make CI newer

2084: bump milli r=Kerollmops a=irevoire

- Fix https://github.com/meilisearch/MeiliSearch/issues/2082 by updating milli dependency
- Fix Clippy error
- Change the MeiliSearch version in the cargo.toml to anticipate the coming release (v0.25.2)

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

.github/release-draft-template.yml

@@ -1,13 +0,0 @@
-name-template: 'v$RESOLVED_VERSION'
-tag-template: 'v$RESOLVED_VERSION'
-version-template: '0.21.0-alpha.$PATCH'
-exclude-labels:
-  - 'skip-changelog'
-template: |
-  ## Changes
-
-  $CHANGES
-no-changes-template: 'Changes are coming soon 😎'
-sort-direction: 'ascending'
-version-resolver:
-  default: patch

.github/workflows/coverage.yml

@@ -1,7 +1,6 @@
 ---
 on:
-  pull_request:
-    types: [review_requested, ready_for_review]
+  workflow_dispatch:
 
 name: Execute code coverage
 

.github/workflows/publish-binaries.yml

@@ -9,6 +9,7 @@ jobs:
     name: Publish for ${{ matrix.os }}
     runs-on: ${{ matrix.os }}
     strategy:
+      fail-fast: false
       matrix:
         os: [ubuntu-18.04, macos-latest, windows-latest]
         include:
@@ -42,11 +43,13 @@ jobs:
     runs-on: ubuntu-18.04
     steps:
       - uses: actions/checkout@v2
-      - uses: uraimo/run-on-arch-action@v1.0.7
+      - uses: uraimo/run-on-arch-action@v2.1.1
         id: runcmd
         with:
-          architecture: aarch64 # aka ARMv8
-          distribution: ubuntu18.04
+          arch: aarch64 # aka ARMv8
+          distro: ubuntu18.04
+          env: |
+            JEMALLOC_SYS_WITH_LG_PAGE: 16
           run: |
             apt update
             apt install -y curl gcc make

.github/workflows/publish-crossbuild.yml

@@ -0,0 +1,76 @@
+name: Publish aarch64 binary
+
+on:
+  release:
+    types: [published]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  publish-aarch64:
+    name: Publish to Github
+    runs-on: ${{ matrix.os }}
+    continue-on-error: false
+    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
+            asset_name: meilisearch-linux-aarch64
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Installing Rust toolchain
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          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:
+        #   JEMALLOC_SYS_WITH_LG_PAGE: 16
+        #   RUSTFLAGS: '-Clink-arg=-fuse-ld=gold'
+        run: |
+          echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config
+          echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config
+          echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV
+          echo RUSTFLAGS="-Clink-arg=-fuse-ld=gold" >> $GITHUB_ENV
+
+      - name: Cargo build
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          use-cross: ${{ matrix.use-cross }}
+          args: --release --target ${{ matrix.target }}
+
+      - name: List target output files
+        run: ls -lR ./target
+
+      - name: Upload the binary to release
+        uses: svenstaro/upload-release-action@v1-release
+        with:
+          repo_token: ${{ secrets.PUBLISH_TOKEN }}
+          file: target/${{ matrix.target }}/release/meilisearch
+          asset_name: ${{ matrix.asset_name }}
+          tag: ${{ github.ref }}

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

@@ -0,0 +1,105 @@
+name: Publish images to Docker Hub
+
+on:
+  push:
+    # Will run for every tag pushed except `latest`
+    # When the `latest` git tag is created with this [CI](../latest-git-tag.yml)
+    # we don't need to create a Docker `latest` image again.
+    # The `latest` Docker image push is already done in this CI when releasing a stable version of Meilisearch.
+    tags-ignore:
+      - latest
+  # Both `schedule` and `workflow_dispatch` build the nightly tag
+  schedule:
+    - cron: '0 23 * * *' # Every day at 11:00pm
+  workflow_dispatch:
+
+jobs:
+  docker:
+    runs-on: docker
+    steps:
+      - uses: actions/checkout@v3
+
+      # If we are running a cron or manual job ('schedule' or 'workflow_dispatch' event), it means we are publishing the `nightly` tag, so not considered stable.
+      # If we have pushed a tag, and the tag has the v<nmumber>.<number>.<number> format, it means we are publishing an official release, so considered stable.
+      # In this situation, we need to set `output.stable` to create/update the following tags (additionally to the `vX.Y.Z` Docker tag):
+      # - a `vX.Y` (without patch version) Docker tag
+      # - a `latest` Docker tag
+      # For any other tag pushed, this is not considered stable.
+      - name: Define if stable and latest release
+        id: check-tag-format
+        env:
+          # To avoid request limit with the .github/scripts/is-latest-release.sh script
+          GITHUB_PATH: ${{ secrets.MEILI_BOT_GH_PAT }}
+        run: |
+          escaped_tag=$(printf "%q" ${{ github.ref_name }})
+          echo "latest=false" >> $GITHUB_OUTPUT
+
+          if [[ ${{ github.event_name }} != 'push' ]]; then
+            echo "stable=false" >> $GITHUB_OUTPUT
+          elif [[ $escaped_tag =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            echo "stable=true" >> $GITHUB_OUTPUT
+            echo "latest=$(sh .github/scripts/is-latest-release.sh)" >> $GITHUB_OUTPUT
+          else
+            echo "stable=false" >> $GITHUB_OUTPUT
+          fi
+
+      # Check only the validity of the tag for stable releases (not for pre-releases or other tags)
+      - name: Check release validity
+        if: steps.check-tag-format.outputs.stable == 'true'
+        run: bash .github/scripts/check-release.sh
+
+      - name: Set build-args for Docker buildx
+        id: build-metadata
+        run: |
+          # Extract commit date
+          commit_date=$(git show -s --format=%cd --date=iso-strict ${{ github.sha }})
+
+          echo "date=$commit_date" >> $GITHUB_OUTPUT
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: getmeili/meilisearch
+          # Prevent `latest` to be updated for each new tag pushed.
+          # We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
+          flavor: latest=false
+          tags: |
+            type=ref,event=tag
+            type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
+            type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
+            type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
+
+      - name: Build and push
+        uses: docker/build-push-action@v4
+        with:
+          push: true
+          platforms: linux/amd64,linux/arm64
+          tags: ${{ steps.meta.outputs.tags }}
+          build-args: |
+            COMMIT_SHA=${{ 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
+        # Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event)
+        if: github.event_name == 'push'
+        uses: peter-evans/repository-dispatch@v2
+        with:
+          token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          repository: meilisearch/meilisearch-cloud
+          event-type: cloud-docker-build
+          client-payload: '{ "meilisearch_version": "${{ github.ref_name }}", "stable": "${{ steps.check-tag-format.outputs.stable }}" }'

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

@@ -1,22 +0,0 @@
----
-on:
-  release:
-    types: [released]
-
-name: Publish latest image to Docker Hub
-
-jobs:
-  build:
-    runs-on: ubuntu-18.04
-    steps:
-      - uses: actions/checkout@v2
-      - name: Check if current release is latest
-        run: echo "##[set-output name=is_latest;]$(sh .github/is-latest-release.sh)"
-        id: release
-      - name: Publish to Registry
-        if: steps.release.outputs.is_latest == 'true'
-        uses: elgohr/Publish-Docker-Github-Action@master
-        with:
-          name: getmeili/meilisearch
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_PASSWORD }}

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

@@ -1,22 +0,0 @@
----
-on:
-  push:
-    tags:
-      - '*'
-
-name: Publish tagged image to Docker Hub
-
-jobs:
-  build:
-    runs-on: ubuntu-18.04
-    steps:
-      - uses: actions/checkout@v2
-      - name: Publish to Registry
-        uses: elgohr/Publish-Docker-Github-Action@master
-        env:
-          COMMIT_SHA: ${{ github.sha }}
-        with:
-          name: getmeili/meilisearch
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_PASSWORD }}
-          tag_names: true

