
-            }),
+            displayed_attributes: v2::Setting::from(source.displayed_attributes)
+                .map(|displayed_attributes| displayed_attributes.into_iter().collect()),
             searchable_attributes: source.searchable_attributes.into(),
-            filterable_attributes: attributes_for_faceting.map(|opt| {
-                opt.map(|attributes_for_faceting| attributes_for_faceting.into_iter().collect())
-            }),
+            filterable_attributes: v2::Setting::from(source.attributes_for_faceting.clone())
+                .map(|attributes_for_faceting| attributes_for_faceting.into_iter().collect()),
+            sortable_attributes: v2::Setting::from(source.attributes_for_faceting)
+                .map(|attributes_for_faceting| attributes_for_faceting.into_iter().collect()),
             ranking_rules,
             stop_words: source.stop_words.into(),
             synonyms: source.synonyms.into(),
@@ -314,12 +310,12 @@ impl From<v1::settings::RankingRule> for Option<v2::settings::Criterion> {
     }
 }
 
-impl<T> From<v1::settings::UpdateState<T>> for Option<Option<T>> {
+impl<T> From<v1::settings::UpdateState<T>> for v2::Setting<T> {
     fn from(source: v1::settings::UpdateState<T>) -> Self {
         match source {
-            v1::settings::UpdateState::Update(new_value) => Some(Some(new_value)),
-            v1::settings::UpdateState::Clear => Some(None),
-            v1::settings::UpdateState::Nothing => None,
+            v1::settings::UpdateState::Update(new_value) => v2::Setting::Set(new_value),
+            v1::settings::UpdateState::Clear => v2::Setting::Reset,
+            v1::settings::UpdateState::Nothing => v2::Setting::NotSet,
         }
     }
 }
@@ -352,7 +348,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"ad6245d98d1a8e30535f3339a9a8d223");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"2298010973ee98cf4670787314176a3a");
         assert_eq!(update_files.len(), 9);
         assert!(update_files[..].iter().all(|u| u.is_none())); // no update file in dumps v1
 

dump/src/reader/compat/v2_to_v3.rs

@@ -361,28 +361,29 @@ impl From<String> for v3::Code {
     }
 }
 
-fn option_to_setting<T>(opt: Option<Option<T>>) -> v3::Setting<T> {
-    match opt {
-        Some(Some(t)) => v3::Setting::Set(t),
-        None => v3::Setting::NotSet,
-        Some(None) => v3::Setting::Reset,
+impl<A> From<v2::Setting<A>> for v3::Setting<A> {
+    fn from(setting: v2::Setting<A>) -> Self {
+        match setting {
+            v2::settings::Setting::Set(a) => v3::settings::Setting::Set(a),
+            v2::settings::Setting::Reset => v3::settings::Setting::Reset,
+            v2::settings::Setting::NotSet => v3::settings::Setting::NotSet,
+        }
     }
 }
 
 impl<T> From<v2::Settings<T>> for v3::Settings<v3::Unchecked> {
     fn from(settings: v2::Settings<T>) -> Self {
         v3::Settings {
-            displayed_attributes: option_to_setting(settings.displayed_attributes),
-            searchable_attributes: option_to_setting(settings.searchable_attributes),
-            filterable_attributes: option_to_setting(settings.filterable_attributes)
-                .map(|f| f.into_iter().collect()),
-            sortable_attributes: v3::Setting::NotSet,
-            ranking_rules: option_to_setting(settings.ranking_rules).map(|criteria| {
+            displayed_attributes: settings.displayed_attributes.into(),
+            searchable_attributes: settings.searchable_attributes.into(),
+            filterable_attributes: settings.filterable_attributes.into(),
+            sortable_attributes: settings.sortable_attributes.into(),
+            ranking_rules: v3::Setting::from(settings.ranking_rules).map(|criteria| {
                 criteria.into_iter().map(|criterion| patch_ranking_rules(&criterion)).collect()
             }),
-            stop_words: option_to_setting(settings.stop_words),
-            synonyms: option_to_setting(settings.synonyms),
-            distinct_attribute: option_to_setting(settings.distinct_attribute),
+            stop_words: settings.stop_words.into(),
+            synonyms: settings.synonyms.into(),
+            distinct_attribute: settings.distinct_attribute.into(),
             _kind: std::marker::PhantomData,
         }
     }
@@ -394,6 +395,7 @@ fn patch_ranking_rules(ranking_rule: &str) -> String {
         Ok(v2::settings::Criterion::Typo) => String::from("typo"),
         Ok(v2::settings::Criterion::Proximity) => String::from("proximity"),
         Ok(v2::settings::Criterion::Attribute) => String::from("attribute"),
+        Ok(v2::settings::Criterion::Sort) => String::from("sort"),
         Ok(v2::settings::Criterion::Exactness) => String::from("exactness"),
         Ok(v2::settings::Criterion::Asc(name)) => format!("{name}:asc"),
         Ok(v2::settings::Criterion::Desc(name)) => format!("{name}:desc"),

dump/src/reader/compat/v5_to_v6.rs

@@ -181,10 +181,8 @@ impl CompatV5ToV6 {
                     .indexes
                     .into_iter()
                     .map(|index| match index {
-                        v5::StarOr::Star => v6::StarOr::Star,
-                        v5::StarOr::Other(uid) => {
-                            v6::StarOr::Other(v6::IndexUid::new_unchecked(uid.as_str()))
-                        }
+                        v5::StarOr::Star => v6::IndexUidPattern::all(),
+                        v5::StarOr::Other(uid) => v6::IndexUidPattern::new_unchecked(uid.as_str()),
                     })
                     .collect(),
                 expires_at: key.expires_at,
@@ -260,7 +258,7 @@ impl From<v5::ResponseError> for v6::ResponseError {
             "index_already_exists" => v6::Code::IndexAlreadyExists,
             "index_not_found" => v6::Code::IndexNotFound,
             "invalid_index_uid" => v6::Code::InvalidIndexUid,
-            "invalid_min_word_length_for_typo" => v6::Code::InvalidMinWordLengthForTypo,
+            "invalid_min_word_length_for_typo" => v6::Code::InvalidSettingsTypoTolerance,
             "invalid_state" => v6::Code::InvalidState,
             "primary_key_inference_failed" => v6::Code::IndexPrimaryKeyNoCandidateFound,
             "index_primary_key_already_exists" => v6::Code::IndexPrimaryKeyAlreadyExists,
@@ -439,7 +437,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"10c673c97f053830aa659876d7aa0b53");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"41f91d3a94911b2735ec41b07540df5c");
         assert_eq!(update_files.len(), 22);
         assert!(update_files[0].is_none()); // the dump creation
         assert!(update_files[1].is_some()); // the enqueued document addition

dump/src/reader/mod.rs

@@ -201,7 +201,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"10c673c97f053830aa659876d7aa0b53");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"41f91d3a94911b2735ec41b07540df5c");
         assert_eq!(update_files.len(), 22);
         assert!(update_files[0].is_none()); // the dump creation
         assert!(update_files[1].is_some()); // the enqueued document addition
@@ -279,7 +279,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"12eca43d5d1e1f334200eb4df653b0c9");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"c2445ddd1785528b80f2ba534d3bd00c");
         assert_eq!(update_files.len(), 10);
         assert!(update_files[0].is_some()); // the enqueued document addition
         assert!(update_files[1..].iter().all(|u| u.is_none())); // everything already processed
@@ -356,7 +356,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"2f51c6345fabccf47b18c82bad618ffe");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"cd12efd308fe3ed226356a727ab42ed3");
         assert_eq!(update_files.len(), 10);
         assert!(update_files[0].is_some()); // the enqueued document addition
         assert!(update_files[1..].iter().all(|u| u.is_none())); // everything already processed
@@ -449,7 +449,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"b27292d0bb86d4b4dd1b375a46b33890");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"bc616290adfe7d09a624cf6065ca9069");
         assert_eq!(update_files.len(), 9);
         assert!(update_files[0].is_some()); // the enqueued document addition
         assert!(update_files[1..].iter().all(|u| u.is_none())); // everything already processed
@@ -530,6 +530,82 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"235016433dd04262c7f2da01d1e808ce");
     }
 
+    #[test]
+    fn import_dump_v2_from_meilisearch_v0_22_0_issue_3435() {
+        let dump = File::open("tests/assets/v2-v0.22.0.dump").unwrap();
+        let mut dump = DumpReader::open(dump).unwrap();
+
+        // top level infos
+        insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
+        assert_eq!(dump.instance_uid().unwrap(), None);
+
+        // tasks
+        let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"2db37756d8af1fb7623436b76e8956a6");
+        assert_eq!(update_files.len(), 8);
+        assert!(update_files[0..].iter().all(|u| u.is_none())); // everything already processed
+
+        // keys
+        let keys = dump.keys().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(keys), @"d751713988987e9331980363e24189ce");
+
+        // indexes
+        let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        // the index are not ordered in any way by default
+        indexes.sort_by_key(|index| index.metadata().uid.to_string());
+
+        let mut products = indexes.pop().unwrap();
+        let mut movies = indexes.pop().unwrap();
+        let mut spells = indexes.pop().unwrap();
+        assert!(indexes.is_empty());
+
+        // products
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "products",
+          "primaryKey": "sku",
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(products.settings().unwrap());
+        let documents = products.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
+
+        // movies
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "movies",
+          "primaryKey": "id",
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(movies.settings().unwrap());
+        let documents = movies.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
+
+        // spells
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "dnd_spells",
+          "primaryKey": "index",
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(spells.settings().unwrap());
+        let documents = spells.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"235016433dd04262c7f2da01d1e808ce");
+    }
+
     #[test]
     fn import_dump_v1() {
         let dump = File::open("tests/assets/v1.dump").unwrap();
@@ -542,7 +618,7 @@ pub(crate) mod test {
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
-        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"9725ccfceea3f8d5846c44006c9e1e7b");
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"8df6eab075a44b3c1af6b726f9fd9a43");
         assert_eq!(update_files.len(), 9);
         assert!(update_files[..].iter().all(|u| u.is_none())); // no update file in dump v1
 

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-11.snap

@@ -10,6 +10,7 @@ expression: spells.settings().unwrap()
     "*"
   ],
   "filterableAttributes": [],
+  "sortableAttributes": [],
   "rankingRules": [
     "typo",
     "words",

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-5.snap

@@ -10,6 +10,7 @@ expression: products.settings().unwrap()
     "*"
   ],
   "filterableAttributes": [],
+  "sortableAttributes": [],
   "rankingRules": [
     "typo",
     "words",

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-8.snap

@@ -13,6 +13,10 @@ expression: movies.settings().unwrap()
     "genres",
     "id"
   ],
+  "sortableAttributes": [
+    "genres",
+    "id"
+  ],
   "rankingRules": [
     "typo",
     "words",

dump/src/reader/snapshots/dump__reader__test__import_dump_v2_from_meilisearch_v0_22_0_issue_3435-11.snap

@@ -0,0 +1,25 @@
+---
+source: dump/src/reader/mod.rs
+expression: spells.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v2_from_meilisearch_v0_22_0_issue_3435-5.snap

@@ -0,0 +1,39 @@
+---
+source: dump/src/reader/mod.rs
+expression: products.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {
+    "android": [
+      "phone",
+      "smartphone"
+    ],
+    "iphone": [
+      "phone",
+      "smartphone"
+    ],
+    "phone": [
+      "android",
+      "iphone",
+      "smartphone"
+    ]
+  },
+  "distinctAttribute": null
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v2_from_meilisearch_v0_22_0_issue_3435-8.snap

@@ -0,0 +1,30 @@
+---
+source: dump/src/reader/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [
+    "genres",
+    "id"
+  ],
+  "sortableAttributes": [
+    "release_date"
+  ],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness",
+    "release_date:asc"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/v2/mod.rs

@@ -41,6 +41,7 @@ use super::Document;
 use crate::{IndexMetadata, Result, Version};
 
 pub type Settings<T> = settings::Settings<T>;
+pub type Setting<T> = settings::Setting<T>;
 pub type Checked = settings::Checked;
 pub type Unchecked = settings::Unchecked;
 
@@ -306,4 +307,81 @@ pub(crate) mod test {
         assert_eq!(documents.len(), 10);
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"235016433dd04262c7f2da01d1e808ce");
     }
+
+    #[test]
+    fn read_dump_v2_from_meilisearch_v0_22_0_issue_3435() {
+        let dump = File::open("tests/assets/v2-v0.22.0.dump").unwrap();
+        let dir = TempDir::new().unwrap();
+        let mut dump = BufReader::new(dump);
+        let gz = GzDecoder::new(&mut dump);
+        let mut archive = tar::Archive::new(gz);
+        archive.unpack(dir.path()).unwrap();
+
+        let mut dump = V2Reader::open(dir).unwrap();
+
+        // top level infos
+        insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
+
+        // tasks
+        let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();
+        let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"aca8ba13046272664eb3ea2da3031633");
+        assert_eq!(update_files.len(), 8);
+        assert!(update_files[0..].iter().all(|u| u.is_none())); // everything has already been processed
+
+        // indexes
+        let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        // the index are not ordered in any way by default
+        indexes.sort_by_key(|index| index.metadata().uid.to_string());
+
+        let mut products = indexes.pop().unwrap();
+        let mut movies = indexes.pop().unwrap();
+        let mut spells = indexes.pop().unwrap();
+        assert!(indexes.is_empty());
+
+        // products
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "products",
+          "primaryKey": "sku",
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(products.settings().unwrap());
+        let documents = products.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
+
+        // movies
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "movies",
+          "primaryKey": "id",
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(movies.settings().unwrap());
+        let documents = movies.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
+
+        // spells
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "dnd_spells",
+          "primaryKey": "index",
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(spells.settings().unwrap());
+        let documents = spells.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"235016433dd04262c7f2da01d1e808ce");
+    }
 }

dump/src/reader/v2/settings.rs

@@ -1,35 +1,33 @@
 use std::collections::{BTreeMap, BTreeSet};
-use std::fmt::Display;
+use std::fmt;
 use std::marker::PhantomData;
 use std::str::FromStr;
 
-use once_cell::sync::Lazy;
-use regex::Regex;
 use serde::{Deserialize, Deserializer};
 
 #[cfg(test)]
 fn serialize_with_wildcard<S>(
-    field: &Option<Option<Vec<String>>>,
+    field: &Setting<Vec<String>>,
     s: S,
 ) -> std::result::Result<S::Ok, S::Error>
 where
     S: serde::Serializer,
 {
-    let wildcard = vec!["*".to_string()];
-    s.serialize_some(&field.as_ref().map(|o| o.as_ref().unwrap_or(&wildcard)))
-}
+    use serde::Serialize;
 
-fn deserialize_some<'de, T, D>(deserializer: D) -> std::result::Result<Option<T>, D::Error>
-where
-    T: Deserialize<'de>,
-    D: Deserializer<'de>,
-{
-    Deserialize::deserialize(deserializer).map(Some)
+    let wildcard = vec!["*".to_string()];
+    match field {
+        Setting::Set(value) => Some(value),
+        Setting::Reset => Some(&wildcard),
+        Setting::NotSet => None,
+    }
+    .serialize(s)
 }
 
 #[derive(Clone, Default, Debug)]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub struct Checked;
+
 #[derive(Clone, Default, Debug, Deserialize)]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub struct Unchecked;
@@ -42,75 +40,54 @@ pub struct Unchecked;
 pub struct Settings<T> {
     #[serde(
         default,
-        deserialize_with = "deserialize_some",
         serialize_with = "serialize_with_wildcard",
-        skip_serializing_if = "Option::is_none"
+        skip_serializing_if = "Setting::is_not_set"
     )]
-    pub displayed_attributes: Option<Option<Vec<String>>>,
+    pub displayed_attributes: Setting<Vec<String>>,
 
     #[serde(
         default,
-        deserialize_with = "deserialize_some",
         serialize_with = "serialize_with_wildcard",
-        skip_serializing_if = "Option::is_none"
+        skip_serializing_if = "Setting::is_not_set"
     )]
-    pub searchable_attributes: Option<Option<Vec<String>>>,
+    pub searchable_attributes: Setting<Vec<String>>,
 
-    #[serde(
-        default,
-        deserialize_with = "deserialize_some",
-        skip_serializing_if = "Option::is_none"
-    )]
-    pub filterable_attributes: Option<Option<BTreeSet<String>>>,
-
-    #[serde(
-        default,
-        deserialize_with = "deserialize_some",
-        skip_serializing_if = "Option::is_none"
-    )]
-    pub ranking_rules: Option<Option<Vec<String>>>,
-    #[serde(
-        default,
-        deserialize_with = "deserialize_some",
-        skip_serializing_if = "Option::is_none"
-    )]
-    pub stop_words: Option<Option<BTreeSet<String>>>,
-    #[serde(
-        default,
-        deserialize_with = "deserialize_some",
-        skip_serializing_if = "Option::is_none"
-    )]
-    pub synonyms: Option<Option<BTreeMap<String, Vec<String>>>>,
-    #[serde(
-        default,
-        deserialize_with = "deserialize_some",
-        skip_serializing_if = "Option::is_none"
-    )]
-    pub distinct_attribute: Option<Option<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub filterable_attributes: Setting<BTreeSet<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub sortable_attributes: Setting<BTreeSet<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub ranking_rules: Setting<Vec<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub stop_words: Setting<BTreeSet<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub synonyms: Setting<BTreeMap<String, Vec<String>>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub distinct_attribute: Setting<String>,
 