.github/workflows/release-drafter.yml

@@ -1,16 +0,0 @@
-name: Release Drafter
-
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  update_release_draft:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: release-drafter/release-drafter@v5
-        with:
-          config-name: release-draft-template.yml
-        env:
-          GITHUB_TOKEN: ${{ secrets.RELEASE_DRAFTER_TOKEN }}

.github/workflows/rust.yml

@@ -11,6 +11,7 @@ on:
 
 env:
   CARGO_TERM_COLOR: always
+  RUST_BACKTRACE: 1
 
 jobs:
   tests:
@@ -23,12 +24,7 @@ jobs:
     steps:
     - uses: actions/checkout@v2
     - name: Cache dependencies
-      uses: actions/cache@v2
-      with:
-        path: |
-          ~/.cargo
-          ./target
-        key: ${{ matrix.os }}-${{ hashFiles('Cargo.lock') }}
+      uses: Swatinem/rust-cache@v1.3.0
     - name: Run cargo check without any default features
       uses: actions-rs/cargo@v1
       with:
@@ -45,19 +41,14 @@ jobs:
     runs-on: ubuntu-18.04
     steps:
       - uses: actions/checkout@v2
-      - name: Cache dependencies
-        uses: actions/cache@v2
-        with:
-          path: |
-            ~/.cargo
-            ./target
-          key: ${{ matrix.os }}-${{ hashFiles('Cargo.lock') }}
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
           toolchain: stable
           override: true
           components: clippy
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v1.3.0
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -69,18 +60,13 @@ jobs:
     runs-on: ubuntu-18.04
     steps:
       - uses: actions/checkout@v2
-      - name: Cache dependencies
-        uses: actions/cache@v2
-        with:
-          path: |
-            ~/.cargo
-            ./target
-          key: ${{ matrix.os }}-${{ hashFiles('Cargo.lock') }}
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
           toolchain: nightly
           override: true
           components: rustfmt
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v1.3.0
       - name: Run cargo fmt
         run: cargo fmt --all -- --check

CONTRIBUTING.md

@@ -1,112 +1,80 @@
 # Contributing
 
-First, thank you for contributing to MeiliSearch! The goal of this document is to
-provide everything you need to start contributing to MeiliSearch. The
-following TOC is sorted progressively, starting with the basics and
-expanding into more specifics.
+First, thank you for contributing to MeiliSearch! The goal of this document is to provide everything you need to start contributing to MeiliSearch.
 
-<!-- MarkdownTOC autolink="true" style="ordered" indent="   " -->
-
-1. [Assumptions](#assumptions)
-1. [Your First Contribution](#your-first-contribution)
-1. [Change Control](#change-control)
-   1. [Git Branches](#git-branches)
-   1. [Git Commits](#git-commits)
-      1. [Style](#style)
-   1. [Github Pull Requests](#github-pull-requests)
-      1. [Reviews & Approvals](#reviews--approvals)
-      1. [Merge Style](#merge-style)
-   1. [CI](#ci)
-1. [Development](#development)
-   1. [Setup](#setup)
-   1. [Testing](#testing)
-   1. [Benchmarking](#benchmarking--profiling)
-1. [Humans](#humans)
-   1. [Documentation](#documentation)
-   1. [Changelog](#changelog)
-
-<!-- /MarkdownTOC -->
+- [Assumptions](#assumptions)
+- [How to Contribute](#how-to-contribute)
+- [Development Workflow](#development-workflow)
+- [Git Guidelines](#git-guidelines)
 
 ## Assumptions
 
-1. **You're familiar with [Github](https://github.com) and the [pull request](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/about-pull-requests)
-   workflow.**
-2. **You've read the MeiliSearch [docs](https://docs.meilisearch.com).**
+1. **You're familiar with [Github](https://github.com) and the [Pull Requests](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/about-pull-requests)(PR) workflow.**
+2. **You've read the MeiliSearch [documentation](https://docs.meilisearch.com).**
 3. **You know about the [MeiliSearch community](https://docs.meilisearch.com/learn/what_is_meilisearch/contact.html).
    Please use this for help.**
 
-## Your First Contribution
+## How to Contribute
 
 1. Ensure your change has an issue! Find an
    [existing issue](https://github.com/meilisearch/meilisearch/issues/) or [open a new issue](https://github.com/meilisearch/meilisearch/issues/new).
    * This is where you can get a feel if the change will be accepted or not.
-2. Once approved, [fork the MeiliSearch repository](https://help.github.com/en/github/getting-started-with-github/fork-a-repo) in your own
-   Github account.
+2. Once approved, [fork the MeiliSearch repository](https://help.github.com/en/github/getting-started-with-github/fork-a-repo) in your own Github account.
 3. [Create a new Git branch](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/creating-and-deleting-branches-within-your-repository)
-4. Review the MeiliSearch [workflow](#workflow) and [development](#development).
-5. Make your changes.
-6. [Submit the branch as a pull request](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/creating-a-pull-request-from-a-fork) to the main MeiliSearch
-   repo. A MeiliSearch team member should comment and/or review your pull request
-   with a few days. Although, depending on the circumstances, it may take
-   longer.
+4. Review the [Development Workflow](#development-workflow) section that describes the steps to maintain the repository.
+5. Make your changes on your branch.
+6. [Submit the branch as a Pull Request](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/creating-a-pull-request-from-a-fork) pointing to the `main` branch of the MeiliSearch repository. A maintainer should comment and/or review your Pull Request within a few days. Although depending on the circumstances, it may take longer.
 
-## Change Control
+## Development Workflow
+
+### Setup and run MeiliSearch
+
+```bash
+cargo run --release
+```
+
+We recommend using the `--release` flag to test the full performance of MeiliSearch.
+
+### Test
+
+```bash
+cargo test
+```
+
+If you get a "Too many open files" error you might want to increase the open file limit using this command:
+
+```bash
+ulimit -Sn 3000
+```
+
+## Git Guidelines
 
 ### Git Branches
 
-_All_ changes must be made in a branch and submitted as [pull requests](#pull-requests).
-MeiliSearch does not adopt any type of branch naming style, but please use something
-descriptive of your changes.
+All changes must be made in a branch and submitted as PR.
+
+We do not enforce any branch naming style, but please use something descriptive of your changes.
 
 ### Git Commits
 
-#### Style
+As minimal requirements, your commit message should:
+- be capitalized
+- not finish by a dot or any other punctuation character (!,?)
+- start with a verb so that we can read your commit message this way: "This commit will ...", where "..." is the commit message.
+  e.g.: "Fix the home page button" or "Add more tests for create_index method"
 
-Please ensure your commits are small and focused; they should tell a story of
-your change. This helps reviewers to follow your changes, especially for more
-complex changes.
-
-Familiarise yourself with [How to Write a Git Commit Message](https://chris.beams.io/posts/git-commit/).
+We don't follow any other convention, but if you want to use one, we recommend [the Chris Beams one](https://chris.beams.io/posts/git-commit/).
 
 ### Github Pull Requests
 
-Once your changes are ready you must submit your branch as a pull request.
+Some notes on GitHub PRs:
 
-#### Reviews & Approvals
+- All PRs must be reviewed and approved by at least one maintainer.
+- The PR title should be accurate and descriptive of the changes.
+- [Convert your PR as a draft](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/changing-the-stage-of-a-pull-request) if your changes are a work in progress: no one will review it until you pass your PR as ready for review.<br>
+  The draft PRs are recommended when you want to show that you are working on something and make your work visible.
+- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [Bors](https://github.com/bors-ng/bors-ng) to automatically enforce this requirement without the PR author having to rebase manually.
 