     #[serde(skip)]
     pub _kind: PhantomData<T>,
 }
 
 impl Settings<Unchecked> {
-    pub fn check(mut self) -> Settings<Checked> {
-        let displayed_attributes = match self.displayed_attributes.take() {
-            Some(Some(fields)) => {
+    pub fn check(self) -> Settings<Checked> {
+        let displayed_attributes = match self.displayed_attributes {
+            Setting::Set(fields) => {
                 if fields.iter().any(|f| f == "*") {
-                    Some(None)
+                    Setting::Reset
                 } else {
-                    Some(Some(fields))
+                    Setting::Set(fields)
                 }
             }
             otherwise => otherwise,
         };
 
-        let searchable_attributes = match self.searchable_attributes.take() {
-            Some(Some(fields)) => {
+        let searchable_attributes = match self.searchable_attributes {
+            Setting::Set(fields) => {
                 if fields.iter().any(|f| f == "*") {
-                    Some(None)
+                    Setting::Reset
                 } else {
-                    Some(Some(fields))
+                    Setting::Set(fields)
                 }
             }
             otherwise => otherwise,
@@ -120,6 +97,7 @@ impl Settings<Unchecked> {
             displayed_attributes,
             searchable_attributes,
             filterable_attributes: self.filterable_attributes,
+            sortable_attributes: self.sortable_attributes,
             ranking_rules: self.ranking_rules,
             stop_words: self.stop_words,
             synonyms: self.synonyms,
@@ -129,10 +107,61 @@ impl Settings<Unchecked> {
     }
 }
 
-static ASC_DESC_REGEX: Lazy<Regex> =
-    Lazy::new(|| Regex::new(r#"(asc|desc)\(([\w_-]+)\)"#).unwrap());
+#[derive(Debug, Clone, PartialEq)]
+pub enum Setting<T> {
+    Set(T),
+    Reset,
+    NotSet,
+}
 
-#[derive(Debug, Deserialize, Clone, PartialEq, Eq)]
+impl<T> Default for Setting<T> {
+    fn default() -> Self {
+        Self::NotSet
+    }
+}
+
+impl<T> Setting<T> {
+    pub const fn is_not_set(&self) -> bool {
+        matches!(self, Self::NotSet)
+    }
+
+    pub fn map<A>(self, f: fn(T) -> A) -> Setting<A> {
+        match self {
+            Setting::Set(a) => Setting::Set(f(a)),
+            Setting::Reset => Setting::Reset,
+            Setting::NotSet => Setting::NotSet,
+        }
+    }
+}
+
+#[cfg(test)]
+impl<T: serde::Serialize> serde::Serialize for Setting<T> {
+    fn serialize<S>(&self, serializer: S) -> std::result::Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        match self {
+            Self::Set(value) => Some(value),
+            // Usually not_set isn't serialized by setting skip_serializing_if field attribute
+            Self::NotSet | Self::Reset => None,
+        }
+        .serialize(serializer)
+    }
+}
+
+impl<'de, T: Deserialize<'de>> Deserialize<'de> for Setting<T> {
+    fn deserialize<D>(deserializer: D) -> std::result::Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        Deserialize::deserialize(deserializer).map(|x| match x {
+            Some(x) => Self::Set(x),
+            None => Self::Reset, // Reset is forced by sending null value
+        })
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
 pub enum Criterion {
     /// Sorted by decreasing number of matched query terms.
     /// Query words at the front of an attribute is considered better than if it was at the back.
@@ -142,8 +171,11 @@ pub enum Criterion {
     /// Sorted by increasing distance between matched query terms.
     Proximity,
     /// Documents with quey words contained in more important
-    /// attributes are considred better.
+    /// attributes are considered better.
     Attribute,
+    /// Dynamically sort at query time the documents. None, one or multiple Asc/Desc sortable
+    /// attributes can be used in place of this criterion at query time.
+    Sort,
     /// Sorted by the similarity of the matched words with the query words.
     Exactness,
     /// Sorted by the increasing value of the field specified.
@@ -152,40 +184,86 @@ pub enum Criterion {
     Desc(String),
 }
 
+impl Criterion {
+    /// Returns the field name parameter of this criterion.
+    pub fn field_name(&self) -> Option<&str> {
+        match self {
+            Criterion::Asc(name) | Criterion::Desc(name) => Some(name),
+            _otherwise => None,
+        }
+    }
+}
+
 impl FromStr for Criterion {
+    // since we're not going to show the custom error message we can override the
+    // error type.
     type Err = ();
 
-    fn from_str(txt: &str) -> Result<Criterion, Self::Err> {
-        match txt {
+    fn from_str(text: &str) -> Result<Criterion, Self::Err> {
+        match text {
             "words" => Ok(Criterion::Words),
             "typo" => Ok(Criterion::Typo),
             "proximity" => Ok(Criterion::Proximity),
             "attribute" => Ok(Criterion::Attribute),
+            "sort" => Ok(Criterion::Sort),
             "exactness" => Ok(Criterion::Exactness),
-            text => {
-                let caps = ASC_DESC_REGEX.captures(text).ok_or(())?;
-                let order = caps.get(1).unwrap().as_str();
-                let field_name = caps.get(2).unwrap().as_str();
-                match order {
-                    "asc" => Ok(Criterion::Asc(field_name.to_string())),
-                    "desc" => Ok(Criterion::Desc(field_name.to_string())),
-                    _text => Err(()),
-                }
-            }
+            text => match AscDesc::from_str(text) {
+                Ok(AscDesc::Asc(field)) => Ok(Criterion::Asc(field)),
+                Ok(AscDesc::Desc(field)) => Ok(Criterion::Desc(field)),
+                Err(_) => Err(()),
+            },
         }
     }
 }
 
-impl Display for Criterion {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        match self {
-            Criterion::Words => write!(f, "words"),
-            Criterion::Typo => write!(f, "typo"),
-            Criterion::Proximity => write!(f, "proximity"),
-            Criterion::Attribute => write!(f, "attribute"),
-            Criterion::Exactness => write!(f, "exactness"),
-            Criterion::Asc(field_name) => write!(f, "asc({})", field_name),
-            Criterion::Desc(field_name) => write!(f, "desc({})", field_name),
+#[derive(Debug, Deserialize, Clone, PartialEq, Eq)]
+pub enum AscDesc {
+    Asc(String),
+    Desc(String),
+}
+
+impl FromStr for AscDesc {
+    type Err = ();
+
+    // since we don't know if this comes from the old or new syntax we need to check
+    // for both syntax.
+    // WARN: this code doesn't come from the original meilisearch v0.22.0 but was
+    // written specifically to be able to import the dump of meilisearch v0.21.0 AND
+    // meilisearch v0.22.0.
+    fn from_str(text: &str) -> Result<AscDesc, Self::Err> {
+        if let Some((field_name, asc_desc)) = text.rsplit_once(':') {
+            match asc_desc {
+                "asc" => Ok(AscDesc::Asc(field_name.to_string())),
+                "desc" => Ok(AscDesc::Desc(field_name.to_string())),
+                _ => Err(()),
+            }
+        } else if text.starts_with("asc(") && text.ends_with(')') {
+            Ok(AscDesc::Asc(
+                text.strip_prefix("asc(").unwrap().strip_suffix(')').unwrap().to_string(),
+            ))
+        } else if text.starts_with("desc(") && text.ends_with(')') {
+            Ok(AscDesc::Desc(
+                text.strip_prefix("desc(").unwrap().strip_suffix(')').unwrap().to_string(),
+            ))
+        } else {
+            Err(())
+        }
+    }
+}
+
+impl fmt::Display for Criterion {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        use Criterion::*;
+
+        match self {
+            Words => f.write_str("words"),
+            Typo => f.write_str("typo"),
+            Proximity => f.write_str("proximity"),
+            Attribute => f.write_str("attribute"),
+            Sort => f.write_str("sort"),
+            Exactness => f.write_str("exactness"),
+            Asc(attr) => write!(f, "{}:asc", attr),
+            Desc(attr) => write!(f, "{}:desc", attr),
         }
     }
 }

dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2_from_meilisearch_v0_22_0_issue_3435-10.snap

@@ -0,0 +1,25 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: spells.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2_from_meilisearch_v0_22_0_issue_3435-4.snap

@@ -0,0 +1,39 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: products.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {
+    "android": [
+      "phone",
+      "smartphone"
+    ],
+    "iphone": [
+      "phone",
+      "smartphone"
+    ],
+    "phone": [
+      "android",
+      "iphone",
+      "smartphone"
+    ]
+  },
+  "distinctAttribute": null
+}

dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2_from_meilisearch_v0_22_0_issue_3435-7.snap

@@ -0,0 +1,30 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [
+    "genres",
+    "id"
+  ],
+  "sortableAttributes": [
+    "release_date"
+  ],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness",
+    "release_date:asc"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/v4/errors.rs

@@ -5,10 +5,8 @@ use serde::{Deserialize, Serialize};
 
 #[derive(Debug, Serialize, Deserialize, Clone, PartialEq, Eq)]
 #[serde(rename_all = "camelCase")]
-#[cfg_attr(feature = "test-traits", derive(proptest_derive::Arbitrary))]
 pub struct ResponseError {
     #[serde(skip)]
-    #[cfg_attr(feature = "test-traits", proptest(strategy = "strategy::status_code_strategy()"))]
     pub code: StatusCode,
     pub message: String,
     #[serde(rename = "code")]

dump/src/reader/v5/errors.rs

@@ -5,7 +5,6 @@ use serde::Deserialize;
 
 #[derive(Debug, Deserialize, Clone, PartialEq, Eq)]
 #[serde(rename_all = "camelCase")]
-#[cfg_attr(feature = "test-traits", derive(proptest_derive::Arbitrary))]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub struct ResponseError {
     #[serde(skip)]

dump/src/reader/v6/mod.rs

@@ -34,8 +34,7 @@ pub type PaginationSettings = meilisearch_types::settings::PaginationSettings;
 
 // everything related to the api keys
 pub type Action = meilisearch_types::keys::Action;
-pub type StarOr<T> = meilisearch_types::star_or::StarOr<T>;
-pub type IndexUid = meilisearch_types::index_uid::IndexUid;
+pub type IndexUidPattern = meilisearch_types::index_uid_pattern::IndexUidPattern;
 
 // everything related to the errors
 pub type ResponseError = meilisearch_types::error::ResponseError;

file-store/Cargo.toml

@@ -1,7 +1,14 @@
 [package]
 name = "file-store"
-version = "1.0.0"
-edition = "2021"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [dependencies]
 tempfile = "3.3.0"

file-store/src/lib.rs

@@ -1,4 +1,3 @@
-use std::collections::BTreeSet;
 use std::fs::File as StdFile;
 use std::ops::{Deref, DerefMut};
 use std::path::{Path, PathBuf};
@@ -11,10 +10,14 @@ const UPDATE_FILES_PATH: &str = "updates/updates_files";
 
 #[derive(Debug, thiserror::Error)]
 pub enum Error {
+    #[error("Could not parse file name as utf-8")]
+    CouldNotParseFileNameAsUtf8,
     #[error(transparent)]
     IoError(#[from] std::io::Error),
     #[error(transparent)]
     PersistError(#[from] tempfile::PersistError),
+    #[error(transparent)]
+    UuidError(#[from] uuid::Error),
 }
 
 pub type Result<T> = std::result::Result<T, Error>;
@@ -33,13 +36,11 @@ impl DerefMut for File {
     }
 }
 
-#[cfg_attr(test, faux::create)]
 #[derive(Clone, Debug)]
 pub struct FileStore {
     path: PathBuf,
 }
 
-#[cfg(not(test))]
 impl FileStore {
     pub fn new(path: impl AsRef<Path>) -> Result<FileStore> {
         let path = path.as_ref().to_path_buf();
@@ -48,7 +49,6 @@ impl FileStore {
     }
 }
 
-#[cfg_attr(test, faux::methods)]
 impl FileStore {
     /// Creates a new temporary update file.
     /// A call to `persist` is needed to persist the file in the database.
@@ -94,7 +94,17 @@ impl FileStore {
         Ok(())
     }
 
-    pub fn get_size(&self, uuid: Uuid) -> Result<u64> {
+    /// Compute the size of all the updates contained in the file store.
+    pub fn compute_total_size(&self) -> Result<u64> {
+        let mut total = 0;
+        for uuid in self.all_uuids()? {
+            total += self.compute_size(uuid?).unwrap_or_default();
+        }
+        Ok(total)
+    }
+
+    /// Compute the size of one update
+    pub fn compute_size(&self, uuid: Uuid) -> Result<u64> {
         Ok(self.get_update(uuid)?.metadata()?.len())
     }
 
@@ -105,17 +115,22 @@ impl FileStore {
     }
 
     /// List the Uuids of the files in the FileStore
-    ///
-    /// This function is meant to be used by tests only.
-    #[doc(hidden)]
-    pub fn __all_uuids(&self) -> BTreeSet<Uuid> {
-        let mut uuids = BTreeSet::new();
-        for entry in self.path.read_dir().unwrap() {
-            let entry = entry.unwrap();
-            let uuid = Uuid::from_str(entry.file_name().to_str().unwrap()).unwrap();
-            uuids.insert(uuid);
-        }
-        uuids
+    pub fn all_uuids(&self) -> Result<impl Iterator<Item = Result<Uuid>>> {
+        Ok(self.path.read_dir()?.filter_map(|entry| {
+            let file_name = match entry {
+                Ok(entry) => entry.file_name(),
+                Err(e) => return Some(Err(e.into())),
+            };
+            let file_name = match file_name.to_str() {
+                Some(file_name) => file_name,
+                None => return Some(Err(Error::CouldNotParseFileNameAsUtf8)),
+            };
+            if file_name.starts_with('.') {
+                None
+            } else {
+                Some(Uuid::from_str(file_name).map_err(|e| e.into()))
+            }
+        }))
     }
 }
 
@@ -130,3 +145,34 @@ impl File {
         Ok(())
     }
 }
+
+#[cfg(test)]
+mod test {
+    use std::io::Write;
+
+    use tempfile::TempDir;
+
+    use super::*;
+
+    #[test]
+    fn all_uuids() {
+        let dir = TempDir::new().unwrap();
+        let fs = FileStore::new(dir.path()).unwrap();
+        let (uuid, mut file) = fs.new_update().unwrap();
+        file.write_all(b"Hello world").unwrap();
+        file.persist().unwrap();
+        let all_uuids = fs.all_uuids().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(all_uuids, vec![uuid]);
+
+        let (uuid2, file) = fs.new_update().unwrap();
+        let all_uuids = fs.all_uuids().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(all_uuids, vec![uuid]);
+
+        file.persist().unwrap();
+        let mut all_uuids = fs.all_uuids().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        all_uuids.sort();
+        let mut expected = vec![uuid, uuid2];
+        expected.sort();
+        assert_eq!(all_uuids, expected);
+    }
+}

filter-parser/Cargo.toml

@@ -1,10 +1,16 @@
 [package]
 name = "filter-parser"
-version = "1.0.0"
-edition = "2021"
 description = "The parser for the Meilisearch filter syntax"
 publish = false
 
+version.workspace = true
+authors.workspace = true
+# description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
 [dependencies]
 nom = "7.1.1"
 nom_locate = "4.0.0"

filter-parser/src/error.rs

@@ -156,10 +156,10 @@ impl<'a> Display for Error<'a> {
                 writeln!(f, "The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.")?
             }
             ErrorKind::GeoBoundingBox => {
-                writeln!(f, "The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox((latitude, longitude), (latitude, longitude))`.")?
+                writeln!(f, "The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.")?
             }
             ErrorKind::ReservedGeo(name) => {
-                writeln!(f, "`{}` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance), or _geoBoundingBox((latitude, longitude), (latitude, longitude)) built-in rules to filter on `_geo` coordinates.", name.escape_debug())?
+                writeln!(f, "`{}` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance), or _geoBoundingBox([latitude, longitude], [latitude, longitude]) built-in rules to filter on `_geo` coordinates.", name.escape_debug())?
             }
             ErrorKind::MisusedGeoRadius => {
                 writeln!(f, "The `_geoRadius` filter is an operation and can't be used as a value.")?

filter-parser/src/lib.rs

@@ -18,7 +18,7 @@
 //! doubleQuoted   = "\"" .* all but double quotes "\""
 //! word           = (alphanumeric | _ | - | .)+
 //! geoRadius      = "_geoRadius(" WS* float WS* "," WS* float WS* "," float WS* ")"
-//! geoBoundingBox = "_geoBoundingBox((" WS * float WS* "," WS* float WS* "), (" WS* float WS* "," WS* float WS* ")")
+//! geoBoundingBox = "_geoBoundingBox([" WS * float WS* "," WS* float WS* "], [" WS* float WS* "," WS* float WS* "]")
 //! ```
 //!
 //! Other BNF grammar used to handle some specific errors:
@@ -88,10 +88,15 @@ impl<'a> Token<'a> {
         Self { span, value }
     }
 