-All pull requests must be reviewed and approved by at least one MeiliSearch team
-member.
+<hr>
 
-#### Merge Style
-
-All pull requests are squashed and merged. We generally discourage large pull
-requests that are over 300-500 lines of diff. If you would like to propose
-a change that is larger we suggest coming onto our chat channel and
-discuss it with one of our engineers. This way we can talk through the
-solution and discuss if a change that large is even needed! This overall
-will produce a quicker response to the change and likely produce code that
-aligns better with our process.
-
-## Development
-
-### Setup
-
-See the [MeiliSearch Docs](https://docs.meilisearch.com/reference/features/installation.html) for how to set up a development environment.
-
-### Benchmarking & Profiling
-
-We do not yet do any benchmarking, nor have we formalised our profiling. If you'd like to work on this please get in touch!
-
-## Humans
-
-After making your change, you'll want to prepare it for MeiliSearch users (mostly humans). This usually entails updating documentation and announcing your feature.
-
-### Documentation
-
-Documentation is very important to MeiliSearch. All contributions that
-alter user-facing behavior MUST include documentation changes. Please see
-[GitHub.com/meilisearch/documentation](https://github.com/meilisearch/documentation) for more info.
-
-### Changelog
-
-Until we have guidelines in place, updating the [`Changelog`](/CHANGELOG.md) is solely the responsibility of MeiliSearch team members.
+Thank you again for reading this through, we can not wait to begin to work with you if you made your way through this contributing guide ❤️

Cargo.toml

@@ -2,7 +2,8 @@
 members = [
     "meilisearch-http",
     "meilisearch-error",
+    "meilisearch-lib",
+    "meilisearch-auth",
 ]
 
-[profile.release]
-debug = true
+resolver = "2"

Cross.toml

@@ -0,0 +1,7 @@
+[build.env]
+passthrough = [
+    "RUST_BACKTRACE",
+    "CARGO_TERM_COLOR",
+    "RUSTFLAGS",
+    "JEMALLOC_SYS_WITH_LG_PAGE"
+]

Dockerfile

@@ -1,9 +1,8 @@
 # Compile
 FROM    alpine:3.14 AS compiler
 
-RUN     apk update --quiet
-RUN     apk add curl
-RUN     apk add build-base
+RUN     apk update --quiet \
+        && apk add -q --no-cache curl build-base
 
 RUN     curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
 
@@ -12,8 +11,10 @@ WORKDIR /meilisearch
 COPY    Cargo.lock .
 COPY    Cargo.toml .
 
+COPY    meilisearch-auth/Cargo.toml meilisearch-auth/
 COPY    meilisearch-error/Cargo.toml meilisearch-error/
 COPY    meilisearch-http/Cargo.toml meilisearch-http/
+COPY    meilisearch-lib/Cargo.toml meilisearch-lib/
 
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
@@ -34,11 +35,14 @@ RUN     $HOME/.cargo/bin/cargo build --release
 # Run
 FROM    alpine:3.14
 
-RUN     apk add -q --no-cache libgcc tini
+ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
+ENV     MEILI_SERVER_PROVIDER docker
+
+RUN     apk update --quiet \
+        && apk add -q --no-cache libgcc tini curl
 
 COPY    --from=compiler /meilisearch/target/release/meilisearch .
 
-ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
 EXPOSE  7700/tcp
 
 ENTRYPOINT ["tini", "--"]

README.md

@@ -61,6 +61,10 @@ meilisearch
 docker run -p 7700:7700 -v "$(pwd)/data.ms:/data.ms" getmeili/meilisearch
 ```
 
+#### Announcing a cloud-hosted MeiliSearch
+
+Join the closed beta by filling out this [form](https://meilisearch.typeform.com/to/FtnzvZfh).
+
 #### Try MeiliSearch in our Sandbox
 
 Create a MeiliSearch instance in [MeiliSearch Sandbox](https://sandbox.meilisearch.com/). This instance is free, and will be active for 48 hours.
@@ -183,7 +187,7 @@ Search and indexation are the domain of our core engine, [`milli`](https://githu
 MeiliSearch collects anonymous data regarding general usage.
 This helps us better understand developers' usage of MeiliSearch features.
 
-To see what information we're retrieving, please see the complete list [on the dedicated issue](https://github.com/meilisearch/MeiliSearch/issues/720).
+To find out more on what information we're retrieving, please see our documentation on [Telemetry](https://docs.meilisearch.com/learn/what_is_meilisearch/telemetry.html).
 
 This program is optional, you can disable these analytics by using the `MEILI_NO_ANALYTICS` env variable.
 

SECURITY.md

@@ -0,0 +1,33 @@
+# Security
+
+MeiliSearch takes the security of our software products and services seriously.
+
+If you believe you have found a security vulnerability in any MeiliSearch-owned repository, please report it to us as described below.
+
+## Suported versions
+
+As long as we are pre-v1.0, only the latest version of MeiliSearch will be supported with security updates. 
+
+## Reporting security issues
+
+⚠️ Please do not report security vulnerabilities through public GitHub issues. ⚠️ 
+
+Instead, please kindly email us at security@meilisearch.com
+
+Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
+
+- Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
+- Full paths of source file(s) related to the manifestation of the issue
+- The location of the affected source code (tag/branch/commit or direct URL)
+- Any special configuration required to reproduce the issue
+- Step-by-step instructions to reproduce the issue
+- Proof-of-concept or exploit code (if possible)
+- Impact of the issue, including how an attacker might exploit the issue
+
+This information will help us triage your report more quickly.
+
+You will receive a response from us within 72 hours. If the issue is confirmed, we will release a patch as soon as possible depending on complexity.
+
+## Preferred languages
+
+We prefer all communications to be in English.

bors.toml

@@ -5,5 +5,6 @@ status = [
     'Run Clippy',
     'Run Rustfmt'
 ]
+pr_status = ['Milestone Check']
 # 3 hours timeout
 timeout-sec = 10800

datasets/movies/README.md

@@ -1 +0,0 @@
-_datas in movies.json are from https://www.themoviedb.org/_

download-latest.sh

@@ -51,13 +51,13 @@ semverLT() {
     if [ $MAJOR_A -le $MAJOR_B ] && [ $MINOR_A -le $MINOR_B ] && [ $PATCH_A -lt $PATCH_B ]; then
         return 0
     fi
-    if [ "_$SPECIAL_A"  == "_" ] && [ "_$SPECIAL_B"  == "_" ] ; then
+    if [ "_$SPECIAL_A"  == '_' ] && [ "_$SPECIAL_B"  == '_' ] ; then
         return 1
     fi
-    if [ "_$SPECIAL_A"  == "_" ] && [ "_$SPECIAL_B"  != "_" ] ; then
+    if [ "_$SPECIAL_A"  == '_' ] && [ "_$SPECIAL_B"  != '_' ] ; then
         return 1
     fi
-    if [ "_$SPECIAL_A"  != "_" ] && [ "_$SPECIAL_B"  == "_" ] ; then
+    if [ "_$SPECIAL_A"  != '_' ] && [ "_$SPECIAL_B"  == '_' ] ; then
         return 0
     fi
     if [ "_$SPECIAL_A" < "_$SPECIAL_B" ]; then
@@ -67,39 +67,47 @@ semverLT() {
     return 1
 }
 
+# Get a token from https://github.com/settings/tokens to increasae rate limit (from 60 to 5000), make sure the token scope is set to 'public_repo'
+# Create GITHUB_PAT enviroment variable once you aquired the token to start using it
 # Returns the tag of the latest stable release (in terms of semver and not of release date)
 get_latest() {
     temp_file='temp_file' # temp_file needed because the grep would start before the download is over
-    curl -s 'https://api.github.com/repos/meilisearch/MeiliSearch/releases' > "$temp_file" || return 1
+
+        if [ -z "$GITHUB_PAT" ]; then
+        curl -s 'https://api.github.com/repos/meilisearch/MeiliSearch/releases' > "$temp_file" || return 1
+    else
+        curl -H "Authorization: token $GITHUB_PAT" -s 'https://api.github.com/repos/meilisearch/MeiliSearch/releases' > "$temp_file" || return 1
+    fi
+
     releases=$(cat "$temp_file" | \
-        grep -E "tag_name|draft|prerelease" \
+        grep -E '"tag_name":|"draft":|"prerelease":' \
         | tr -d ',"' | cut -d ':' -f2 | tr -d ' ')
         # Returns a list of [tag_name draft_boolean prerelease_boolean ...]
         # Ex: v0.10.1 false false v0.9.1-rc.1 false true v0.9.0 false false...
 
     i=0
-    latest=""
-    current_tag=""
+    latest=''
+    current_tag=''
     for release_info in $releases; do
         if [ $i -eq 0 ]; then # Cheking tag_name
             if echo "$release_info" | grep -q "$GREP_SEMVER_REGEXP"; then # If it's not an alpha or beta release
                 current_tag=$release_info
             else
-                current_tag=""
+                current_tag=''
             fi
             i=1
         elif [ $i -eq 1 ]; then # Checking draft boolean
-            if [ "$release_info" = "true" ]; then
-                current_tag=""
+            if [ "$release_info" = 'true' ]; then
+                current_tag=''
             fi
             i=2
         elif [ $i -eq 2 ]; then # Checking prerelease boolean
-            if [ "$release_info" = "true" ]; then
-                current_tag=""
+            if [ "$release_info" = 'true' ]; then
+                current_tag=''
             fi
             i=0
-            if [ "$current_tag" != "" ]; then # If the current_tag is valid
-                if [ "$latest" = "" ]; then # If there is no latest yet
+            if [ "$current_tag" != '' ]; then # If the current_tag is valid
+                if [ "$latest" = '' ]; then # If there is no latest yet
                     latest="$current_tag"
                 else
                     semverLT $current_tag $latest # Comparing latest and the current tag
@@ -140,7 +148,7 @@ get_os() {
 get_archi() {
     architecture=$(uname -m)
     case "$architecture" in
-    'x86_64' | 'amd64')
+    'x86_64' | 'amd64' | 'arm64')
         archi='amd64'
         ;;
     'aarch64')
@@ -153,7 +161,7 @@ get_archi() {
 }
 
 success_usage() {
-    printf "$GREEN%s\n$DEFAULT" "MeiliSearch binary successfully downloaded as '$BINARY_NAME' file."
+    printf "$GREEN%s\n$DEFAULT" "MeiliSearch $latest binary successfully downloaded as '$binary_name' file."
     echo ''
     echo 'Run it:'
     echo '    $ ./meilisearch'
@@ -171,6 +179,13 @@ failure_usage() {
 # MAIN
 latest="$(get_latest)"
 
+if [ "$latest" = '' ]; then
+    echo ''
+    echo 'Impossible to get the latest stable version of MeiliSearch.'
+    echo 'Please let us know about this issue: https://github.com/meilisearch/MeiliSearch/issues/new/choose'
+    exit 1
+fi
+
 if ! get_os; then
     failure_usage
     exit 1
@@ -185,16 +200,16 @@ echo "Downloading MeiliSearch binary $latest for $os, architecture $archi..."
 case "$os" in
     'windows')
         release_file="meilisearch-$os-$archi.exe"
-		BINARY_NAME='meilisearch.exe'
+		binary_name='meilisearch.exe'
 
         ;;
-	*) 
+	*)
 		release_file="meilisearch-$os-$archi"
-		BINARY_NAME='meilisearch'
+		binary_name='meilisearch'
 
 esac
 link="https://github.com/meilisearch/MeiliSearch/releases/download/$latest/$release_file"
 curl -OL "$link"
-mv "$release_file" "$BINARY_NAME"
-chmod 744 "$BINARY_NAME"
+mv "$release_file" "$binary_name"
+chmod 744 "$binary_name"
 success_usage

meilisearch-auth/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "meilisearch-auth"