+    /// Returns the string contained in the span of the `Token`.
+    /// This is only useful in the tests. You should always use
+    /// the value.
+    #[cfg(test)]
     pub fn lexeme(&self) -> &str {
         &self.span
     }
 
+    /// Return the string contained in the token.
     pub fn value(&self) -> &str {
         self.value.as_ref().map_or(&self.span, |value| value)
     }
@@ -136,7 +141,7 @@ pub enum FilterCondition<'a> {
     Or(Vec<Self>),
     And(Vec<Self>),
     GeoLowerThan { point: [Token<'a>; 2], radius: Token<'a> },
-    GeoBoundingBox { top_left_point: [Token<'a>; 2], bottom_right_point: [Token<'a>; 2] },
+    GeoBoundingBox { top_right_point: [Token<'a>; 2], bottom_left_point: [Token<'a>; 2] },
 }
 
 impl<'a> FilterCondition<'a> {
@@ -332,7 +337,7 @@ fn parse_geo_radius(input: Span) -> IResult<FilterCondition> {
     Ok((input, res))
 }
 
-/// geoBoundingBox      = WS* "_geoBoundingBox((float WS* "," WS* float WS* "), (float WS* "," WS* float WS* ")")
+/// geoBoundingBox      = WS* "_geoBoundingBox([float WS* "," WS* float WS* "], [float WS* "," WS* float WS* "]")
 /// If we parse `_geoBoundingBox` we MUST parse the rest of the expression.
 fn parse_geo_bounding_box(input: Span) -> IResult<FilterCondition> {
     // we want to allow space BEFORE the _geoBoundingBox but not after
@@ -343,7 +348,7 @@ fn parse_geo_bounding_box(input: Span) -> IResult<FilterCondition> {
             char('('),
             separated_list1(
                 tag(","),
-                ws(delimited(char('('), separated_list1(tag(","), ws(recognize_float)), char(')'))),
+                ws(delimited(char('['), separated_list1(tag(","), ws(recognize_float)), char(']'))),
             ),
             char(')'),
         )),
@@ -357,8 +362,8 @@ fn parse_geo_bounding_box(input: Span) -> IResult<FilterCondition> {
     }
 
     let res = FilterCondition::GeoBoundingBox {
-        top_left_point: [args[0][0].into(), args[0][1].into()],
-        bottom_right_point: [args[1][0].into(), args[1][1].into()],
+        top_right_point: [args[0][0].into(), args[0][1].into()],
+        bottom_left_point: [args[1][0].into(), args[1][1].into()],
     };
     Ok((input, res))
 }
@@ -510,9 +515,9 @@ pub mod tests {
         insta::assert_display_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})");
 
         // Test geo bounding box
-        insta::assert_display_snapshot!(p("_geoBoundingBox((12, 13), (14, 15))"), @"_geoBoundingBox(({12}, {13}), ({14}, {15}))");
-        insta::assert_display_snapshot!(p("NOT _geoBoundingBox((12, 13), (14, 15))"), @"NOT (_geoBoundingBox(({12}, {13}), ({14}, {15})))");
-        insta::assert_display_snapshot!(p("_geoBoundingBox((12,13),(14,15))"), @"_geoBoundingBox(({12}, {13}), ({14}, {15}))");
+        insta::assert_display_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
+        insta::assert_display_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))");
+        insta::assert_display_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
 
         // Test OR + AND
         insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
@@ -601,27 +606,27 @@ pub mod tests {
         "###);
 
         insta::assert_display_snapshot!(p("_geoBoundingBox"), @r###"
-        The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox((latitude, longitude), (latitude, longitude))`.
+        The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
         1:16 _geoBoundingBox
         "###);
 
         insta::assert_display_snapshot!(p("_geoBoundingBox = 12"), @r###"
-        The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox((latitude, longitude), (latitude, longitude))`.
+        The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
         1:21 _geoBoundingBox = 12
         "###);
 
         insta::assert_display_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###"
-        The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox((latitude, longitude), (latitude, longitude))`.
+        The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
         1:26 _geoBoundingBox(1.0, 1.0)
         "###);
 
         insta::assert_display_snapshot!(p("_geoPoint(12, 13, 14)"), @r###"
-        `_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance), or _geoBoundingBox((latitude, longitude), (latitude, longitude)) built-in rules to filter on `_geo` coordinates.
+        `_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance), or _geoBoundingBox([latitude, longitude], [latitude, longitude]) built-in rules to filter on `_geo` coordinates.
         1:22 _geoPoint(12, 13, 14)
         "###);
 
         insta::assert_display_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###"
-        `_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance), or _geoBoundingBox((latitude, longitude), (latitude, longitude)) built-in rules to filter on `_geo` coordinates.
+        `_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance), or _geoBoundingBox([latitude, longitude], [latitude, longitude]) built-in rules to filter on `_geo` coordinates.
         13:34 position <= _geoPoint(12, 13, 14)
         "###);
 
@@ -775,10 +780,13 @@ impl<'a> std::fmt::Display for FilterCondition<'a> {
             FilterCondition::GeoLowerThan { point, radius } => {
                 write!(f, "_geoRadius({}, {}, {})", point[0], point[1], radius)
             }
-            FilterCondition::GeoBoundingBox { top_left_point, bottom_right_point } => {
+            FilterCondition::GeoBoundingBox {
+                top_right_point: top_left_point,
+                bottom_left_point: bottom_right_point,
+            } => {
                 write!(
                     f,
-                    "_geoBoundingBox(({}, {}), ({}, {}))",
+                    "_geoBoundingBox([{}, {}], [{}, {}])",
                     top_left_point[0],
                     top_left_point[1],
                     bottom_right_point[0],

flatten-serde-json/Cargo.toml

@@ -1,11 +1,17 @@
 [package]
 name = "flatten-serde-json"
-version = "1.0.0"
-edition = "2021"
 description = "Flatten serde-json objects like elastic search"
 readme = "README.md"
 publish = false
 
+version.workspace = true
+authors.workspace = true
+# description.workspace = true
+homepage.workspace = true
+# readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
 [dependencies]
 serde_json = "1.0"
 

index-scheduler/Cargo.toml

@@ -1,7 +1,14 @@
 [package]
 name = "index-scheduler"
-version = "1.0.0"
-edition = "2021"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [dependencies]
 anyhow = "1.0.64"
@@ -12,6 +19,7 @@ dump = { path = "../dump" }
 enum-iterator = "1.1.3"
 file-store = { path = "../file-store" }
 log = "0.4.14"
+meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
 roaring = { version = "0.10.0", features = ["serde"] }

index-scheduler/src/autobatcher.rs

@@ -19,10 +19,16 @@ use crate::KindWithContent;
 ///
 /// Only the non-prioritised tasks that can be grouped in a batch have a corresponding [`AutobatchKind`]
 enum AutobatchKind {
-    DocumentImport { method: IndexDocumentsMethod, allow_index_creation: bool },
+    DocumentImport {
+        method: IndexDocumentsMethod,
+        allow_index_creation: bool,
+        primary_key: Option<String>,
+    },
     DocumentDeletion,
     DocumentClear,
-    Settings { allow_index_creation: bool },
+    Settings {
+        allow_index_creation: bool,
+    },
     IndexCreation,
     IndexDeletion,
     IndexUpdate,
@@ -38,14 +44,24 @@ impl AutobatchKind {
             _ => None,
         }
     }
+
+    fn primary_key(&self) -> Option<Option<&str>> {
+        match self {
+            AutobatchKind::DocumentImport { primary_key, .. } => Some(primary_key.as_deref()),
+            _ => None,
+        }
+    }
 }
 
 impl From<KindWithContent> for AutobatchKind {
     fn from(kind: KindWithContent) -> Self {
         match kind {
-            KindWithContent::DocumentAdditionOrUpdate { method, allow_index_creation, .. } => {
-                AutobatchKind::DocumentImport { method, allow_index_creation }
-            }
+            KindWithContent::DocumentAdditionOrUpdate {
+                method,
+                allow_index_creation,
+                primary_key,
+                ..
+            } => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key },
             KindWithContent::DocumentDeletion { .. } => AutobatchKind::DocumentDeletion,
             KindWithContent::DocumentClear { .. } => AutobatchKind::DocumentClear,
             KindWithContent::SettingsUpdate { allow_index_creation, is_deletion, .. } => {
@@ -72,10 +88,11 @@ pub enum BatchKind {
     DocumentClear {
         ids: Vec<TaskId>,
     },
-    DocumentImport {
+    DocumentOperation {
         method: IndexDocumentsMethod,
         allow_index_creation: bool,
-        import_ids: Vec<TaskId>,
+        primary_key: Option<String>,
+        operation_ids: Vec<TaskId>,
     },
     DocumentDeletion {
         deletion_ids: Vec<TaskId>,
@@ -85,11 +102,12 @@ pub enum BatchKind {
         allow_index_creation: bool,
         settings_ids: Vec<TaskId>,
     },
-    SettingsAndDocumentImport {
+    SettingsAndDocumentOperation {
         settings_ids: Vec<TaskId>,
         method: IndexDocumentsMethod,
         allow_index_creation: bool,
-        import_ids: Vec<TaskId>,
+        primary_key: Option<String>,
+        operation_ids: Vec<TaskId>,
     },
     Settings {
         allow_index_creation: bool,
@@ -113,13 +131,23 @@ impl BatchKind {
     #[rustfmt::skip]
     fn allow_index_creation(&self) -> Option<bool> {
         match self {
-            BatchKind::DocumentImport { allow_index_creation, .. }
+            BatchKind::DocumentOperation { allow_index_creation, .. }
             | BatchKind::ClearAndSettings { allow_index_creation, .. }
-            | BatchKind::SettingsAndDocumentImport { allow_index_creation, .. }
+            | BatchKind::SettingsAndDocumentOperation { allow_index_creation, .. }
             | BatchKind::Settings { allow_index_creation, .. } => Some(*allow_index_creation),
             _ => None,
         }
     }
+
+    fn primary_key(&self) -> Option<Option<&str>> {
+        match self {
+            BatchKind::DocumentOperation { primary_key, .. }
+            | BatchKind::SettingsAndDocumentOperation { primary_key, .. } => {
+                Some(primary_key.as_deref())
+            }
+            _ => None,
+        }
+    }
 }
 
 impl BatchKind {
@@ -131,6 +159,7 @@ impl BatchKind {
     pub fn new(
         task_id: TaskId,
         kind: KindWithContent,
+        primary_key: Option<&str>,
     ) -> (ControlFlow<BatchKind, BatchKind>, bool) {
         use AutobatchKind as K;
 
@@ -140,11 +169,26 @@ impl BatchKind {
             K::IndexUpdate => (Break(BatchKind::IndexUpdate { id: task_id }), false),
             K::IndexSwap => (Break(BatchKind::IndexSwap { id: task_id }), false),
             K::DocumentClear => (Continue(BatchKind::DocumentClear { ids: vec![task_id] }), false),
-            K::DocumentImport { method, allow_index_creation } => (
-                Continue(BatchKind::DocumentImport {
+            K::DocumentImport { method, allow_index_creation, primary_key: pk }
+                if primary_key.is_none() || pk.is_none() || primary_key == pk.as_deref() =>
+            {
+                (
+                    Continue(BatchKind::DocumentOperation {
+                        method,
+                        allow_index_creation,
+                        primary_key: pk,
+                        operation_ids: vec![task_id],
+                    }),
+                    allow_index_creation,
+                )
+            }
+            // if the primary key set in the task was different than ours we should stop and make this batch fail asap.
+            K::DocumentImport { method, allow_index_creation, primary_key } => (
+                Break(BatchKind::DocumentOperation {
                     method,
                     allow_index_creation,
-                    import_ids: vec![task_id],
+                    primary_key,
+                    operation_ids: vec![task_id],
                 }),
                 allow_index_creation,
             ),
@@ -163,7 +207,7 @@ impl BatchKind {
     /// To ease the writting of the code. `true` can be returned when you don't need to create an index
     /// but false can't be returned if you needs to create an index.
     #[rustfmt::skip]
-    fn accumulate(self, id: TaskId, kind: AutobatchKind, index_already_exists: bool) -> ControlFlow<BatchKind, BatchKind> {
+    fn accumulate(self, id: TaskId, kind: AutobatchKind, index_already_exists: bool, primary_key: Option<&str>) -> ControlFlow<BatchKind, BatchKind> {
         use AutobatchKind as K;
 
         match (self, kind) {
@@ -173,11 +217,39 @@ impl BatchKind {
             (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
                 Break(this)
             },
+            // NOTE: We need to negate the whole condition since we're checking if we need to break instead of continue.
+            //       I wrote it this way because it's easier to understand than the other way around.
+            (this, kind) if !(
+                // 1. If both task don't interact with primary key -> we can continue
+                (this.primary_key().is_none() && kind.primary_key().is_none()) ||
+                // 2. Else ->
+                (
+                    // 2.1 If we already have a primary-key ->
+                    (
+                        primary_key.is_some() &&
+                        // 2.1.1 If the task we're trying to accumulate have a pk it must be equal to our primary key
+                        // 2.1.2 If the task don't have a primary-key -> we can continue
+                        kind.primary_key().map_or(true, |pk| pk == primary_key)
+                    ) ||
+                    // 2.2 If we don't have a primary-key ->
+                    (
+                        // 2.2.1 If both the batch and the task have a primary key they should be equal
+                        // 2.2.2 If the batch is set to Some(None), the task should be too
+                        // 2.2.3 If the batch is set to None -> we can continue
+                        this.primary_key().zip(kind.primary_key()).map_or(true, |(this, kind)| this == kind)
+                    )
+                )
+
+                ) // closing the negation
+
+            => {
+                Break(this)
+            },
             // The index deletion can batch with everything but must stop after
             (
                 BatchKind::DocumentClear { mut ids }
                 | BatchKind::DocumentDeletion { deletion_ids: mut ids }
-                | BatchKind::DocumentImport { method: _, allow_index_creation: _, import_ids: mut ids }
+                | BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, operation_ids: mut ids }
                 | BatchKind::Settings { allow_index_creation: _, settings_ids: mut ids },
                 K::IndexDeletion,
             ) => {
@@ -186,7 +258,7 @@ impl BatchKind {
             }
             (
                 BatchKind::ClearAndSettings { settings_ids: mut ids, allow_index_creation: _, mut other }
-                | BatchKind::SettingsAndDocumentImport { import_ids: mut ids, method: _, allow_index_creation: _, settings_ids: mut other },
+                | BatchKind::SettingsAndDocumentOperation { operation_ids: mut ids, method: _, allow_index_creation: _, primary_key: _, settings_ids: mut other },
                 K::IndexDeletion,
             ) => {
                 ids.push(id);
@@ -206,59 +278,71 @@ impl BatchKind {
                 K::DocumentImport { .. } | K::Settings { .. },
             ) => Break(this),
             (
-                BatchKind::DocumentImport { method: _, allow_index_creation: _, import_ids: mut ids },
+                BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, mut operation_ids },
                 K::DocumentClear,
             ) => {
-                ids.push(id);
-                Continue(BatchKind::DocumentClear { ids })
+                operation_ids.push(id);
+                Continue(BatchKind::DocumentClear { ids: operation_ids })
             }
 
             // we can autobatch the same kind of document additions / updates
             (
-                BatchKind::DocumentImport { method: ReplaceDocuments, allow_index_creation, mut import_ids },
-                K::DocumentImport { method: ReplaceDocuments, .. },
+                BatchKind::DocumentOperation { method: ReplaceDocuments, allow_index_creation, primary_key: _, mut operation_ids },
+                K::DocumentImport { method: ReplaceDocuments, primary_key: pk, .. },
             ) => {
-                import_ids.push(id);
-                Continue(BatchKind::DocumentImport {
+                operation_ids.push(id);
+                Continue(BatchKind::DocumentOperation {
                     method: ReplaceDocuments,
                     allow_index_creation,
-                    import_ids,
+                    operation_ids,
+                    primary_key: pk,
                 })
             }
             (
-                BatchKind::DocumentImport { method: UpdateDocuments, allow_index_creation, mut import_ids },
-                K::DocumentImport { method: UpdateDocuments, .. },
+                BatchKind::DocumentOperation { method: UpdateDocuments, allow_index_creation, primary_key: _, mut operation_ids },
+                K::DocumentImport { method: UpdateDocuments, primary_key: pk, .. },
             ) => {
-                import_ids.push(id);
-                Continue(BatchKind::DocumentImport {
+                operation_ids.push(id);
+                Continue(BatchKind::DocumentOperation {
                     method: UpdateDocuments,
                     allow_index_creation,
-                    import_ids,
+                    primary_key: pk,
+                    operation_ids,
                 })
             }
-
+            (
+                this @ BatchKind::DocumentOperation { .. },
+                K::DocumentDeletion,
+            ) => Break(this),
             // but we can't autobatch documents if it's not the same kind
             // this match branch MUST be AFTER the previous one
             (
-                this @ BatchKind::DocumentImport { .. },
-                K::DocumentDeletion | K::DocumentImport { .. },
+                this @ BatchKind::DocumentOperation { .. },
+                K::DocumentImport { .. },
             ) => Break(this),
 
             (
-                BatchKind::DocumentImport { method, allow_index_creation, import_ids },
+                BatchKind::DocumentOperation { method, allow_index_creation, primary_key, operation_ids },
                 K::Settings { .. },
-            ) => Continue(BatchKind::SettingsAndDocumentImport {
+            ) => Continue(BatchKind::SettingsAndDocumentOperation {
                 settings_ids: vec![id],
                 method,
                 allow_index_creation,
-                import_ids,
+                primary_key,
+                operation_ids,
             }),
 
             (BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentClear) => {
                 deletion_ids.push(id);
                 Continue(BatchKind::DocumentClear { ids: deletion_ids })
             }
-            (this @ BatchKind::DocumentDeletion { .. }, K::DocumentImport { .. }) => Break(this),
+            // we can't autobatch a deletion and an import
+            (
+                this @ BatchKind::DocumentDeletion { .. },
+                K::DocumentImport { .. }
+            ) => {
+                Break(this)
+            }
             (BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentDeletion) => {
                 deletion_ids.push(id);
                 Continue(BatchKind::DocumentDeletion { deletion_ids })
@@ -327,57 +411,60 @@ impl BatchKind {
                 })
             }
             (
-                BatchKind::SettingsAndDocumentImport { settings_ids, method: _, import_ids: mut other, allow_index_creation },
+                BatchKind::SettingsAndDocumentOperation { settings_ids, method: _, mut operation_ids, allow_index_creation, primary_key: _ },
                 K::DocumentClear,
             ) => {
-                other.push(id);
+                operation_ids.push(id);
                 Continue(BatchKind::ClearAndSettings {
                     settings_ids,
-                    other,
+                    other: operation_ids,
                     allow_index_creation,
                 })
             }
 
             (
-                BatchKind::SettingsAndDocumentImport { settings_ids, method: ReplaceDocuments, mut import_ids, allow_index_creation },
-                K::DocumentImport { method: ReplaceDocuments, .. },
+                BatchKind::SettingsAndDocumentOperation { settings_ids, method: ReplaceDocuments, mut operation_ids, allow_index_creation, primary_key: _},
+                K::DocumentImport { method: ReplaceDocuments, primary_key: pk2, .. },
             ) => {
-                import_ids.push(id);
-                Continue(BatchKind::SettingsAndDocumentImport {
+                operation_ids.push(id);
+                Continue(BatchKind::SettingsAndDocumentOperation {
                     settings_ids,
                     method: ReplaceDocuments,
                     allow_index_creation,
-                    import_ids,
+                        primary_key: pk2,
+                    operation_ids,
                 })
             }
             (
-                BatchKind::SettingsAndDocumentImport { settings_ids, method: UpdateDocuments, allow_index_creation, mut import_ids },
-                K::DocumentImport { method: UpdateDocuments, .. },
+                BatchKind::SettingsAndDocumentOperation { settings_ids, method: UpdateDocuments, allow_index_creation, primary_key: _, mut operation_ids },
+                K::DocumentImport { method: UpdateDocuments, primary_key: pk2, .. },
             ) => {
-                import_ids.push(id);
-                Continue(BatchKind::SettingsAndDocumentImport {
+                operation_ids.push(id);
+                Continue(BatchKind::SettingsAndDocumentOperation {
                     settings_ids,
                     method: UpdateDocuments,
                     allow_index_creation,
-                    import_ids,
+                    primary_key: pk2,
+                    operation_ids,
                 })
             }
             // But we can't batch a settings and a doc op with another doc op
             // this MUST be AFTER the two previous branch
             (
-                this @ BatchKind::SettingsAndDocumentImport { .. },
+                this @ BatchKind::SettingsAndDocumentOperation { .. },
                 K::DocumentDeletion | K::DocumentImport { .. },
             ) => Break(this),
             (
-                BatchKind::SettingsAndDocumentImport { mut settings_ids, method, allow_index_creation, import_ids },
+                BatchKind::SettingsAndDocumentOperation { mut settings_ids, method, allow_index_creation,primary_key, operation_ids },
                 K::Settings { .. },
             ) => {
                 settings_ids.push(id);
-                Continue(BatchKind::SettingsAndDocumentImport {
+                Continue(BatchKind::SettingsAndDocumentOperation {
                     settings_ids,
                     method,
                     allow_index_creation,
-                    import_ids,
+                    primary_key,
+                    operation_ids,
                 })
             }
             (
@@ -406,6 +493,7 @@ impl BatchKind {
 pub fn autobatch(
     enqueued: Vec<(TaskId, KindWithContent)>,
     index_already_exists: bool,
+    primary_key: Option<&str>,
 ) -> Option<(BatchKind, bool)> {
     let mut enqueued = enqueued.into_iter();
     let (id, kind) = enqueued.next()?;
@@ -413,7 +501,7 @@ pub fn autobatch(
     // index_exist will keep track of if the index should exist at this point after the tasks we batched.
     let mut index_exist = index_already_exists;
 
-    let (mut acc, must_create_index) = match BatchKind::new(id, kind) {
+    let (mut acc, must_create_index) = match BatchKind::new(id, kind, primary_key) {
         (Continue(acc), create) => (acc, create),
         (Break(acc), create) => return Some((acc, create)),
     };
@@ -422,7 +510,7 @@ pub fn autobatch(
     index_exist |= must_create_index;
 
     for (id, kind) in enqueued {
-        acc = match acc.accumulate(id, kind.into(), index_exist) {
+        acc = match acc.accumulate(id, kind.into(), index_exist, primary_key) {
             Continue(acc) => acc,
             Break(acc) => return Some((acc, must_create_index)),
         };
@@ -441,18 +529,24 @@ mod tests {
 
     fn autobatch_from(
         index_already_exists: bool,
+        primary_key: Option<&str>,
         input: impl IntoIterator<Item = KindWithContent>,
     ) -> Option<(BatchKind, bool)> {
         autobatch(
             input.into_iter().enumerate().map(|(id, kind)| (id as TaskId, kind)).collect(),
             index_already_exists,
+            primary_key,
         )
     }
 
-    fn doc_imp(method: IndexDocumentsMethod, allow_index_creation: bool) -> KindWithContent {
+    fn doc_imp(
+        method: IndexDocumentsMethod,
+        allow_index_creation: bool,
+        primary_key: Option<&str>,
+    ) -> KindWithContent {
         KindWithContent::DocumentAdditionOrUpdate {
             index_uid: String::from("doggo"),
-            primary_key: None,
+            primary_key: primary_key.map(|pk| pk.to_string()),
             method,
             content_file: Uuid::new_v4(),
             documents_count: 0,
@@ -502,226 +596,301 @@ mod tests {
     fn autobatch_simple_operation_together() {
         // we can autobatch one or multiple `ReplaceDocuments` together.
         // if the index exists.
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, false)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp( ReplaceDocuments, true ), doc_imp(ReplaceDocuments, true )]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, false), doc_imp( ReplaceDocuments, false ), doc_imp(ReplaceDocuments, false )]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp( ReplaceDocuments, false , None), doc_imp(ReplaceDocuments, false , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
         // if it doesn't exists.
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, false)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true), doc_imp( ReplaceDocuments, true ), doc_imp(ReplaceDocuments, true )]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, false), doc_imp( ReplaceDocuments, true ), doc_imp(ReplaceDocuments, true )]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
         // we can autobatch one or multiple `UpdateDocuments` together.
         // if the index exists.
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false), doc_imp(UpdateDocuments, false), doc_imp(UpdateDocuments, false)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: false, import_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
         // if it doesn't exists.
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false), doc_imp(UpdateDocuments, false), doc_imp(UpdateDocuments, false)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: false, import_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
         // we can autobatch one or multiple DocumentDeletion together
-        debug_snapshot!(autobatch_from(true, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
 
         // we can autobatch one or multiple Settings together
-        debug_snapshot!(autobatch_from(true, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
 
-        debug_snapshot!(autobatch_from(false, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(false, [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(false, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
+
+        // We can't autobatch document addition with document deletion
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        // we also can't do the only way around
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
     }
 
     #[test]
     fn simple_document_operation_dont_autobatch_with_other() {
         // addition, updates and deletion can't batch together
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(UpdateDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_del()]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), doc_del()]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), doc_imp(UpdateDocuments, true)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), idx_create()]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), idx_create()]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
 
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), idx_update()]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), idx_update()]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
 
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), idx_swap()]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), idx_swap()]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
     }
 
     #[test]
     fn document_addition_batch_with_settings() {
         // simple case
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
         // multiple settings and doc addition
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true), settings(true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [2, 3], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true), settings(true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [2, 3], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [2, 3], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [2, 3], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
 
         // addition and setting unordered
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), doc_imp(ReplaceDocuments, true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1, 3], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), doc_imp(UpdateDocuments, true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1, 3], method: UpdateDocuments, allow_index_creation: true, import_ids: [0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1, 3], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1, 3], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 2] }, true))");
 
         // We ensure this kind of batch doesn't batch with forbidden operations
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), doc_imp(UpdateDocuments, true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), doc_imp(ReplaceDocuments, true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), doc_del()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), doc_del()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), idx_create()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), idx_create()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), idx_update()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), idx_update()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), idx_swap()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), idx_swap()]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, import_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_del()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_del()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_create()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_create()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_update()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_update()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_swap()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_swap()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
     }
 
     #[test]
     fn clear_and_additions() {
         // these two doesn't need to batch
-        debug_snapshot!(autobatch_from(true, [doc_clr(), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentClear { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_clr(), doc_imp(UpdateDocuments, true)]), @"Some((DocumentClear { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false))");
 
         // Basic use case
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
 
         // This batch kind doesn't mix with other document addition
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true), doc_clr(), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true), doc_clr(), doc_imp(UpdateDocuments, true)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
 
         // But you can batch multiple clear together
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), doc_imp(UpdateDocuments, true), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true))");
     }
 
     #[test]
     fn clear_and_additions_and_settings() {
         // A clear don't need to autobatch the settings that happens AFTER there is no documents
-        debug_snapshot!(autobatch_from(true, [doc_clr(), settings(true)]), @"Some((DocumentClear { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_clr(), settings(true)]), @"Some((DocumentClear { ids: [0] }, false))");
 
-        debug_snapshot!(autobatch_from(true, [settings(true), doc_clr(), settings(true)]), @"Some((ClearAndSettings { other: [1], allow_index_creation: true, settings_ids: [0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), doc_clr()]), @"Some((ClearAndSettings { other: [0, 2], allow_index_creation: true, settings_ids: [1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), doc_clr()]), @"Some((ClearAndSettings { other: [0, 2], allow_index_creation: true, settings_ids: [1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [settings(true), doc_clr(), settings(true)]), @"Some((ClearAndSettings { other: [1], allow_index_creation: true, settings_ids: [0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr()]), @"Some((ClearAndSettings { other: [0, 2], allow_index_creation: true, settings_ids: [1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr()]), @"Some((ClearAndSettings { other: [0, 2], allow_index_creation: true, settings_ids: [1] }, true))");
     }
 
     #[test]
     fn anything_and_index_deletion() {
         // The `IndexDeletion` doesn't batch with anything that happens AFTER.
-        debug_snapshot!(autobatch_from(true, [idx_del(), doc_imp(ReplaceDocuments, true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), doc_imp(UpdateDocuments, true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), doc_imp(ReplaceDocuments, false)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), doc_imp(UpdateDocuments, false)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
 
-        debug_snapshot!(autobatch_from(false, [idx_del(), doc_imp(ReplaceDocuments, true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), doc_imp(UpdateDocuments, true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), doc_imp(ReplaceDocuments, false)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), doc_imp(UpdateDocuments, false)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
 
         // The index deletion can accept almost any type of `BatchKind` and transform it to an `IndexDeletion`.
         // First, the basic cases
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
 
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
 
         // Then the mixed cases.
         // The index already exists, whatever is the right of the tasks it shouldn't change the result.
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments,false), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments,false), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments,false), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments,false), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, false), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments,true), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments,true), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(UpdateDocuments, true), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
 
         // When the index doesn't exists yet it's more complicated.
         // Either the first task we encounter create it, in which case we can create a big batch with everything.
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
         // The right of the tasks following isn't really important.
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments,true), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments,true), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, true), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
         // Or, the second case; the first task doesn't create the index and thus we wants to batch it with only tasks that can't create an index.
         // that can be a second task that don't have the right to create an index. Or anything that can't create an index like an index deletion, document deletion, document clear, etc.
         // All theses tasks are going to throw an error `Index doesn't exist` once the batch is processed.
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments,false), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments,false), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
         // The third and final case is when the first task doesn't create an index but is directly followed by a task creating an index. In this case we can't batch whith what
         // follows because we first need to process the erronous batch.
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments,false), settings(true), idx_del()]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false), settings(true), idx_del()]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments,false), settings(true), doc_clr(), idx_del()]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(UpdateDocuments, false), settings(true), doc_clr(), idx_del()]), @"Some((DocumentImport { method: UpdateDocuments, allow_index_creation: false, import_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(true), idx_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(true), idx_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(true), doc_clr(), idx_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(true), doc_clr(), idx_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
     }
 
     #[test]
     fn allowed_and_disallowed_index_creation() {
         // `DocumentImport` can't be mixed with those disallowed to do so except if the index already exists.
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, false), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, false), doc_imp(ReplaceDocuments, false)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, [doc_imp(ReplaceDocuments, false), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, false), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true), doc_imp(ReplaceDocuments, true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: true, import_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, false), doc_imp(ReplaceDocuments, false)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, true), settings(true)]), @"Some((SettingsAndDocumentImport { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, import_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(false, [doc_imp(ReplaceDocuments, false), settings(true)]), @"Some((DocumentImport { method: ReplaceDocuments, allow_index_creation: false, import_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+
+        // batch deletion and addition
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+    }
+
+    #[test]
+    fn autobatch_primary_key() {
+        // ==> If I have a pk
+        // With a single update
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+
+        // With a multiple updates
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other"))]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
+
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+
+        // ==> If I don't have a pk
+        // With a single update
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
+
+        // With a multiple updates
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
     }
 }

index-scheduler/src/batch.rs

@@ -28,8 +28,7 @@ use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
 use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::update::{
-    DocumentAdditionResult, DocumentDeletionResult, IndexDocumentsConfig, IndexDocumentsMethod,
-    Settings as MilliSettings,
+    DocumentDeletionResult, IndexDocumentsConfig, IndexDocumentsMethod, Settings as MilliSettings,
 };
 use meilisearch_types::milli::{self, BEU32};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
@@ -86,15 +85,21 @@ pub(crate) enum Batch {
     },
 }
 
+#[derive(Debug)]
+pub(crate) enum DocumentOperation {
+    Add(Uuid),
+    Delete(Vec<String>),
+}
+
 /// A [batch](Batch) that combines multiple tasks operating on an index.
 #[derive(Debug)]
 pub(crate) enum IndexOperation {
-    DocumentImport {
+    DocumentOperation {
         index_uid: String,
         primary_key: Option<String>,
         method: IndexDocumentsMethod,
         documents_counts: Vec<u64>,
-        content_files: Vec<Uuid>,
+        operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
     DocumentDeletion {
@@ -121,13 +126,13 @@ pub(crate) enum IndexOperation {
         settings: Vec<(bool, Settings<Unchecked>)>,
         settings_tasks: Vec<Task>,
     },
-    SettingsAndDocumentImport {
+    SettingsAndDocumentOperation {
         index_uid: String,
 
         primary_key: Option<String>,
         method: IndexDocumentsMethod,
         documents_counts: Vec<u64>,
-        content_files: Vec<Uuid>,
+        operations: Vec<DocumentOperation>,
         document_import_tasks: Vec<Task>,
 