+version = "0.25.0"
+edition = "2018"
+
+[dependencies]
+enum-iterator = "0.7.0"
+heed = { git = "https://github.com/Kerollmops/heed", tag = "v0.12.1" }
+sha2 = "0.9.6"
+chrono = { version = "0.4.19", features = ["serde"] }
+meilisearch-error = { path = "../meilisearch-error" }
+serde_json = { version = "1.0.67", features = ["preserve_order"] }
+rand = "0.8.4"
+serde = { version = "1.0.130", features = ["derive"] }
+thiserror = "1.0.28"

meilisearch-auth/src/action.rs

@@ -0,0 +1,104 @@
+use enum_iterator::IntoEnumIterator;
+use serde::{Deserialize, Serialize};
+
+#[derive(IntoEnumIterator, Copy, Clone, Serialize, Deserialize, Debug, Eq, PartialEq)]
+#[repr(u8)]
+pub enum Action {
+    #[serde(rename = "*")]
+    All = 0,
+    #[serde(rename = "search")]
+    Search = actions::SEARCH,
+    #[serde(rename = "documents.add")]
+    DocumentsAdd = actions::DOCUMENTS_ADD,
+    #[serde(rename = "documents.get")]
+    DocumentsGet = actions::DOCUMENTS_GET,
+    #[serde(rename = "documents.delete")]
+    DocumentsDelete = actions::DOCUMENTS_DELETE,
+    #[serde(rename = "indexes.create")]
+    IndexesAdd = actions::INDEXES_CREATE,
+    #[serde(rename = "indexes.get")]
+    IndexesGet = actions::INDEXES_GET,
+    #[serde(rename = "indexes.update")]
+    IndexesUpdate = actions::INDEXES_UPDATE,
+    #[serde(rename = "indexes.delete")]
+    IndexesDelete = actions::INDEXES_DELETE,
+    #[serde(rename = "tasks.get")]
+    TasksGet = actions::TASKS_GET,
+    #[serde(rename = "settings.get")]
+    SettingsGet = actions::SETTINGS_GET,
+    #[serde(rename = "settings.update")]
+    SettingsUpdate = actions::SETTINGS_UPDATE,
+    #[serde(rename = "stats.get")]
+    StatsGet = actions::STATS_GET,
+    #[serde(rename = "dumps.create")]
+    DumpsCreate = actions::DUMPS_CREATE,
+    #[serde(rename = "dumps.get")]
+    DumpsGet = actions::DUMPS_GET,
+    #[serde(rename = "version")]
+    Version = actions::VERSION,
+}
+
+impl Action {
+    pub fn from_repr(repr: u8) -> Option<Self> {
+        use actions::*;
+        match repr {
+            0 => Some(Self::All),
+            SEARCH => Some(Self::Search),
+            DOCUMENTS_ADD => Some(Self::DocumentsAdd),
+            DOCUMENTS_GET => Some(Self::DocumentsGet),
+            DOCUMENTS_DELETE => Some(Self::DocumentsDelete),
+            INDEXES_CREATE => Some(Self::IndexesAdd),
+            INDEXES_GET => Some(Self::IndexesGet),
+            INDEXES_UPDATE => Some(Self::IndexesUpdate),
+            INDEXES_DELETE => Some(Self::IndexesDelete),
+            TASKS_GET => Some(Self::TasksGet),
+            SETTINGS_GET => Some(Self::SettingsGet),
+            SETTINGS_UPDATE => Some(Self::SettingsUpdate),
+            STATS_GET => Some(Self::StatsGet),
+            DUMPS_CREATE => Some(Self::DumpsCreate),
+            DUMPS_GET => Some(Self::DumpsGet),
+            VERSION => Some(Self::Version),
+            _otherwise => None,
+        }
+    }
+
+    pub fn repr(&self) -> u8 {
+        use actions::*;
+        match self {
+            Self::All => 0,
+            Self::Search => SEARCH,
+            Self::DocumentsAdd => DOCUMENTS_ADD,
+            Self::DocumentsGet => DOCUMENTS_GET,
+            Self::DocumentsDelete => DOCUMENTS_DELETE,
+            Self::IndexesAdd => INDEXES_CREATE,
+            Self::IndexesGet => INDEXES_GET,
+            Self::IndexesUpdate => INDEXES_UPDATE,
+            Self::IndexesDelete => INDEXES_DELETE,
+            Self::TasksGet => TASKS_GET,
+            Self::SettingsGet => SETTINGS_GET,
+            Self::SettingsUpdate => SETTINGS_UPDATE,
+            Self::StatsGet => STATS_GET,
+            Self::DumpsCreate => DUMPS_CREATE,
+            Self::DumpsGet => DUMPS_GET,
+            Self::Version => VERSION,
+        }
+    }
+}
+
+pub mod actions {
+    pub const SEARCH: u8 = 1;
+    pub const DOCUMENTS_ADD: u8 = 2;
+    pub const DOCUMENTS_GET: u8 = 3;
+    pub const DOCUMENTS_DELETE: u8 = 4;
+    pub const INDEXES_CREATE: u8 = 5;
+    pub const INDEXES_GET: u8 = 6;
+    pub const INDEXES_UPDATE: u8 = 7;
+    pub const INDEXES_DELETE: u8 = 8;
+    pub const TASKS_GET: u8 = 9;
+    pub const SETTINGS_GET: u8 = 10;
+    pub const SETTINGS_UPDATE: u8 = 11;
+    pub const STATS_GET: u8 = 12;
+    pub const DUMPS_CREATE: u8 = 13;
+    pub const DUMPS_GET: u8 = 14;
+    pub const VERSION: u8 = 15;
+}

meilisearch-auth/src/dump.rs

@@ -0,0 +1,44 @@
+use std::fs::File;
+use std::io::BufRead;
+use std::io::BufReader;
+use std::io::Write;
+use std::path::Path;
+
+use crate::{AuthController, HeedAuthStore, Result};
+
+const KEYS_PATH: &str = "keys";
+
+impl AuthController {
+    pub fn dump(src: impl AsRef<Path>, dst: impl AsRef<Path>) -> Result<()> {
+        let store = HeedAuthStore::new(&src)?;
+
+        let keys_file_path = dst.as_ref().join(KEYS_PATH);
+
+        let keys = store.list_api_keys()?;
+        let mut keys_file = File::create(&keys_file_path)?;
+        for key in keys {
+            serde_json::to_writer(&mut keys_file, &key)?;
+            keys_file.write_all(b"\n")?;
+        }
+
+        Ok(())
+    }
+
+    pub fn load_dump(src: impl AsRef<Path>, dst: impl AsRef<Path>) -> Result<()> {
+        let store = HeedAuthStore::new(&dst)?;
+
+        let keys_file_path = src.as_ref().join(KEYS_PATH);
+
+        if !keys_file_path.exists() {
+            return Ok(());
+        }
+
+        let mut reader = BufReader::new(File::open(&keys_file_path)?).lines();
+        while let Some(key) = reader.next().transpose()? {
+            let key = serde_json::from_str(&key)?;
+            store.put_api_key(key)?;
+        }
+
+        Ok(())
+    }
+}

meilisearch-auth/src/error.rs

@@ -0,0 +1,46 @@
+use std::error::Error;
+
+use meilisearch_error::ErrorCode;
+use meilisearch_error::{internal_error, Code};
+use serde_json::Value;
+
+pub type Result<T> = std::result::Result<T, AuthControllerError>;
+
+#[derive(Debug, thiserror::Error)]
+pub enum AuthControllerError {
+    #[error("`{0}` field is mandatory.")]
+    MissingParameter(&'static str),
+    #[error("actions field value `{0}` is invalid. It should be an array of string representing action names.")]
+    InvalidApiKeyActions(Value),
+    #[error("indexes field value `{0}` is invalid. It should be an array of string representing index names.")]
+    InvalidApiKeyIndexes(Value),
+    #[error("expiresAt field value `{0}` is invalid. It should be in ISO-8601 format to represents a date or datetime in the future or specified as a null value. e.g. 'YYYY-MM-DD' or 'YYYY-MM-DDTHH:MM:SS'.")]
+    InvalidApiKeyExpiresAt(Value),
+    #[error("description field value `{0}` is invalid. It should be a string or specified as a null value.")]
+    InvalidApiKeyDescription(Value),
+    #[error("API key `{0}` not found.")]
+    ApiKeyNotFound(String),
+    #[error("Internal error: {0}")]
+    Internal(Box<dyn Error + Send + Sync + 'static>),
+}
+
+internal_error!(
+    AuthControllerError: heed::Error,
+    std::io::Error,
+    serde_json::Error,
+    std::str::Utf8Error
+);
+
+impl ErrorCode for AuthControllerError {
+    fn error_code(&self) -> Code {
+        match self {
+            Self::MissingParameter(_) => Code::MissingParameter,
+            Self::InvalidApiKeyActions(_) => Code::InvalidApiKeyActions,
+            Self::InvalidApiKeyIndexes(_) => Code::InvalidApiKeyIndexes,
+            Self::InvalidApiKeyExpiresAt(_) => Code::InvalidApiKeyExpiresAt,
+            Self::InvalidApiKeyDescription(_) => Code::InvalidApiKeyDescription,
+            Self::ApiKeyNotFound(_) => Code::ApiKeyNotFound,
+            Self::Internal(_) => Code::Internal,
+        }
+    }
+}

meilisearch-auth/src/key.rs

@@ -0,0 +1,161 @@
+use crate::action::Action;
+use crate::error::{AuthControllerError, Result};
+use crate::store::{KeyId, KEY_ID_LENGTH};