         // The boolean indicates if it's a settings deletion or creation.
@@ -149,13 +154,13 @@ impl Batch {
                 tasks.iter().map(|task| task.uid).collect()
             }
             Batch::IndexOperation { op, .. } => match op {
-                IndexOperation::DocumentImport { tasks, .. }
+                IndexOperation::DocumentOperation { tasks, .. }
                 | IndexOperation::DocumentDeletion { tasks, .. }
                 | IndexOperation::Settings { tasks, .. }
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     tasks.iter().map(|task| task.uid).collect()
                 }
-                IndexOperation::SettingsAndDocumentImport {
+                IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
                     ..
@@ -169,17 +174,33 @@ impl Batch {
             Batch::IndexSwap { task } => vec![task.uid],
         }
     }
+
+    /// Return the index UID associated with this batch
+    pub fn index_uid(&self) -> Option<&str> {
+        use Batch::*;
+        match self {
+            TaskCancelation { .. }
+            | TaskDeletion(_)
+            | SnapshotCreation(_)
+            | Dump(_)
+            | IndexSwap { .. } => None,
+            IndexOperation { op, .. } => Some(op.index_uid()),
+            IndexCreation { index_uid, .. }
+            | IndexUpdate { index_uid, .. }
+            | IndexDeletion { index_uid, .. } => Some(index_uid),
+        }
+    }
 }
 
 impl IndexOperation {
     pub fn index_uid(&self) -> &str {
         match self {
-            IndexOperation::DocumentImport { index_uid, .. }
+            IndexOperation::DocumentOperation { index_uid, .. }
             | IndexOperation::DocumentDeletion { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
-            | IndexOperation::SettingsAndDocumentImport { index_uid, .. } => index_uid,
+            | IndexOperation::SettingsAndDocumentOperation { index_uid, .. } => index_uid,
         }
     }
 }
@@ -206,18 +227,24 @@ impl IndexScheduler {
                 },
                 must_create_index,
             })),
-            BatchKind::DocumentImport { method, import_ids, .. } => {
-                let tasks = self.get_existing_tasks(rtxn, import_ids)?;
-                let primary_key = match &tasks[0].kind {
-                    KindWithContent::DocumentAdditionOrUpdate { primary_key, .. } => {
-                        primary_key.clone()
-                    }
-                    _ => unreachable!(),
-                };
+            BatchKind::DocumentOperation { method, operation_ids, .. } => {
+                let tasks = self.get_existing_tasks(rtxn, operation_ids)?;
+                let primary_key = tasks
+                    .iter()
+                    .find_map(|task| match task.kind {
+                        KindWithContent::DocumentAdditionOrUpdate { ref primary_key, .. } => {
+                            // we want to stop on the first document addition
+                            Some(primary_key.clone())
+                        }
+                        KindWithContent::DocumentDeletion { .. } => None,
+                        _ => unreachable!(),
+                    })
+                    .flatten();
 
                 let mut documents_counts = Vec::new();
-                let mut content_files = Vec::new();
-                for task in &tasks {
+                let mut operations = Vec::new();
+
+                for task in tasks.iter() {
                     match task.kind {
                         KindWithContent::DocumentAdditionOrUpdate {
                             content_file,
@@ -225,19 +252,23 @@ impl IndexScheduler {
                             ..
                         } => {
                             documents_counts.push(documents_count);
-                            content_files.push(content_file);
+                            operations.push(DocumentOperation::Add(content_file));
+                        }
+                        KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
+                            documents_counts.push(documents_ids.len() as u64);
+                            operations.push(DocumentOperation::Delete(documents_ids.clone()));
                         }
                         _ => unreachable!(),
                     }
                 }
 
                 Ok(Some(Batch::IndexOperation {
-                    op: IndexOperation::DocumentImport {
+                    op: IndexOperation::DocumentOperation {
                         index_uid,
                         primary_key,
                         method,
                         documents_counts,
-                        content_files,
+                        operations,
                         tasks,
                     },
                     must_create_index,
@@ -321,11 +352,12 @@ impl IndexScheduler {
                     must_create_index,
                 }))
             }
-            BatchKind::SettingsAndDocumentImport {
+            BatchKind::SettingsAndDocumentOperation {
                 settings_ids,
                 method,
                 allow_index_creation,
-                import_ids,
+                primary_key,
+                operation_ids,
             } => {
                 let settings = self.create_next_batch_index(
                     rtxn,
@@ -337,7 +369,12 @@ impl IndexScheduler {
                 let document_import = self.create_next_batch_index(
                     rtxn,
                     index_uid.clone(),
-                    BatchKind::DocumentImport { method, allow_index_creation, import_ids },
+                    BatchKind::DocumentOperation {
+                        method,
+                        allow_index_creation,
+                        primary_key,
+                        operation_ids,
+                    },
                     must_create_index,
                 )?;
 
@@ -345,10 +382,10 @@ impl IndexScheduler {
                     (
                         Some(Batch::IndexOperation {
                             op:
-                                IndexOperation::DocumentImport {
+                                IndexOperation::DocumentOperation {
                                     primary_key,
                                     documents_counts,
-                                    content_files,
+                                    operations,
                                     tasks: document_import_tasks,
                                     ..
                                 },
@@ -359,12 +396,12 @@ impl IndexScheduler {
                             ..
                         }),
                     ) => Ok(Some(Batch::IndexOperation {
-                        op: IndexOperation::SettingsAndDocumentImport {
+                        op: IndexOperation::SettingsAndDocumentOperation {
                             index_uid,
                             primary_key,
                             method,
                             documents_counts,
-                            content_files,
+                            operations,
                             document_import_tasks,
                             settings,
                             settings_tasks,
@@ -467,6 +504,12 @@ impl IndexScheduler {
         };
 
         let index_already_exists = self.index_mapper.exists(rtxn, index_name)?;
+        let mut primary_key = None;
+        if index_already_exists {
+            let index = self.index_mapper.index(rtxn, index_name)?;
+            let rtxn = index.read_txn()?;
+            primary_key = index.primary_key(&rtxn)?.map(|pk| pk.to_string());
+        }
 
         let index_tasks = self.index_tasks(rtxn, index_name)? & enqueued;
 
@@ -484,7 +527,7 @@ impl IndexScheduler {
             .collect::<Result<Vec<_>>>()?;
 
         if let Some((batchkind, create_index)) =
-            autobatcher::autobatch(enqueued, index_already_exists)
+            autobatcher::autobatch(enqueued, index_already_exists, primary_key.as_deref())
         {
             return self.create_next_batch_index(
                 rtxn,
@@ -632,9 +675,6 @@ impl IndexScheduler {
                 }
 
                 // 3. Snapshot every indexes
-                // TODO we are opening all of the indexes it can be too much we should unload all
-                //      of the indexes we are trying to open. It would be even better to only unload
-                //      the ones that were opened by us. Or maybe use a LRU in the index mapper.
                 for result in self.index_mapper.index_mapping.iter(&rtxn)? {
                     let (name, uuid) = result?;
                     let index = self.index_mapper.index(&rtxn, name)?;
@@ -671,6 +711,14 @@ impl IndexScheduler {
                 // 5.3 Change the permission to make the snapshot readonly
                 let mut permissions = file.metadata()?.permissions();
                 permissions.set_readonly(true);
+                #[cfg(unix)]
+                {
+                    use std::os::unix::fs::PermissionsExt;
+                    #[allow(clippy::non_octal_unix_permissions)]
+                    //                     rwxrwxrwx
+                    permissions.set_mode(0b100100100);
+                }
+
                 file.set_permissions(permissions)?;
 
                 for task in &mut tasks {
@@ -745,15 +793,15 @@ impl IndexScheduler {
                 dump_tasks.flush()?;
 
                 // 3. Dump the indexes
-                for (uid, index) in self.index_mapper.indexes(&rtxn)? {
+                self.index_mapper.try_for_each_index(&rtxn, |uid, index| -> Result<()> {
                     let rtxn = index.read_txn()?;
                     let metadata = IndexMetadata {
-                        uid: uid.clone(),
+                        uid: uid.to_owned(),
                         primary_key: index.primary_key(&rtxn)?.map(String::from),
                         created_at: index.created_at(&rtxn)?,
                         updated_at: index.updated_at(&rtxn)?,
                     };
-                    let mut index_dumper = dump.create_index(&uid, &metadata)?;
+                    let mut index_dumper = dump.create_index(uid, &metadata)?;
 
                     let fields_ids_map = index.fields_ids_map(&rtxn)?;
                     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
@@ -766,9 +814,10 @@ impl IndexScheduler {
                     }
 
                     // 3.2. Dump the settings
-                    let settings = meilisearch_types::settings::settings(&index, &rtxn)?;
+                    let settings = meilisearch_types::settings::settings(index, &rtxn)?;
                     index_dumper.settings(&settings)?;
-                }
+                    Ok(())
+                })?;
 
                 let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"
@@ -784,20 +833,38 @@ impl IndexScheduler {
                 Ok(vec![task])
             }
             Batch::IndexOperation { op, must_create_index } => {
-                let index_uid = op.index_uid();
+                let index_uid = op.index_uid().to_string();
                 let index = if must_create_index {
                     // create the index if it doesn't already exist
                     let wtxn = self.env.write_txn()?;
-                    self.index_mapper.create_index(wtxn, index_uid, None)?
+                    self.index_mapper.create_index(wtxn, &index_uid, None)?
                 } else {
                     let rtxn = self.env.read_txn()?;
-                    self.index_mapper.index(&rtxn, index_uid)?
+                    self.index_mapper.index(&rtxn, &index_uid)?
                 };
 
                 let mut index_wtxn = index.write_txn()?;
                 let tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
                 index_wtxn.commit()?;
 
+                // if the update processed successfully, we're going to store the new
+                // stats of the index. Since the tasks have already been processed and
+                // this is a non-critical operation. If it fails, we should not fail
+                // the entire batch.
+                let res = || -> Result<()> {
+                    let index_rtxn = index.read_txn()?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
+                    let mut wtxn = self.env.write_txn()?;
+                    self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
+                    wtxn.commit()?;
+                    Ok(())
+                }();
+
+                match res {
+                    Ok(_) => (),
+                    Err(e) => error!("Could not write the stats of the index {}", e),
+                }
+
                 Ok(tasks)
             }
             Batch::IndexCreation { index_uid, primary_key, task } => {
@@ -828,9 +895,31 @@ impl IndexScheduler {
                     )?;
                     index_wtxn.commit()?;
                 }
+
+                // drop rtxn before starting a new wtxn on the same db
+                rtxn.commit()?;
+
                 task.status = Status::Succeeded;
                 task.details = Some(Details::IndexInfo { primary_key });
 
+                // if the update processed successfully, we're going to store the new
+                // stats of the index. Since the tasks have already been processed and
+                // this is a non-critical operation. If it fails, we should not fail
+                // the entire batch.
+                let res = || -> Result<()> {
+                    let mut wtxn = self.env.write_txn()?;
+                    let index_rtxn = index.read_txn()?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
+                    self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
+                    wtxn.commit()?;
+                    Ok(())
+                }();
+
+                match res {
+                    Ok(_) => (),
+                    Err(e) => error!("Could not write the stats of the index {}", e),
+                }
+
                 Ok(vec![task])
             }
             Batch::IndexDeletion { index_uid, index_has_been_created, mut tasks } => {
@@ -949,7 +1038,7 @@ impl IndexScheduler {
     /// The list of processed tasks.
     fn apply_index_operation<'i>(
         &self,
-        index_wtxn: &'_ mut RwTxn<'i, '_>,
+        index_wtxn: &mut RwTxn<'i, '_>,
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
@@ -974,28 +1063,42 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
-            IndexOperation::DocumentImport {
+            IndexOperation::DocumentOperation {
                 index_uid: _,
                 primary_key,
                 method,
-                documents_counts,
-                content_files,
+                documents_counts: _,
+                operations,
                 mut tasks,
             } => {
                 let mut primary_key_has_been_set = false;
                 let must_stop_processing = self.must_stop_processing.clone();
                 let indexer_config = self.index_mapper.indexer_config();
-                // TODO use the code from the IndexCreate operation
+
                 if let Some(primary_key) = primary_key {
-                    if index.primary_key(index_wtxn)?.is_none() {
-                        let mut builder =
-                            milli::update::Settings::new(index_wtxn, index, indexer_config);
-                        builder.set_primary_key(primary_key);
-                        builder.execute(
-                            |indexing_step| debug!("update: {:?}", indexing_step),
-                            || must_stop_processing.clone().get(),
-                        )?;
-                        primary_key_has_been_set = true;
+                    match index.primary_key(index_wtxn)? {
+                        // if a primary key was set AND had already been defined in the index
+                        // but to a different value, we can make the whole batch fail.
+                        Some(pk) => {
+                            if primary_key != pk {
+                                return Err(milli::Error::from(
+                                    milli::UserError::PrimaryKeyCannotBeChanged(pk.to_string()),
+                                )
+                                .into());
+                            }
+                        }
+                        // if the primary key was set and there was no primary key set for this index
+                        // we set it to the received value before starting the indexing process.
+                        None => {
+                            let mut builder =
+                                milli::update::Settings::new(index_wtxn, index, indexer_config);
+                            builder.set_primary_key(primary_key);
+                            builder.execute(
+                                |indexing_step| debug!("update: {:?}", indexing_step),
+                                || must_stop_processing.clone().get(),
+                            )?;
+                            primary_key_has_been_set = true;
+                        }
                     }
                 }
 
@@ -1010,26 +1113,82 @@ impl IndexScheduler {
                     || must_stop_processing.get(),
                 )?;
 
-                let mut results = Vec::new();
-                for content_uuid in content_files.into_iter() {
-                    let content_file = self.file_store.get_update(content_uuid)?;
-                    let reader = DocumentsBatchReader::from_reader(content_file)
-                        .map_err(milli::Error::from)?;
-                    let (new_builder, user_result) = builder.add_documents(reader)?;
-                    builder = new_builder;
+                for (operation, task) in operations.into_iter().zip(tasks.iter_mut()) {
+                    match operation {
+                        DocumentOperation::Add(content_uuid) => {
+                            let content_file = self.file_store.get_update(content_uuid)?;
+                            let reader = DocumentsBatchReader::from_reader(content_file)
+                                .map_err(milli::Error::from)?;
+                            let (new_builder, user_result) = builder.add_documents(reader)?;
+                            builder = new_builder;
 
-                    let user_result = match user_result {
-                        Ok(count) => Ok(DocumentAdditionResult {
-                            indexed_documents: count,
-                            number_of_documents: count, // TODO: this is wrong, we should use the value stored in the Details.
-                        }),
-                        Err(e) => Err(milli::Error::from(e)),
-                    };
+                            let received_documents =
+                                if let Some(Details::DocumentAdditionOrUpdate {
+                                    received_documents,
+                                    ..
+                                }) = task.details
+                                {
+                                    received_documents
+                                } else {
+                                    // In the case of a `documentAdditionOrUpdate` the details MUST be set
+                                    unreachable!();
+                                };
 
-                    results.push(user_result);
+                            match user_result {
+                                Ok(count) => {
+                                    task.status = Status::Succeeded;
+                                    task.details = Some(Details::DocumentAdditionOrUpdate {
+                                        received_documents,
+                                        indexed_documents: Some(count),
+                                    })
+                                }
+                                Err(e) => {
+                                    task.status = Status::Failed;
+                                    task.details = Some(Details::DocumentAdditionOrUpdate {
+                                        received_documents,
+                                        indexed_documents: Some(0),
+                                    });
+                                    task.error = Some(milli::Error::from(e).into());
+                                }
+                            }
+                        }
+                        DocumentOperation::Delete(document_ids) => {
+                            let (new_builder, user_result) =
+                                builder.remove_documents(document_ids)?;
+                            builder = new_builder;
+
+                            let provided_ids =
+                                if let Some(Details::DocumentDeletion { provided_ids, .. }) =
+                                    task.details
+                                {
+                                    provided_ids
+                                } else {
+                                    // In the case of a `documentAdditionOrUpdate` the details MUST be set
+                                    unreachable!();
+                                };
+
+                            match user_result {
+                                Ok(count) => {
+                                    task.status = Status::Succeeded;
+                                    task.details = Some(Details::DocumentDeletion {
+                                        provided_ids,
+                                        deleted_documents: Some(count),
+                                    });
+                                }
+                                Err(e) => {
+                                    task.status = Status::Failed;
+                                    task.details = Some(Details::DocumentDeletion {
+                                        provided_ids,
+                                        deleted_documents: Some(0),
+                                    });
+                                    task.error = Some(milli::Error::from(e).into());
+                                }
+                            }
+                        }
+                    }
                 }
 
-                if results.iter().any(|res| res.is_ok()) {
+                if !tasks.iter().all(|res| res.error.is_some()) {
                     let addition = builder.execute()?;
                     info!("document addition done: {:?}", addition);
                 } else if primary_key_has_been_set {
@@ -1044,28 +1203,6 @@ impl IndexScheduler {
                     )?;
                 }
 
-                for (task, (ret, count)) in
-                    tasks.iter_mut().zip(results.into_iter().zip(documents_counts))
-                {
-                    match ret {
-                        Ok(DocumentAdditionResult { indexed_documents, number_of_documents }) => {
-                            task.status = Status::Succeeded;
-                            task.details = Some(Details::DocumentAdditionOrUpdate {
-                                received_documents: number_of_documents,
-                                indexed_documents: Some(indexed_documents),
-                            });
-                        }
-                        Err(error) => {
-                            task.status = Status::Failed;
-                            task.details = Some(Details::DocumentAdditionOrUpdate {
-                                received_documents: count,
-                                indexed_documents: Some(count),
-                            });
-                            task.error = Some(error.into())
-                        }
-                    }
-                }
-
                 Ok(tasks)
             }
             IndexOperation::DocumentDeletion { index_uid: _, documents, mut tasks } => {
@@ -1108,12 +1245,12 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
-            IndexOperation::SettingsAndDocumentImport {
+            IndexOperation::SettingsAndDocumentOperation {
                 index_uid,
                 primary_key,
                 method,
                 documents_counts,
-                content_files,
+                operations,
                 document_import_tasks,
                 settings,
                 settings_tasks,
@@ -1131,12 +1268,12 @@ impl IndexScheduler {
                 let mut import_tasks = self.apply_index_operation(
                     index_wtxn,
                     index,
-                    IndexOperation::DocumentImport {
+                    IndexOperation::DocumentOperation {
                         index_uid,
                         primary_key,
                         method,
                         documents_counts,
-                        content_files,
+                        operations,
                         tasks: document_import_tasks,
                     },
                 )?;

index-scheduler/src/error.rs

@@ -100,9 +100,9 @@ pub enum Error {
     InvalidIndexUid { index_uid: String },
     #[error("Task `{0}` not found.")]
     TaskNotFound(TaskId),
-    #[error("Query parameters to filter the tasks to delete are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
+    #[error("Query parameters to filter the tasks to delete are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
     TaskDeletionWithEmptyQuery,
-    #[error("Query parameters to filter the tasks to cancel are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
+    #[error("Query parameters to filter the tasks to cancel are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
     TaskCancelationWithEmptyQuery,
 
     #[error(transparent)]
@@ -141,8 +141,8 @@ impl ErrorCode for Error {
             Error::IndexAlreadyExists(_) => Code::IndexAlreadyExists,
             Error::SwapDuplicateIndexesFound(_) => Code::InvalidSwapDuplicateIndexFound,
             Error::SwapDuplicateIndexFound(_) => Code::InvalidSwapDuplicateIndexFound,
-            Error::SwapIndexNotFound(_) => Code::InvalidSwapIndexes,
-            Error::SwapIndexesNotFound(_) => Code::InvalidSwapIndexes,
+            Error::SwapIndexNotFound(_) => Code::IndexNotFound,
+            Error::SwapIndexesNotFound(_) => Code::IndexNotFound,
             Error::InvalidTaskDate { field, .. } => (*field).into(),
             Error::InvalidTaskUids { .. } => Code::InvalidTaskUids,
             Error::InvalidTaskStatuses { .. } => Code::InvalidTaskStatuses,

index-scheduler/src/index_mapper.rs

@@ -1,250 +0,0 @@
-use std::collections::hash_map::Entry;
-use std::collections::HashMap;
-use std::path::{Path, PathBuf};
-use std::sync::{Arc, RwLock};
-use std::{fs, thread};
-
-use log::error;
-use meilisearch_types::heed::types::Str;
-use meilisearch_types::heed::{Database, Env, EnvOpenOptions, RoTxn, RwTxn};
-use meilisearch_types::milli::update::IndexerConfig;
-use meilisearch_types::milli::Index;
-use time::OffsetDateTime;
-use uuid::Uuid;
-
-use self::IndexStatus::{Available, BeingDeleted};
-use crate::uuid_codec::UuidCodec;
-use crate::{clamp_to_page_size, Error, Result};
-
-const INDEX_MAPPING: &str = "index-mapping";
-
-/// Structure managing meilisearch's indexes.
-///
-/// It is responsible for:
-/// 1. Creating new indexes
-/// 2. Opening indexes and storing references to these opened indexes
-/// 3. Accessing indexes through their uuid
-/// 4. Mapping a user-defined name to each index uuid.
-#[derive(Clone)]
-pub struct IndexMapper {
-    /// Keep track of the opened indexes. Used mainly by the index resolver.
-    index_map: Arc<RwLock<HashMap<Uuid, IndexStatus>>>,
-
-    /// Map an index name with an index uuid currently available on disk.
-    pub(crate) index_mapping: Database<Str, UuidCodec>,
-
-    /// Path to the folder where the LMDB environments of each index are.
-    base_path: PathBuf,
-    index_size: usize,
-    pub indexer_config: Arc<IndexerConfig>,
-}
-
-/// Whether the index is available for use or is forbidden to be inserted back in the index map
-#[allow(clippy::large_enum_variant)]
-#[derive(Clone)]
-pub enum IndexStatus {
-    /// Do not insert it back in the index map as it is currently being deleted.
-    BeingDeleted,
-    /// You can use the index without worrying about anything.
-    Available(Index),
-}
-
-impl IndexMapper {
-    pub fn new(
-        env: &Env,
-        base_path: PathBuf,
-        index_size: usize,
-        indexer_config: IndexerConfig,
-    ) -> Result<Self> {
-        Ok(Self {
-            index_map: Arc::default(),
-            index_mapping: env.create_database(Some(INDEX_MAPPING))?,
-            base_path,
-            index_size,
-            indexer_config: Arc::new(indexer_config),
-        })
-    }
-
-    /// Create or open an index in the specified path.
-    /// The path *must* exists or an error will be thrown.
-    fn create_or_open_index(
-        &self,
-        path: &Path,
-        date: Option<(OffsetDateTime, OffsetDateTime)>,
-    ) -> Result<Index> {
-        let mut options = EnvOpenOptions::new();
-        options.map_size(clamp_to_page_size(self.index_size));
-        options.max_readers(1024);
-
-        if let Some((created, updated)) = date {
-            Ok(Index::new_with_creation_dates(options, path, created, updated)?)
-        } else {
-            Ok(Index::new(options, path)?)
-        }
-    }
-
-    /// Get or create the index.
-    pub fn create_index(
-        &self,
-        mut wtxn: RwTxn,
-        name: &str,
-        date: Option<(OffsetDateTime, OffsetDateTime)>,
-    ) -> Result<Index> {
-        match self.index(&wtxn, name) {
-            Ok(index) => {
-                wtxn.commit()?;
-                Ok(index)
-            }
-            Err(Error::IndexNotFound(_)) => {
-                let uuid = Uuid::new_v4();
-                self.index_mapping.put(&mut wtxn, name, &uuid)?;
-
-                let index_path = self.base_path.join(uuid.to_string());
-                fs::create_dir_all(&index_path)?;
-
-                let index = self.create_or_open_index(&index_path, date)?;
-
-                wtxn.commit()?;
-                // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
-                if let Some(BeingDeleted) =
-                    self.index_map.write().unwrap().insert(uuid, Available(index.clone()))
-                {
-                    panic!("Uuid v4 conflict.");
-                }
-
-                Ok(index)
-            }
-            error => error,
-        }
-    }
-
-    /// Removes the index from the mapping table and the in-memory index map
-    /// but keeps the associated tasks.
-    pub fn delete_index(&self, mut wtxn: RwTxn, name: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(&wtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // Once we retrieved the UUID of the index we remove it from the mapping table.
-        assert!(self.index_mapping.delete(&mut wtxn, name)?);
-
-        wtxn.commit()?;
-        // We remove the index from the in-memory index map.
-        let mut lock = self.index_map.write().unwrap();
-        let closing_event = match lock.insert(uuid, BeingDeleted) {
-            Some(Available(index)) => Some(index.prepare_for_closing()),
-            _ => None,
-        };
-
-        drop(lock);
-
-        let index_map = self.index_map.clone();
-        let index_path = self.base_path.join(uuid.to_string());
-        let index_name = name.to_string();
-        thread::Builder::new()
-            .name(String::from("index_deleter"))
-            .spawn(move || {
-                // We first wait to be sure that the previously opened index is effectively closed.
-                // This can take a lot of time, this is why we do that in a seperate thread.
-                if let Some(closing_event) = closing_event {
-                    closing_event.wait();
-                }
-
-                // Then we remove the content from disk.
-                if let Err(e) = fs::remove_dir_all(&index_path) {
-                    error!(
-                        "An error happened when deleting the index {} ({}): {}",
-                        index_name, uuid, e
-                    );
-                }
-
-                // Finally we remove the entry from the index map.
-                assert!(matches!(index_map.write().unwrap().remove(&uuid), Some(BeingDeleted)));
-            })
-            .unwrap();
-
-        Ok(())
-    }
-
-    pub fn exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
-        Ok(self.index_mapping.get(rtxn, name)?.is_some())
-    }
-
-    /// Return an index, may open it if it wasn't already opened.
-    pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // we clone here to drop the lock before entering the match
-        let index = self.index_map.read().unwrap().get(&uuid).cloned();
-        let index = match index {
-            Some(Available(index)) => index,
-            Some(BeingDeleted) => return Err(Error::IndexNotFound(name.to_string())),
-            // since we're lazy, it's possible that the index has not been opened yet.
-            None => {
-                let mut index_map = self.index_map.write().unwrap();
-                // between the read lock and the write lock it's not impossible
-                // that someone already opened the index (eg if two search happens
-                // at the same time), thus before opening it we check a second time
-                // if it's not already there.
-                // Since there is a good chance it's not already there we can use
-                // the entry method.
-                match index_map.entry(uuid) {
-                    Entry::Vacant(entry) => {
-                        let index_path = self.base_path.join(uuid.to_string());
-
-                        let index = self.create_or_open_index(&index_path, None)?;
-                        entry.insert(Available(index.clone()));
-                        index
-                    }
-                    Entry::Occupied(entry) => match entry.get() {
-                        Available(index) => index.clone(),
-                        BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
-                    },
-                }
-            }
-        };
-
-        Ok(index)
-    }
-
-    /// Return all indexes, may open them if they weren't already opened.
-    pub fn indexes(&self, rtxn: &RoTxn) -> Result<Vec<(String, Index)>> {
-        self.index_mapping
-            .iter(rtxn)?
-            .map(|ret| {
-                ret.map_err(Error::from).and_then(|(name, _)| {
-                    self.index(rtxn, name).map(|index| (name.to_string(), index))
-                })
-            })
-            .collect()
-    }
-
-    /// Swap two index names.
-    pub fn swap(&self, wtxn: &mut RwTxn, lhs: &str, rhs: &str) -> Result<()> {
-        let lhs_uuid = self
-            .index_mapping
-            .get(wtxn, lhs)?
-            .ok_or_else(|| Error::IndexNotFound(lhs.to_string()))?;
-        let rhs_uuid = self
-            .index_mapping
-            .get(wtxn, rhs)?
-            .ok_or_else(|| Error::IndexNotFound(rhs.to_string()))?;
-
-        self.index_mapping.put(wtxn, lhs, &rhs_uuid)?;
-        self.index_mapping.put(wtxn, rhs, &lhs_uuid)?;
-
-        Ok(())
-    }
-
-    pub fn index_exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
-        Ok(self.index_mapping.get(rtxn, name)?.is_some())
-    }
-
-    pub fn indexer_config(&self) -> &IndexerConfig {
-        &self.indexer_config
-    }
-}

index-scheduler/src/index_mapper/index_map.rs

@@ -0,0 +1,370 @@
+/// the map size to use when we don't succeed in reading it in indexes.
+const DEFAULT_MAP_SIZE: usize = 10 * 1024 * 1024 * 1024; // 10 GiB
+
+use std::collections::BTreeMap;
+use std::path::Path;
+use std::time::Duration;
+
+use meilisearch_types::heed::{EnvClosingEvent, EnvOpenOptions};
+use meilisearch_types::milli::Index;
+use time::OffsetDateTime;
+use uuid::Uuid;
+
+use super::IndexStatus::{self, Available, BeingDeleted, Closing, Missing};
+use crate::lru::{InsertionOutcome, LruMap};
+use crate::{clamp_to_page_size, Result};
+
+/// Keep an internally consistent view of the open indexes in memory.
+///
+/// This view is made of an LRU cache that will evict the least frequently used indexes when new indexes are opened.
+/// Indexes that are being closed (for resizing or due to cache eviction) or deleted cannot be evicted from the cache and
+/// are stored separately.
+///
+/// This view provides operations to change the state of the index as it is known in memory:
+/// open an index (making it available for queries), close an index (specifying the new size it should be opened with),
+/// delete an index.
+///
+/// External consistency with the other bits of data of an index is provided by the `IndexMapper` parent structure.
+pub struct IndexMap {
+    /// A LRU map of indexes that are in the open state and available for queries.
+    available: LruMap<Uuid, Index>,
+    /// A map of indexes that are not available for queries, either because they are being deleted
+    /// or because they are being closed.
+    ///
+    /// If they are being deleted, the UUID points to `None`.
+    unavailable: BTreeMap<Uuid, Option<ClosingIndex>>,
+
+    /// A monotonically increasing generation number, used to differentiate between multiple successive index closing requests.
+    ///
+    /// Because multiple readers could be waiting on an index to close, the following could theoretically happen:
+    ///
+    /// 1. Multiple readers wait for the index closing to occur.
+    /// 2. One of them "wins the race", takes the lock and then removes the index that finished closing from the map.
+    /// 3. The index is reopened, but must be closed again (such as being resized again).
+    /// 4. One reader that "lost the race" in (2) wakes up and tries to take the lock and remove the index from the map.
+    ///
+    /// In that situation, the index may or may not have finished closing. The `generation` field allows to remember which
+    /// closing request was made, so the reader that "lost the race" has the old generation and will need to wait again for the index
+    /// to close.
+    generation: usize,
+}
+
+#[derive(Clone)]
+pub struct ClosingIndex {
+    uuid: Uuid,
+    closing_event: EnvClosingEvent,
+    map_size: usize,
+    generation: usize,
+}
+
+impl ClosingIndex {
+    /// Waits for the index to be definitely closed.
+    ///
+    /// To avoid blocking, users should relinquish their locks to the IndexMap before calling this function.
+    ///
+    /// After the index is physically closed, the in memory map must still be updated to take this into account.
+    /// To do so, a `ReopenableIndex` is returned, that can be used to either definitely close or definitely open
+    /// the index without waiting anymore.
+    pub fn wait_timeout(self, timeout: Duration) -> Option<ReopenableIndex> {
+        self.closing_event.wait_timeout(timeout).then_some(ReopenableIndex {
+            uuid: self.uuid,
+            map_size: self.map_size,
+            generation: self.generation,
+        })
+    }
+}
+
+pub struct ReopenableIndex {
+    uuid: Uuid,
+    map_size: usize,
+    generation: usize,
+}
+
+impl ReopenableIndex {
+    /// Attempts to reopen the index, which can result in the index being reopened again or not
+    /// (e.g. if another thread already opened and closed the index again).
+    ///
+    /// Use get again on the IndexMap to get the updated status.
+    ///
+    /// Fails if the underlying index creation fails.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status                                   |
+    /// |-----------------|----------------------------------------------|
+    /// | Missing         | Missing                                      |
+    /// | BeingDeleted    | BeingDeleted                                 |
+    /// | Closing         | Available or Closing depending on generation |
+    /// | Available       | Available                                    |
+    ///
+    pub fn reopen(self, map: &mut IndexMap, path: &Path) -> Result<()> {
+        if let Closing(reopen) = map.get(&self.uuid) {
+            if reopen.generation != self.generation {
+                return Ok(());
+            }
+            map.unavailable.remove(&self.uuid);
+            map.create(&self.uuid, path, None, self.map_size)?;
+        }
+        Ok(())
+    }
+
+    /// Attempts to close the index, which may or may not result in the index being closed
+    /// (e.g. if another thread already reopened the index again).
+    ///
+    /// Use get again on the IndexMap to get the updated status.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status                                 |
+    /// |-----------------|--------------------------------------------|
+    /// | Missing         | Missing                                    |
+    /// | BeingDeleted    | BeingDeleted                               |
+    /// | Closing         | Missing or Closing depending on generation |
+    /// | Available       | Available                                  |
+    pub fn close(self, map: &mut IndexMap) {
+        if let Closing(reopen) = map.get(&self.uuid) {
+            if reopen.generation != self.generation {
+                return;
+            }
+            map.unavailable.remove(&self.uuid);
+        }
+    }
+}
+
+impl IndexMap {
+    pub fn new(cap: usize) -> IndexMap {
+        Self { unavailable: Default::default(), available: LruMap::new(cap), generation: 0 }
+    }
+
+    /// Gets the current status of an index in the map.
+    ///
+    /// If the index is available it can be accessed from the returned status.
+    pub fn get(&self, uuid: &Uuid) -> IndexStatus {
+        self.available
+            .get(uuid)
+            .map(|index| Available(index.clone()))
+            .unwrap_or_else(|| self.get_unavailable(uuid))
+    }
+
+    fn get_unavailable(&self, uuid: &Uuid) -> IndexStatus {
+        match self.unavailable.get(uuid) {
+            Some(Some(reopen)) => Closing(reopen.clone()),
+            Some(None) => BeingDeleted,
+            None => Missing,
+        }
+    }
+
+    /// Attempts to create a new index that wasn't existing before.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status |
+    /// |-----------------|------------|
+    /// | Missing         | Available  |
+    /// | BeingDeleted    | panics     |
+    /// | Closing         | panics     |
+    /// | Available       | panics     |
+    ///
+    pub fn create(
+        &mut self,
+        uuid: &Uuid,
+        path: &Path,
+        date: Option<(OffsetDateTime, OffsetDateTime)>,
+        map_size: usize,
+    ) -> Result<Index> {
+        if !matches!(self.get_unavailable(uuid), Missing) {
+            panic!("Attempt to open an index that was unavailable");
+        }
+        let index = create_or_open_index(path, date, map_size)?;
+        match self.available.insert(*uuid, index.clone()) {
+            InsertionOutcome::InsertedNew => (),
+            InsertionOutcome::Evicted(evicted_uuid, evicted_index) => {
+                self.close(evicted_uuid, evicted_index, 0);
+            }
+            InsertionOutcome::Replaced(_) => {
+                panic!("Attempt to open an index that was already opened")
+            }
+        }
+        Ok(index)
+    }
+
+    /// Increases the current generation. See documentation for this field.
+    ///
+    /// In the unlikely event that the 2^64 generations would have been exhausted, we simply wrap-around.
+    ///
+    /// For this to cause an issue, one should be able to stop a reader in time after it got a `ReopenableIndex` and before it takes the lock
+    /// to remove it from the unavailable map, and keep the reader in this frozen state for 2^64 closing of other indexes.
+    ///
+    /// This seems overwhelmingly impossible to achieve in practice.
+    fn next_generation(&mut self) -> usize {
+        self.generation = self.generation.wrapping_add(1);
+        self.generation
+    }
+
+    /// Attempts to close an index.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status    |
+    /// |-----------------|---------------|
+    /// | Missing         | Missing       |
+    /// | BeingDeleted    | BeingDeleted  |
+    /// | Closing         | Closing       |
+    /// | Available       | Closing       |
+    ///
+    pub fn close_for_resize(&mut self, uuid: &Uuid, map_size_growth: usize) {
+        let Some(index) = self.available.remove(uuid) else { return; };
+        self.close(*uuid, index, map_size_growth);
+    }
+
+    fn close(&mut self, uuid: Uuid, index: Index, map_size_growth: usize) {
+        let map_size = index.map_size().unwrap_or(DEFAULT_MAP_SIZE) + map_size_growth;
+        let closing_event = index.prepare_for_closing();
+        let generation = self.next_generation();
+        self.unavailable
+            .insert(uuid, Some(ClosingIndex { uuid, closing_event, map_size, generation }));
+    }
+
+    /// Attempts to delete and index.
+    ///
+    ///  `end_deletion` must be called just after.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status   | Return value                |
+    /// |-----------------|--------------|-----------------------------|
+    /// | Missing         | BeingDeleted | Ok(None)                    |
+    /// | BeingDeleted    | BeingDeleted | Err(None)                   |
+    /// | Closing         | Closing      | Err(Some(reopen))           |
+    /// | Available       | BeingDeleted | Ok(Some(env_closing_event)) |
+    pub fn start_deletion(
+        &mut self,
+        uuid: &Uuid,
+    ) -> std::result::Result<Option<EnvClosingEvent>, Option<ClosingIndex>> {
+        if let Some(index) = self.available.remove(uuid) {
+            self.unavailable.insert(*uuid, None);
+            return Ok(Some(index.prepare_for_closing()));
+        }
+        match self.unavailable.remove(uuid) {
+            Some(Some(reopen)) => Err(Some(reopen)),
+            Some(None) => Err(None),
+            None => Ok(None),
+        }
+    }
+
+    /// Marks that an index deletion finished.
+    ///
+    /// Must be used after calling `start_deletion`.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status |
+    /// |-----------------|------------|
+    /// | Missing         | Missing    |
+    /// | BeingDeleted    | Missing    |
+    /// | Closing         | panics     |
+    /// | Available       | panics     |
+    pub fn end_deletion(&mut self, uuid: &Uuid) {
+        assert!(
+            self.available.get(uuid).is_none(),
+            "Attempt to finish deletion of an index that was not being deleted"
+        );
+        // Do not panic if the index was Missing or BeingDeleted
+        assert!(
+            !matches!(self.unavailable.remove(uuid), Some(Some(_))),
+            "Attempt to finish deletion of an index that was being closed"
+        );
+    }
+}
+
+/// Create or open an index in the specified path.
+/// The path *must* exist or an error will be thrown.
+fn create_or_open_index(
+    path: &Path,
+    date: Option<(OffsetDateTime, OffsetDateTime)>,
+    map_size: usize,
+) -> Result<Index> {
+    let mut options = EnvOpenOptions::new();
+    options.map_size(clamp_to_page_size(map_size));
+    options.max_readers(1024);
+
+    if let Some((created, updated)) = date {
+        Ok(Index::new_with_creation_dates(options, path, created, updated)?)
+    } else {
+        Ok(Index::new(options, path)?)
+    }
+}
+
+/// Putting the tests of the LRU down there so we have access to the cache's private members
+#[cfg(test)]
+mod tests {
+
+    use meilisearch_types::heed::Env;
+    use meilisearch_types::Index;
+    use uuid::Uuid;
+
+    use super::super::IndexMapper;
+    use crate::tests::IndexSchedulerHandle;
+    use crate::utils::clamp_to_page_size;
+    use crate::IndexScheduler;
+
+    impl IndexMapper {
+        fn test() -> (Self, Env, IndexSchedulerHandle) {
+            let (index_scheduler, handle) = IndexScheduler::test(true, vec![]);
+            (index_scheduler.index_mapper, index_scheduler.env, handle)
+        }
+    }
+
+    fn check_first_unavailable(mapper: &IndexMapper, expected_uuid: Uuid, is_closing: bool) {
+        let index_map = mapper.index_map.read().unwrap();
+        let (uuid, state) = index_map.unavailable.first_key_value().unwrap();
+        assert_eq!(uuid, &expected_uuid);
+        assert_eq!(state.is_some(), is_closing);
+    }
+
+    #[test]
+    fn evict_indexes() {
+        let (mapper, env, _handle) = IndexMapper::test();
+        let mut uuids = vec![];
+        // LRU cap + 1
+        for i in 0..(5 + 1) {
+            let index_name = format!("index-{i}");
+            let wtxn = env.write_txn().unwrap();
+            mapper.create_index(wtxn, &index_name, None).unwrap();
+            let txn = env.read_txn().unwrap();
+            uuids.push(mapper.index_mapping.get(&txn, &index_name).unwrap().unwrap());
+        }
+        // index-0 was evicted
+        check_first_unavailable(&mapper, uuids[0], true);
+
+        // get back the evicted index
+        let wtxn = env.write_txn().unwrap();
+        mapper.create_index(wtxn, "index-0", None).unwrap();
+
+        // Least recently used is now index-1
+        check_first_unavailable(&mapper, uuids[1], true);
+    }
+
+    #[test]
+    fn resize_index() {
+        let (mapper, env, _handle) = IndexMapper::test();
+        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
+        assert_index_size(index, mapper.index_base_map_size);
+
+        mapper.resize_index(&env.read_txn().unwrap(), "index").unwrap();
+
+        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
+        assert_index_size(index, mapper.index_base_map_size + mapper.index_growth_amount);
+
+        mapper.resize_index(&env.read_txn().unwrap(), "index").unwrap();
+
+        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
+        assert_index_size(index, mapper.index_base_map_size + mapper.index_growth_amount * 2);
+    }
+
+    fn assert_index_size(index: Index, expected: usize) {
+        let expected = clamp_to_page_size(expected);
+        let index_map_size = index.map_size().unwrap();
+        assert_eq!(index_map_size, expected);
+    }
+}