+use chrono::{DateTime, NaiveDate, NaiveDateTime, Utc};
+use rand::Rng;
+use serde::{Deserialize, Serialize};
+use serde_json::{from_value, Value};
+
+#[derive(Debug, Deserialize, Serialize)]
+pub struct Key {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    pub id: KeyId,
+    pub actions: Vec<Action>,
+    pub indexes: Vec<String>,
+    pub expires_at: Option<DateTime<Utc>>,
+    pub created_at: DateTime<Utc>,
+    pub updated_at: DateTime<Utc>,
+}
+
+impl Key {
+    pub fn create_from_value(value: Value) -> Result<Self> {
+        let description = value
+            .get("description")
+            .map(|des| {
+                from_value(des.clone())
+                    .map_err(|_| AuthControllerError::InvalidApiKeyDescription(des.clone()))
+            })
+            .transpose()?;
+
+        let id = generate_id();
+
+        let actions = value
+            .get("actions")
+            .map(|act| {
+                from_value(act.clone())
+                    .map_err(|_| AuthControllerError::InvalidApiKeyActions(act.clone()))
+            })
+            .ok_or(AuthControllerError::MissingParameter("actions"))??;
+
+        let indexes = value
+            .get("indexes")
+            .map(|ind| {
+                from_value(ind.clone())
+                    .map_err(|_| AuthControllerError::InvalidApiKeyIndexes(ind.clone()))
+            })
+            .ok_or(AuthControllerError::MissingParameter("indexes"))??;
+
+        let expires_at = value
+            .get("expiresAt")
+            .map(parse_expiration_date)
+            .ok_or(AuthControllerError::MissingParameter("expiresAt"))??;
+
+        let created_at = Utc::now();
+        let updated_at = Utc::now();
+
+        Ok(Self {
+            description,
+            id,
+            actions,
+            indexes,
+            expires_at,
+            created_at,
+            updated_at,
+        })
+    }
+
+    pub fn update_from_value(&mut self, value: Value) -> Result<()> {
+        if let Some(des) = value.get("description") {
+            let des = from_value(des.clone())
+                .map_err(|_| AuthControllerError::InvalidApiKeyDescription(des.clone()));
+            self.description = des?;
+        }
+
+        if let Some(act) = value.get("actions") {
+            let act = from_value(act.clone())
+                .map_err(|_| AuthControllerError::InvalidApiKeyActions(act.clone()));
+            self.actions = act?;
+        }
+
+        if let Some(ind) = value.get("indexes") {
+            let ind = from_value(ind.clone())
+                .map_err(|_| AuthControllerError::InvalidApiKeyIndexes(ind.clone()));
+            self.indexes = ind?;
+        }
+
+        if let Some(exp) = value.get("expiresAt") {
+            self.expires_at = parse_expiration_date(exp)?;
+        }
+
+        self.updated_at = Utc::now();
+
+        Ok(())
+    }
+
+    pub(crate) fn default_admin() -> Self {
+        Self {
+            description: Some("Default Admin API Key (Use it for all other operations. Caution! Do not use it on a public frontend)".to_string()),
+            id: generate_id(),
+            actions: vec![Action::All],
+            indexes: vec!["*".to_string()],
+            expires_at: None,
+            created_at: Utc::now(),
+            updated_at: Utc::now(),
+        }
+    }
+
+    pub(crate) fn default_search() -> Self {
+        Self {
+            description: Some(
+                "Default Search API Key (Use it to search from the frontend)".to_string(),
+            ),
+            id: generate_id(),
+            actions: vec![Action::Search],
+            indexes: vec!["*".to_string()],
+            expires_at: None,
+            created_at: Utc::now(),
+            updated_at: Utc::now(),
+        }
+    }
+}
+
+/// Generate a printable key of 64 characters using thread_rng.
+fn generate_id() -> [u8; KEY_ID_LENGTH] {
+    const CHARSET: &[u8] = b"abcdefghijklmnopqrstuvwxyz0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+
+    let mut rng = rand::thread_rng();
+    let mut bytes = [0; KEY_ID_LENGTH];
+    for byte in bytes.iter_mut() {
+        *byte = CHARSET[rng.gen_range(0..CHARSET.len())];
+    }
+
+    bytes
+}
+
+fn parse_expiration_date(value: &Value) -> Result<Option<DateTime<Utc>>> {
+    match value {
+        Value::String(string) => DateTime::parse_from_rfc3339(string)
+            .map(|d| d.into())
+            .or_else(|_| {
+                NaiveDateTime::parse_from_str(string, "%Y-%m-%dT%H:%M:%S")
+                    .map(|naive| DateTime::from_utc(naive, Utc))
+            })
+            .or_else(|_| {
+                NaiveDate::parse_from_str(string, "%Y-%m-%d")
+                    .map(|naive| DateTime::from_utc(naive.and_hms(0, 0, 0), Utc))
+            })
+            .map_err(|_| AuthControllerError::InvalidApiKeyExpiresAt(value.clone()))
+            // check if the key is already expired.
+            .and_then(|d| {
+                if d > Utc::now() {
+                    Ok(d)
+                } else {
+                    Err(AuthControllerError::InvalidApiKeyExpiresAt(value.clone()))
+                }
+            })
+            .map(Option::Some),
+        Value::Null => Ok(None),
+        _otherwise => Err(AuthControllerError::InvalidApiKeyExpiresAt(value.clone())),
+    }
+}

meilisearch-auth/src/lib.rs

@@ -0,0 +1,151 @@
+mod action;
+mod dump;
+pub mod error;
+mod key;
+mod store;
+
+use std::path::Path;
+use std::str::from_utf8;
+use std::sync::Arc;
+
+use chrono::Utc;
+use serde_json::Value;
+use sha2::{Digest, Sha256};
+
+pub use action::{actions, Action};
+use error::{AuthControllerError, Result};
+pub use key::Key;
+use store::HeedAuthStore;
+
+#[derive(Clone)]
+pub struct AuthController {
+    store: Arc<HeedAuthStore>,
+    master_key: Option<String>,
+}
+
+impl AuthController {
+    pub fn new(db_path: impl AsRef<Path>, master_key: &Option<String>) -> Result<Self> {
+        let store = HeedAuthStore::new(db_path)?;
+
+        if store.is_empty()? {
+            generate_default_keys(&store)?;
+        }
+
+        Ok(Self {
+            store: Arc::new(store),
+            master_key: master_key.clone(),
+        })
+    }
+
+    pub async fn create_key(&self, value: Value) -> Result<Key> {
+        let key = Key::create_from_value(value)?;
+        self.store.put_api_key(key)
+    }
+
+    pub async fn update_key(&self, key: impl AsRef<str>, value: Value) -> Result<Key> {
+        let mut key = self.get_key(key).await?;
+        key.update_from_value(value)?;
+        self.store.put_api_key(key)
+    }
+
+    pub async fn get_key(&self, key: impl AsRef<str>) -> Result<Key> {
+        self.store
+            .get_api_key(&key)?
+            .ok_or_else(|| AuthControllerError::ApiKeyNotFound(key.as_ref().to_string()))
+    }
+
+    pub fn get_key_filters(&self, key: impl AsRef<str>) -> Result<AuthFilter> {
+        let mut filters = AuthFilter::default();
+        if self
+            .master_key
+            .as_ref()
+            .map_or(false, |master_key| master_key != key.as_ref())
+        {
+            let key = self
+                .store
+                .get_api_key(&key)?
+                .ok_or_else(|| AuthControllerError::ApiKeyNotFound(key.as_ref().to_string()))?;
+
+            if !key.indexes.iter().any(|i| i.as_str() == "*") {
+                filters.indexes = Some(key.indexes);
+            }
+
+            filters.allow_index_creation = key
+                .actions
+                .iter()
+                .any(|&action| action == Action::IndexesAdd || action == Action::All);
+        }
+
+        Ok(filters)
+    }
+
+    pub async fn list_keys(&self) -> Result<Vec<Key>> {
+        self.store.list_api_keys()
+    }
+
+    pub async fn delete_key(&self, key: impl AsRef<str>) -> Result<()> {