index-scheduler/src/index_mapper/mod.rs

@@ -0,0 +1,453 @@
+use std::path::PathBuf;
+use std::sync::{Arc, RwLock};
+use std::time::Duration;
+use std::{fs, thread};
+
+use log::error;
+use meilisearch_types::heed::types::{SerdeJson, Str};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::milli::update::IndexerConfig;
+use meilisearch_types::milli::{FieldDistribution, Index};
+use serde::{Deserialize, Serialize};
+use time::OffsetDateTime;
+use uuid::Uuid;
+
+use self::index_map::IndexMap;
+use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
+use crate::uuid_codec::UuidCodec;
+use crate::{Error, Result};
+
+mod index_map;
+
+const INDEX_MAPPING: &str = "index-mapping";
+const INDEX_STATS: &str = "index-stats";
+
+/// Structure managing meilisearch's indexes.
+///
+/// It is responsible for:
+/// 1. Creating new indexes
+/// 2. Opening indexes and storing references to these opened indexes
+/// 3. Accessing indexes through their uuid
+/// 4. Mapping a user-defined name to each index uuid.
+///
+/// # Implementation notes
+///
+/// An index exists as 3 bits of data:
+/// 1. The index data on disk, that can exist in 3 states: Missing, Present, or BeingDeleted.
+/// 2. The persistent database containing the association between the index' name and its UUID,
+///    that can exist in 2 states: Missing or Present.
+/// 3. The state of the index in the in-memory `IndexMap`, that can exist in multiple states:
+///   - Missing
+///   - Available
+///   - Closing (because an index needs resizing or was evicted from the cache)
+///   - BeingDeleted
+///
+/// All of this data should be kept consistent between index operations, which is achieved by the `IndexMapper`
+/// with the use of the following primitives:
+/// - A RwLock on the `IndexMap`.
+/// - Transactions on the association database.
+/// - ClosingEvent signals emitted when closing an environment.
+#[derive(Clone)]
+pub struct IndexMapper {
+    /// Keep track of the opened indexes. Used mainly by the index resolver.
+    index_map: Arc<RwLock<IndexMap>>,
+
+    /// Map an index name with an index uuid currently available on disk.
+    pub(crate) index_mapping: Database<Str, UuidCodec>,
+    /// Map an index UUID with the cached stats associated to the index.
+    ///
+    /// Using an UUID forces to use the index_mapping table to recover the index behind a name, ensuring
+    /// consistency wrt index swapping.
+    pub(crate) index_stats: Database<UuidCodec, SerdeJson<IndexStats>>,
+
+    /// Path to the folder where the LMDB environments of each index are.
+    base_path: PathBuf,
+    /// The map size an index is opened with on the first time.
+    index_base_map_size: usize,
+    /// The quantity by which the map size of an index is incremented upon reopening, in bytes.
+    index_growth_amount: usize,
+    pub indexer_config: Arc<IndexerConfig>,
+}
+
+/// Whether the index is available for use or is forbidden to be inserted back in the index map
+#[allow(clippy::large_enum_variant)]
+#[derive(Clone)]
+pub enum IndexStatus {
+    /// Not currently in the index map.
+    Missing,
+    /// Do not insert it back in the index map as it is currently being deleted.
+    BeingDeleted,
+    /// Temporarily do not insert the index in the index map as it is currently being resized/evicted from the map.
+    Closing(index_map::ClosingIndex),
+    /// You can use the index without worrying about anything.
+    Available(Index),
+}
+
+/// The statistics that can be computed from an `Index` object.
+#[derive(Serialize, Deserialize, Debug)]
+pub struct IndexStats {
+    /// Number of documents in the index.
+    pub number_of_documents: u64,
+    /// Size of the index' DB, in bytes.
+    pub database_size: u64,
+    /// Association of every field name with the number of times it occurs in the documents.
+    pub field_distribution: FieldDistribution,
+    /// Creation date of the index.
+    pub created_at: OffsetDateTime,
+    /// Date of the last update of the index.
+    pub updated_at: OffsetDateTime,
+}
+
+impl IndexStats {
+    /// Compute the stats of an index
+    ///
+    /// # Parameters
+    ///
+    /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
+    pub fn new(index: &Index, rtxn: &RoTxn) -> Result<Self> {
+        let database_size = index.on_disk_size()?;
+        Ok(IndexStats {
+            number_of_documents: index.number_of_documents(rtxn)?,
+            database_size,
+            field_distribution: index.field_distribution(rtxn)?,
+            created_at: index.created_at(rtxn)?,
+            updated_at: index.updated_at(rtxn)?,
+        })
+    }
+}
+
+impl IndexMapper {
+    pub fn new(
+        env: &Env,
+        base_path: PathBuf,
+        index_base_map_size: usize,
+        index_growth_amount: usize,
+        index_count: usize,
+        indexer_config: IndexerConfig,
+    ) -> Result<Self> {
+        Ok(Self {
+            index_map: Arc::new(RwLock::new(IndexMap::new(index_count))),
+            index_mapping: env.create_database(Some(INDEX_MAPPING))?,
+            index_stats: env.create_database(Some(INDEX_STATS))?,
+            base_path,
+            index_base_map_size,
+            index_growth_amount,
+            indexer_config: Arc::new(indexer_config),
+        })
+    }
+
+    /// Get or create the index.
+    pub fn create_index(
+        &self,
+        mut wtxn: RwTxn,
+        name: &str,
+        date: Option<(OffsetDateTime, OffsetDateTime)>,
+    ) -> Result<Index> {
+        match self.index(&wtxn, name) {
+            Ok(index) => {
+                wtxn.commit()?;
+                Ok(index)
+            }
+            Err(Error::IndexNotFound(_)) => {
+                let uuid = Uuid::new_v4();
+                self.index_mapping.put(&mut wtxn, name, &uuid)?;
+
+                let index_path = self.base_path.join(uuid.to_string());
+                fs::create_dir_all(&index_path)?;
+
+                // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
+                // This is very unlikely to happen in practice.
+                // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
+                let index = self.index_map.write().unwrap().create(
+                    &uuid,
+                    &index_path,
+                    date,
+                    self.index_base_map_size,
+                )?;
+
+                wtxn.commit()?;
+
+                Ok(index)
+            }
+            error => error,
+        }
+    }
+
+    /// Removes the index from the mapping table and the in-memory index map
+    /// but keeps the associated tasks.
+    pub fn delete_index(&self, mut wtxn: RwTxn, name: &str) -> Result<()> {
+        let uuid = self
+            .index_mapping
+            .get(&wtxn, name)?
+            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+
+        // Not an error if the index had no stats in cache.
+        self.index_stats.delete(&mut wtxn, &uuid)?;
+
+        // Once we retrieved the UUID of the index we remove it from the mapping table.
+        assert!(self.index_mapping.delete(&mut wtxn, name)?);
+
+        wtxn.commit()?;
+
+        let mut tries = 0;
+        // Attempts to remove the index from the in-memory index map in a loop.
+        //
+        // If the index is currently being closed, we will wait for it to be closed and retry getting it in a subsequent
+        // loop iteration.
+        //
+        // We make 100 attempts before giving up.
+        // This could happen in the following situations:
+        //
+        // 1. There is a bug preventing the index from being correctly closed, or us from detecting this.
+        // 2. A user of the index is keeping it open for more than 600 seconds. This could happen e.g. during a pathological search.
+        //    This can not be caused by indexation because deleting an index happens in the scheduler itself, so cannot be concurrent with indexation.
+        //
+        // In these situations, reporting the error through a panic is in order.
+        let closing_event = loop {
+            let mut lock = self.index_map.write().unwrap();
+            match lock.start_deletion(&uuid) {
+                Ok(env_closing) => break env_closing,
+                Err(Some(reopen)) => {
+                    // drop the lock here so that we don't synchronously wait for the index to close.
+                    drop(lock);
+                    tries += 1;
+                    if tries >= 100 {
+                        panic!("Too many attempts to close index {name} prior to deletion.")
+                    }
+                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
+                        reopen
+                    } else {
+                        continue;
+                    };
+                    reopen.close(&mut self.index_map.write().unwrap());
+                    continue;
+                }
+                Err(None) => return Ok(()),
+            }
+        };
+
+        let index_map = self.index_map.clone();
+        let index_path = self.base_path.join(uuid.to_string());
+        let index_name = name.to_string();
+        thread::Builder::new()
+            .name(String::from("index_deleter"))
+            .spawn(move || {
+                // We first wait to be sure that the previously opened index is effectively closed.
+                // This can take a lot of time, this is why we do that in a separate thread.
+                if let Some(closing_event) = closing_event {
+                    closing_event.wait();
+                }
+
+                // Then we remove the content from disk.
+                if let Err(e) = fs::remove_dir_all(&index_path) {
+                    error!(
+                        "An error happened when deleting the index {} ({}): {}",
+                        index_name, uuid, e
+                    );
+                }
+
+                // Finally we remove the entry from the index map.
+                index_map.write().unwrap().end_deletion(&uuid);
+            })
+            .unwrap();
+
+        Ok(())
+    }
+
+    pub fn exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
+        Ok(self.index_mapping.get(rtxn, name)?.is_some())
+    }
+
+    /// Resizes the maximum size of the specified index to the double of its current maximum size.
+    ///
+    /// This operation involves closing the underlying environment and so can take a long time to complete.
+    ///
+    /// # Panics
+    ///
+    /// - If the Index corresponding to the passed name is concurrently being deleted/resized or cannot be found in the
+    ///   in memory hash map.
+    pub fn resize_index(&self, rtxn: &RoTxn, name: &str) -> Result<()> {
+        let uuid = self
+            .index_mapping
+            .get(rtxn, name)?
+            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+
+        // We remove the index from the in-memory index map.
+        self.index_map.write().unwrap().close_for_resize(&uuid, self.index_growth_amount);
+
+        Ok(())
+    }
+
+    /// Return an index, may open it if it wasn't already opened.
+    pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
+        let uuid = self
+            .index_mapping
+            .get(rtxn, name)?
+            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+
+        let mut tries = 0;
+        // attempts to open the index in a loop.
+        //
+        // If the index is currently being closed, we will wait for it to be closed and retry getting it in a subsequent
+        // loop iteration.
+        //
+        // We make 100 attempts before giving up.
+        // This could happen in the following situations:
+        //
+        // 1. There is a bug preventing the index from being correctly closed, or us from detecting it was.
+        // 2. A user of the index is keeping it open for more than 600 seconds. This could happen e.g. during a long indexation,
+        //    a pathological search, and so on.
+        //
+        // In these situations, reporting the error through a panic is in order.
+        let index = loop {
+            tries += 1;
+            if tries > 100 {
+                panic!("Too many spurious wake ups while trying to open the index {name}");
+            }
+
+            // we get the index here to drop the lock before entering the match
+            let index = self.index_map.read().unwrap().get(&uuid);
+
+            match index {
+                Available(index) => break index,
+                Closing(reopen) => {
+                    // Avoiding deadlocks: no lock taken while doing this operation.
+                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
+                        reopen
+                    } else {
+                        continue;
+                    };
+                    let index_path = self.base_path.join(uuid.to_string());
+                    // take the lock to reopen the environment.
+                    reopen.reopen(&mut self.index_map.write().unwrap(), &index_path)?;
+                    continue;
+                }
+                BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
+                // since we're lazy, it's possible that the index has not been opened yet.
+                Missing => {
+                    let mut index_map = self.index_map.write().unwrap();
+                    // between the read lock and the write lock it's not impossible
+                    // that someone already opened the index (eg if two searches happen
+                    // at the same time), thus before opening it we check a second time
+                    // if it's not already there.
+                    match index_map.get(&uuid) {
+                        Missing => {
+                            let index_path = self.base_path.join(uuid.to_string());
+
+                            break index_map.create(
+                                &uuid,
+                                &index_path,
+                                None,
+                                self.index_base_map_size,
+                            )?;
+                        }
+                        Available(index) => break index,
+                        Closing(_) => {
+                            // the reopening will be handled in the next loop operation
+                            continue;
+                        }
+                        BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
+                    }
+                }
+            }
+        };
+
+        Ok(index)
+    }
+
+    /// Attempts `f` for each index that exists in the index mapper.
+    ///
+    /// It is preferable to use this function rather than a loop that opens all indexes, as a way to avoid having all indexes opened,
+    /// which is unsupported in general.
+    ///
+    /// Since `f` is allowed to return a result, and `Index` is cloneable, it is still possible to wrongly build e.g. a vector of
+    /// all the indexes, but this function makes it harder and so less likely to do accidentally.
+    pub fn try_for_each_index<U, V>(
+        &self,
+        rtxn: &RoTxn,
+        mut f: impl FnMut(&str, &Index) -> Result<U>,
+    ) -> Result<V>
+    where
+        V: FromIterator<U>,
+    {
+        self.index_mapping
+            .iter(rtxn)?
+            .map(|res| {
+                res.map_err(Error::from)
+                    .and_then(|(name, _)| self.index(rtxn, name).and_then(|index| f(name, &index)))
+            })
+            .collect()
+    }
+
+    /// Return the name of all indexes without opening them.
+    pub fn index_names(&self, rtxn: &RoTxn) -> Result<Vec<String>> {
+        self.index_mapping
+            .iter(rtxn)?
+            .map(|res| res.map_err(Error::from).map(|(name, _)| name.to_string()))
+            .collect()
+    }
+
+    /// Swap two index names.
+    pub fn swap(&self, wtxn: &mut RwTxn, lhs: &str, rhs: &str) -> Result<()> {
+        let lhs_uuid = self
+            .index_mapping
+            .get(wtxn, lhs)?
+            .ok_or_else(|| Error::IndexNotFound(lhs.to_string()))?;
+        let rhs_uuid = self
+            .index_mapping
+            .get(wtxn, rhs)?
+            .ok_or_else(|| Error::IndexNotFound(rhs.to_string()))?;
+
+        self.index_mapping.put(wtxn, lhs, &rhs_uuid)?;
+        self.index_mapping.put(wtxn, rhs, &lhs_uuid)?;
+
+        Ok(())
+    }
+
+    /// The stats of an index.
+    ///
+    /// If available in the cache, they are directly returned.
+    /// Otherwise, the `Index` is opened to compute the stats on the fly (the result is not cached).
+    /// The stats for an index are cached after each `Index` update.
+    pub fn stats_of(&self, rtxn: &RoTxn, index_uid: &str) -> Result<IndexStats> {
+        let uuid = self
+            .index_mapping
+            .get(rtxn, index_uid)?
+            .ok_or_else(|| Error::IndexNotFound(index_uid.to_string()))?;
+
+        match self.index_stats.get(rtxn, &uuid)? {
+            Some(stats) => Ok(stats),
+            None => {
+                let index = self.index(rtxn, index_uid)?;
+                let index_rtxn = index.read_txn()?;
+                IndexStats::new(&index, &index_rtxn)
+            }
+        }
+    }
+
+    /// Stores the new stats for an index.
+    ///
+    /// Expected usage is to compute the stats the index using `IndexStats::new`, the pass it to this function.
+    pub fn store_stats_of(
+        &self,
+        wtxn: &mut RwTxn,
+        index_uid: &str,
+        stats: &IndexStats,
+    ) -> Result<()> {
+        let uuid = self
+            .index_mapping
+            .get(wtxn, index_uid)?
+            .ok_or_else(|| Error::IndexNotFound(index_uid.to_string()))?;
+
+        self.index_stats.put(wtxn, &uuid, stats)?;
+        Ok(())
+    }
+
+    pub fn index_exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
+        Ok(self.index_mapping.get(rtxn, name)?.is_some())
+    }
+
+    pub fn indexer_config(&self) -> &IndexerConfig {
+        &self.indexer_config
+    }
+}