+        if self.store.delete_api_key(&key)? {
+            Ok(())
+        } else {
+            Err(AuthControllerError::ApiKeyNotFound(
+                key.as_ref().to_string(),
+            ))
+        }
+    }
+
+    pub fn get_master_key(&self) -> Option<&String> {
+        self.master_key.as_ref()
+    }
+
+    pub fn authenticate(&self, token: &[u8], action: Action, index: Option<&[u8]>) -> Result<bool> {
+        if let Some(master_key) = &self.master_key {
+            if let Some((id, exp)) = self
+                .store
+                // check if the key has access to all indexes.
+                .get_expiration_date(token, action, None)?
+                .or(match index {
+                    // else check if the key has access to the requested index.
+                    Some(index) => self.store.get_expiration_date(token, action, Some(index))?,
+                    // or to any index if no index has been requested.
+                    None => self.store.prefix_first_expiration_date(token, action)?,
+                })
+            {
+                let id = from_utf8(&id)?;
+                if exp.map_or(true, |exp| Utc::now() < exp)
+                    && generate_key(master_key.as_bytes(), id).as_bytes() == token
+                {
+                    return Ok(true);
+                }
+            }
+        }
+
+        Ok(false)
+    }
+}
+
+pub struct AuthFilter {
+    pub indexes: Option<Vec<String>>,
+    pub allow_index_creation: bool,
+}
+
+impl Default for AuthFilter {
+    fn default() -> Self {
+        Self {
+            indexes: None,
+            allow_index_creation: true,
+        }
+    }
+}
+
+pub fn generate_key(master_key: &[u8], uid: &str) -> String {
+    let key = [uid.as_bytes(), master_key].concat();
+    let sha = Sha256::digest(&key);
+    format!("{}{:x}", uid, sha)
+}
+
+fn generate_default_keys(store: &HeedAuthStore) -> Result<()> {
+    store.put_api_key(Key::default_admin())?;
+    store.put_api_key(Key::default_search())?;
+
+    Ok(())
+}

meilisearch-auth/src/store.rs

@@ -0,0 +1,236 @@
+use enum_iterator::IntoEnumIterator;
+use std::borrow::Cow;
+use std::cmp::Reverse;
+use std::convert::TryFrom;
+use std::convert::TryInto;
+use std::fs::create_dir_all;
+use std::path::Path;
+use std::str;
+
+use chrono::{DateTime, Utc};
+use heed::types::{ByteSlice, DecodeIgnore, SerdeJson};
+use heed::{Database, Env, EnvOpenOptions, RwTxn};
+
+use super::error::Result;
+use super::{Action, Key};
+
+const AUTH_STORE_SIZE: usize = 1_073_741_824; //1GiB
+pub const KEY_ID_LENGTH: usize = 8;
+const AUTH_DB_PATH: &str = "auth";
+const KEY_DB_NAME: &str = "api-keys";
+const KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME: &str = "keyid-action-index-expiration";
+
+pub type KeyId = [u8; KEY_ID_LENGTH];
+
+#[derive(Clone)]
+pub struct HeedAuthStore {
+    env: Env,
+    keys: Database<ByteSlice, SerdeJson<Key>>,
+    action_keyid_index_expiration: Database<KeyIdActionCodec, SerdeJson<Option<DateTime<Utc>>>>,
+}
+
+impl HeedAuthStore {
+    pub fn new(path: impl AsRef<Path>) -> Result<Self> {
+        let path = path.as_ref().join(AUTH_DB_PATH);
+        create_dir_all(&path)?;
+        let mut options = EnvOpenOptions::new();
+        options.map_size(AUTH_STORE_SIZE); // 1GB
+        options.max_dbs(2);
+        let env = options.open(path)?;
+        let keys = env.create_database(Some(KEY_DB_NAME))?;
+        let action_keyid_index_expiration =
+            env.create_database(Some(KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME))?;
+        Ok(Self {
+            env,
+            keys,
+            action_keyid_index_expiration,
+        })
+    }
+
+    pub fn is_empty(&self) -> Result<bool> {
+        let rtxn = self.env.read_txn()?;
+
+        Ok(self.keys.len(&rtxn)? == 0)
+    }
+
+    pub fn put_api_key(&self, key: Key) -> Result<Key> {
+        let mut wtxn = self.env.write_txn()?;
+        self.keys.put(&mut wtxn, &key.id, &key)?;
+
+        let id = key.id;
+        // delete key from inverted database before refilling it.
+        self.delete_key_from_inverted_db(&mut wtxn, &id)?;
+        // create inverted database.
+        let db = self.action_keyid_index_expiration;
+
+        let actions = if key.actions.contains(&Action::All) {
+            // if key.actions contains All, we iterate over all actions.
+            Action::into_enum_iter().collect()
+        } else {
+            key.actions.clone()
+        };
+
+        let no_index_restriction = key.indexes.contains(&"*".to_owned());
+        for action in actions {
+            if no_index_restriction {
+                // If there is no index restriction we put None.
+                db.put(&mut wtxn, &(&id, &action, None), &key.expires_at)?;
+            } else {
+                // else we create a key for each index.
+                for index in key.indexes.iter() {
+                    db.put(
+                        &mut wtxn,
+                        &(&id, &action, Some(index.as_bytes())),
+                        &key.expires_at,
+                    )?;
+                }
+            }
+        }
+
+        wtxn.commit()?;
+
+        Ok(key)
+    }
+
+    pub fn get_api_key(&self, key: impl AsRef<str>) -> Result<Option<Key>> {
+        let rtxn = self.env.read_txn()?;
+        match try_split_array_at::<_, KEY_ID_LENGTH>(key.as_ref().as_bytes()) {
+            Some((id, _)) => self.keys.get(&rtxn, id).map_err(|e| e.into()),
+            None => Ok(None),
+        }
+    }
+
+    pub fn delete_api_key(&self, key: impl AsRef<str>) -> Result<bool> {
+        let mut wtxn = self.env.write_txn()?;
+        let existing = match try_split_array_at(key.as_ref().as_bytes()) {
+            Some((id, _)) => {
+                let existing = self.keys.delete(&mut wtxn, id)?;
+                self.delete_key_from_inverted_db(&mut wtxn, id)?;
+                existing
+            }
+            None => false,
+        };
+        wtxn.commit()?;
+
+        Ok(existing)
+    }
+
+    pub fn list_api_keys(&self) -> Result<Vec<Key>> {
+        let mut list = Vec::new();
+        let rtxn = self.env.read_txn()?;
+        for result in self.keys.remap_key_type::<DecodeIgnore>().iter(&rtxn)? {
+            let (_, content) = result?;
+            list.push(content);
+        }
+        list.sort_unstable_by_key(|k| Reverse(k.created_at));
+        Ok(list)
+    }
+
+    pub fn get_expiration_date(
+        &self,
+        key: &[u8],
+        action: Action,
+        index: Option<&[u8]>,
+    ) -> Result<Option<(KeyId, Option<DateTime<Utc>>)>> {
+        let rtxn = self.env.read_txn()?;
+        match try_split_array_at::<_, KEY_ID_LENGTH>(key) {
+            Some((id, _)) => {
+                let tuple = (id, &action, index);
+                Ok(self
+                    .action_keyid_index_expiration
+                    .get(&rtxn, &tuple)?
+                    .map(|expiration| (*id, expiration)))
+            }
+            None => Ok(None),
+        }
+    }
+
+    pub fn prefix_first_expiration_date(
+        &self,
+        key: &[u8],
+        action: Action,
+    ) -> Result<Option<(KeyId, Option<DateTime<Utc>>)>> {
+        let rtxn = self.env.read_txn()?;
+        match try_split_array_at::<_, KEY_ID_LENGTH>(key) {
+            Some((id, _)) => {
+                let tuple = (id, &action, None);
+                Ok(self
+                    .action_keyid_index_expiration
+                    .prefix_iter(&rtxn, &tuple)?
+                    .next()
+                    .transpose()?
+                    .map(|(_, expiration)| (*id, expiration)))
+            }
+            None => Ok(None),
+        }
+    }
+
+    fn delete_key_from_inverted_db(&self, wtxn: &mut RwTxn, key: &KeyId) -> Result<()> {
+        let mut iter = self
+            .action_keyid_index_expiration
+            .remap_types::<ByteSlice, DecodeIgnore>()
+            .prefix_iter_mut(wtxn, key)?;
+        while iter.next().transpose()?.is_some() {
+            // safety: we don't keep references from inside the LMDB database.
+            unsafe { iter.del_current()? };
+        }
+
+        Ok(())
+    }
+}
+
+/// Codec allowing to retrieve the expiration date of an action,
+/// optionnally on a spcific index, for a given key.
+pub struct KeyIdActionCodec;
+
+impl<'a> heed::BytesDecode<'a> for KeyIdActionCodec {
+    type DItem = (KeyId, Action, Option<&'a [u8]>);
+
+    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
+        let (key_id, action_bytes) = try_split_array_at(bytes)?;
+        let (action_bytes, index) = match try_split_array_at(action_bytes)? {
+            (action, []) => (action, None),
+            (action, index) => (action, Some(index)),
+        };
+        let action = Action::from_repr(u8::from_be_bytes(*action_bytes))?;
+
+        Some((*key_id, action, index))
+    }
+}
+
+impl<'a> heed::BytesEncode<'a> for KeyIdActionCodec {
+    type EItem = (&'a KeyId, &'a Action, Option<&'a [u8]>);
+
+    fn bytes_encode((key_id, action, index): &Self::EItem) -> Option<Cow<[u8]>> {
+        let mut bytes = Vec::new();
+
+        bytes.extend_from_slice(*key_id);
+        let action_bytes = u8::to_be_bytes(action.repr());
+        bytes.extend_from_slice(&action_bytes);
+        if let Some(index) = index {
+            bytes.extend_from_slice(index);
+        }
+
+        Some(Cow::Owned(bytes))
+    }
+}
+
+/// Divides one slice into two at an index, returns `None` if mid is out of bounds.
+pub fn try_split_at<T>(slice: &[T], mid: usize) -> Option<(&[T], &[T])> {
+    if mid <= slice.len() {
+        Some(slice.split_at(mid))
+    } else {
+        None
+    }
+}
+
+/// Divides one slice into an array and the tail at an index,
+/// returns `None` if `N` is out of bounds.
+pub fn try_split_array_at<T, const N: usize>(slice: &[T]) -> Option<(&[T; N], &[T])>
+where
+    [T; N]: for<'a> TryFrom<&'a [T]>,
+{
+    let (head, tail) = try_split_at(slice, N)?;
+    let head = head.try_into().ok()?;
+    Some((head, tail))
+}

meilisearch-error/Cargo.toml

@@ -1,8 +1,16 @@
 [package]
 name = "meilisearch-error"
-version = "0.22.0"
+version = "0.25.2"
 authors = ["marin <postma.marin@protonmail.com>"]
 edition = "2018"
 
 [dependencies]
-actix-http = "=3.0.0-beta.6"
+actix-http = "=3.0.0-beta.10"
+actix-web = "4.0.0-beta.9"
+proptest = { version = "1.0.0", optional = true }
+proptest-derive = { version = "0.3.0", optional = true }
+serde = { version = "1.0.130", features = ["derive"] }
+serde_json = "1.0.69"
+
+[features]
+test-traits = ["proptest", "proptest-derive"]

meilisearch-error/src/lib.rs

@@ -1,6 +1,75 @@
 use std::fmt;
 
-use actix_http::http::StatusCode;
+use actix_http::{body::Body, http::StatusCode};
+use actix_web::{self as aweb, HttpResponseBuilder};
+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()")
+    )]
+    code: StatusCode,
+    message: String,
+    #[serde(rename = "code")]
+    error_code: String,
+    #[serde(rename = "type")]
+    error_type: String,
+    #[serde(rename = "link")]
+    error_link: String,
+}
+
+impl ResponseError {
+    pub fn from_msg(message: String, code: Code) -> Self {
+        Self {
+            code: code.http(),
+            message,
+            error_code: code.err_code().error_name.to_string(),
+            error_type: code.type_(),
+            error_link: code.url(),
+        }
+    }
+}
+
+impl fmt::Display for ResponseError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        self.message.fmt(f)
+    }
+}
+
+impl std::error::Error for ResponseError {}
+
+impl<T> From<T> for ResponseError
+where
+    T: ErrorCode,
+{
+    fn from(other: T) -> Self {
+        Self {
+            code: other.http_status(),
+            message: other.to_string(),
+            error_code: other.error_name(),
+            error_type: other.error_type(),
+            error_link: other.error_url(),
+        }
+    }
+}
+
+impl aweb::error::ResponseError for ResponseError {
+    fn error_response(&self) -> aweb::HttpResponse<Body> {
+        let json = serde_json::to_vec(self).unwrap();
+        HttpResponseBuilder::new(self.status_code())
+            .content_type("application/json")
+            .body(json)
+    }
+
+    fn status_code(&self) -> StatusCode {
+        self.code
+    }
+}
 
 pub trait ErrorCode: std::error::Error {
     fn error_code(&self) -> Code;
@@ -38,20 +107,20 @@ impl fmt::Display for ErrorType {
         use ErrorType::*;
 
         match self {
-            InternalError => write!(f, "internal_error"),
-            InvalidRequestError => write!(f, "invalid_request_error"),
-            AuthenticationError => write!(f, "authentication_error"),
+            InternalError => write!(f, "internal"),
+            InvalidRequestError => write!(f, "invalid_request"),
+            AuthenticationError => write!(f, "auth"),
         }
     }
 }
 
+#[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error
     CreateIndex,
     IndexAlreadyExists,
     IndexNotFound,
     InvalidIndexUid,
-    OpenIndex,
 
     // invalid state error
     InvalidState,
@@ -60,18 +129,24 @@ pub enum Code {
 
     MaxFieldsLimitExceeded,
     MissingDocumentId,
+    InvalidDocumentId,
 
-    Facet,
     Filter,
     Sort,
 
     BadParameter,
     BadRequest,
+    DatabaseSizeLimitReached,
     DocumentNotFound,
     Internal,
+    InvalidGeoField,
+    InvalidRankingRule,
+    InvalidStore,
     InvalidToken,
     MissingAuthorizationHeader,
-    NotFound,
+    NoSpaceLeftOnDevice,
+    DumpNotFound,
+    TaskNotFound,
     PayloadTooLarge,
     RetrieveDocument,
     SearchDocuments,
@@ -79,6 +154,18 @@ pub enum Code {
 
     DumpAlreadyInProgress,
     DumpProcessFailed,
+
+    InvalidContentType,
+    MissingContentType,
+    MalformedPayload,
+    MissingPayload,
+
+    ApiKeyNotFound,
+    MissingParameter,
+    InvalidApiKeyActions,
+    InvalidApiKeyIndexes,
+    InvalidApiKeyExpiresAt,
+    InvalidApiKeyDescription,
 }
 
 impl Code {
@@ -89,22 +176,30 @@ impl Code {
         match self {
             // index related errors
             // create index is thrown on internal error while creating an index.
-            CreateIndex => ErrCode::internal("index_creation_failed", StatusCode::BAD_REQUEST),
-            IndexAlreadyExists => ErrCode::invalid("index_already_exists", StatusCode::BAD_REQUEST),
+            CreateIndex => {
+                ErrCode::internal("index_creation_failed", StatusCode::INTERNAL_SERVER_ERROR)
+            }
+            IndexAlreadyExists => ErrCode::invalid("index_already_exists", StatusCode::CONFLICT),
             // thrown when requesting an unexisting index
             IndexNotFound => ErrCode::invalid("index_not_found", StatusCode::NOT_FOUND),
             InvalidIndexUid => ErrCode::invalid("invalid_index_uid", StatusCode::BAD_REQUEST),
-            OpenIndex => {
-                ErrCode::internal("index_not_accessible", StatusCode::INTERNAL_SERVER_ERROR)
-            }
 
             // invalid state error
             InvalidState => ErrCode::internal("invalid_state", StatusCode::INTERNAL_SERVER_ERROR),
             // thrown when no primary key has been set
-            MissingPrimaryKey => ErrCode::invalid("missing_primary_key", StatusCode::BAD_REQUEST),
+            MissingPrimaryKey => {
+                ErrCode::invalid("primary_key_inference_failed", StatusCode::BAD_REQUEST)
+            }
             // error thrown when trying to set an already existing primary key
             PrimaryKeyAlreadyPresent => {
-                ErrCode::invalid("primary_