index-scheduler/src/insta_snapshot.rs

@@ -1,3 +1,4 @@
+use std::collections::BTreeSet;
 use std::fmt::Write;
 
 use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
@@ -92,7 +93,9 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
 
 pub fn snapshot_file_store(file_store: &file_store::FileStore) -> String {
     let mut snap = String::new();
-    for uuid in file_store.__all_uuids() {
+    // we store the uuid in a `BTreeSet` to keep them ordered.
+    let all_uuids = file_store.all_uuids().unwrap().collect::<Result<BTreeSet<_>, _>>().unwrap();
+    for uuid in all_uuids {
         snap.push_str(&format!("{uuid}\n"));
     }
     snap
@@ -251,6 +254,16 @@ pub fn snapshot_canceled_by(
     snap
 }
 pub fn snapshot_index_mapper(rtxn: &RoTxn, mapper: &IndexMapper) -> String {
-    let names = mapper.indexes(rtxn).unwrap().into_iter().map(|(n, _)| n).collect::<Vec<_>>();
-    format!("{names:?}")
+    let mut s = String::new();
+    let names = mapper.index_names(rtxn).unwrap();
+
+    for name in names {
+        let stats = mapper.stats_of(rtxn, &name).unwrap();
+        s.push_str(&format!(
+            "{name}: {{ number_of_documents: {}, field_distribution: {:?} }}\n",
+            stats.number_of_documents, stats.field_distribution
+        ));
+    }
+
+    s
 }

index-scheduler/src/lru.rs

@@ -0,0 +1,203 @@
+//! Thread-safe `Vec`-backend LRU cache using [`std::sync::atomic::AtomicU64`] for synchronization.
+
+use std::sync::atomic::{AtomicU64, Ordering};
+
+/// Thread-safe `Vec`-backend LRU cache
+#[derive(Debug)]
+pub struct Lru<T> {
+    data: Vec<(AtomicU64, T)>,
+    generation: AtomicU64,
+    cap: usize,
+}
+
+impl<T> Lru<T> {
+    /// Creates a new LRU cache with the specified capacity.
+    ///
+    /// The capacity is allocated up-front, and will never change through a [`Self::put`] operation.
+    ///
+    /// # Panics
+    ///
+    /// - If the capacity is 0.
+    /// - If the capacity exceeds `isize::MAX` bytes.
+    pub fn new(cap: usize) -> Self {
+        assert_ne!(cap, 0, "The capacity of a cache cannot be 0");
+        Self {
+            // Note: since the element of the vector contains an AtomicU64, it is definitely not zero-sized so cap will never be usize::MAX.
+            data: Vec::with_capacity(cap),
+            generation: AtomicU64::new(0),
+            cap,
+        }
+    }
+
+    /// The capacity of this LRU cache, that is the maximum number of elements it can hold before evicting elements from the cache.
+    ///
+    /// The cache will contain at most this number of elements at any given time.
+    pub fn capacity(&self) -> usize {
+        self.cap
+    }
+
+    fn next_generation(&self) -> u64 {
+        // Acquire so this "happens-before" any potential store to a data cell (with Release ordering)
+        let generation = self.generation.fetch_add(1, Ordering::Acquire);
+        generation + 1
+    }
+
+    fn next_generation_mut(&mut self) -> u64 {
+        let generation = self.generation.get_mut();
+        *generation += 1;
+        *generation
+    }
+
+    /// Add a value in the cache, evicting an older value if necessary.
+    ///
+    /// If a value was evicted from the cache, it is returned.
+    ///
+    /// # Complexity
+    ///
+    /// - If the cache is full, then linear in the capacity.
+    /// - Otherwise constant.
+    pub fn put(&mut self, value: T) -> Option<T> {
+        // no need for a memory fence: we assume that whichever mechanism provides us synchronization
+        // (very probably, a RwLock) takes care of fencing for us.
+
+        let next_generation = self.next_generation_mut();
+        let evicted = if self.is_full() { self.pop() } else { None };
+        self.data.push((AtomicU64::new(next_generation), value));
+        evicted
+    }
+
+    /// Evict the oldest value from the cache.
+    ///
+    /// If the cache is empty, `None` will be returned.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn pop(&mut self) -> Option<T> {
+        // Don't use `Iterator::min_by_key` that provides shared references to its elements,
+        // so that we can get an exclusive one.
+        // This allows to handles the `AtomicU64`s as normal integers without using atomic instructions.
+        let mut min_generation_index = None;
+        for (index, (generation, _)) in self.data.iter_mut().enumerate() {
+            let generation = *generation.get_mut();
+            if let Some((_, min_generation)) = min_generation_index {
+                if min_generation > generation {
+                    min_generation_index = Some((index, generation));
+                }
+            } else {
+                min_generation_index = Some((index, generation))
+            }
+        }
+        min_generation_index.map(|(min_index, _)| self.data.swap_remove(min_index).1)
+    }
+
+    /// The current number of elements in the cache.
+    ///
+    /// This value is guaranteed to be less than or equal to [`Self::capacity`].
+    pub fn len(&self) -> usize {
+        self.data.len()
+    }
+
+    /// Returns `true` if putting any additional element in the cache would cause the eviction of an element.
+    pub fn is_full(&self) -> bool {
+        self.len() == self.capacity()
+    }
+}
+
+pub struct LruMap<K, V>(Lru<(K, V)>);
+
+impl<K, V> LruMap<K, V>
+where
+    K: Eq,
+{
+    /// Creates a new LRU cache map with the specified capacity.
+    ///
+    /// The capacity is allocated up-front, and will never change through a [`Self::insert`] operation.
+    ///
+    /// # Panics
+    ///
+    /// - If the capacity is 0.
+    /// - If the capacity exceeds `isize::MAX` bytes.
+    pub fn new(cap: usize) -> Self {
+        Self(Lru::new(cap))
+    }
+
+    /// Gets a value in the cache map by its key.
+    ///
+    /// If no value matches, `None` will be returned.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn get(&self, key: &K) -> Option<&V> {
+        for (generation, (candidate, value)) in self.0.data.iter() {
+            if key == candidate {
+                generation.store(self.0.next_generation(), Ordering::Release);
+                return Some(value);
+            }
+        }
+        None
+    }
+
+    /// Gets a value in the cache map by its key.
+    ///
+    /// If no value matches, `None` will be returned.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn get_mut(&mut self, key: &K) -> Option<&mut V> {
+        let next_generation = self.0.next_generation_mut();
+        for (generation, (candidate, value)) in self.0.data.iter_mut() {
+            if key == candidate {
+                *generation.get_mut() = next_generation;
+                return Some(value);
+            }
+        }
+        None
+    }
+
+    /// Inserts a value in the cache map by its key, replacing any existing value and returning any evicted value.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn insert(&mut self, key: K, mut value: V) -> InsertionOutcome<K, V> {
+        match self.get_mut(&key) {
+            Some(old_value) => {
+                std::mem::swap(old_value, &mut value);
+                InsertionOutcome::Replaced(value)
+            }
+            None => match self.0.put((key, value)) {
+                Some((key, value)) => InsertionOutcome::Evicted(key, value),
+                None => InsertionOutcome::InsertedNew,
+            },
+        }
+    }
+
+    /// Removes an element from the cache map by its key, returning its value.
+    ///
+    /// Returns `None` if there was no element with this key in the cache.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn remove(&mut self, key: &K) -> Option<V> {
+        for (index, (_, (candidate, _))) in self.0.data.iter_mut().enumerate() {
+            if key == candidate {
+                return Some(self.0.data.swap_remove(index).1 .1);
+            }
+        }
+        None
+    }
+}
+
+/// The result of an insertion in a LRU map.
+pub enum InsertionOutcome<K, V> {
+    /// The key was not in the cache, the key-value pair has been inserted.
+    InsertedNew,
+    /// The key was not in the cache and an old key-value pair was evicted from the cache to make room for its insertions.
+    Evicted(K, V),
+    /// The key was already in the cache map, its value has been updated.
+    Replaced(V),
+}

index-scheduler/src/snapshots/lib.rs/cancel_enqueued_task/cancel_processed.snap

@@ -1,6 +1,5 @@
 ---
 source: index-scheduler/src/lib.rs
-assertion_line: 1755
 ---
 ### Autobatching Enabled = true
 ### Processing Tasks:
@@ -23,7 +22,7 @@ canceled [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 1 [0,]

index-scheduler/src/snapshots/lib.rs/cancel_enqueued_task/initial_tasks_enqueued.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/aborted_indexation.snap

@@ -25,7 +25,9 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["beavero", "catto"]
+beavero: { number_of_documents: 0, field_distribution: {} }
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/cancel_processed.snap

@@ -1,6 +1,5 @@
 ---
 source: index-scheduler/src/lib.rs
-assertion_line: 1859
 ---
 ### Autobatching Enabled = true
 ### Processing Tasks:
@@ -27,7 +26,9 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["beavero", "catto"]
+beavero: { number_of_documents: 0, field_distribution: {} }
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 3 [1,2,]

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/first_task_processed.snap

@@ -23,7 +23,8 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/processing_second_task_cancel_enqueued.snap

@@ -25,7 +25,8 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/aborted_indexation.snap

@@ -20,7 +20,8 @@ enqueued [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/cancel_processed.snap

@@ -1,6 +1,5 @@
 ---
 source: index-scheduler/src/lib.rs
-assertion_line: 1818
 ---
 ### Autobatching Enabled = true
 ### Processing Tasks:
@@ -23,7 +22,8 @@ canceled [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 1 [0,]

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/cancel_task_registered.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/initial_task_processing.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_succeeded_task/cancel_processed.snap

@@ -21,7 +21,8 @@ succeeded [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 1 []

index-scheduler/src/snapshots/lib.rs/cancel_succeeded_task/initial_task_processed.snap

@@ -19,7 +19,8 @@ succeeded [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_succeeded_task/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/do_not_batch_task_of_different_indexes/all_tasks_processed.snap

@@ -27,7 +27,10 @@ doggos [0,3,]
 girafos [2,5,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["cattos", "doggos", "girafos"]
+cattos: { number_of_documents: 0, field_distribution: {} }
+doggos: { number_of_documents: 0, field_distribution: {} }
+girafos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition/after_register.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition/after_the_batch_creation.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition/once_everything_is_processed.snap

@@ -19,7 +19,8 @@ succeeded [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/after_processing_the_batch.snap

@@ -0,0 +1,43 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_document_ids: 2, deleted_documents: Some(2) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [0,]
+"documentDeletion" [1,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,1,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,1,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/documents.snap

@@ -0,0 +1,9 @@
+---
+source: index-scheduler/src/lib.rs
+---
+[
+  {
+    "id": 3,
+    "doggo": "bork"
+  }
+]

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/registered_the_first_task.snap

@@ -0,0 +1,37 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/registered_the_second_task.snap

@@ -0,0 +1,40 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+1 {uid: 1, status: enqueued, details: { received_document_ids: 2, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [0,]
+"documentDeletion" [1,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/before_index_creation.snap

@@ -23,7 +23,8 @@ succeeded [0,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/both_task_succeeded.snap

@@ -23,7 +23,7 @@ succeeded [0,1,2,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/registered_the_second_task.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/registered_the_third_task.snap

@@ -22,7 +22,7 @@ enqueued [0,1,2,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion_on_unexisting_index/1.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion_on_unexisting_index/2.snap

@@ -21,7 +21,7 @@ succeeded [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/after_failing_the_deletion.snap

@@ -0,0 +1,43 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: failed, error: ResponseError { code: 200, message: "Index `doggos` not found.", error_code: "index_not_found", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_not_found" }, details: { received_document_ids: 2, deleted_documents: Some(0) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
+1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [1,]
+failed [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"documentDeletion" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/after_last_successful_addition.snap

@@ -0,0 +1,46 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: failed, error: ResponseError { code: 200, message: "Index `doggos` not found.", error_code: "index_not_found", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_not_found" }, details: { received_document_ids: 2, deleted_documents: Some(0) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
+1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [1,]
+failed [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"documentDeletion" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/documents.snap

@@ -0,0 +1,17 @@
+---
+source: index-scheduler/src/lib.rs
+---
+[
+  {
+    "id": 1,
+    "doggo": "jean bob"
+  },
+  {
+    "id": 2,
+    "catto": "jorts"
+  },
+  {
+    "id": 3,
+    "doggo": "bork"
+  }
+]

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/registered_the_first_task.snap

@@ -0,0 +1,36 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { received_document_ids: 2, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentDeletion" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/registered_the_second_task.snap

@@ -0,0 +1,40 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { received_document_ids: 2, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
+1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"documentDeletion" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/document_addition_batch_created.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/document_addition_failed.snap

@@ -19,7 +19,7 @@ failed [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_index_creation/after_register.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_index_creation/index_creation_failed.snap

@@ -19,7 +19,7 @@ failed [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/after_batch_succeeded.snap

@@ -18,7 +18,8 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/after_failing_to_commit.snap

@@ -18,7 +18,8 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By: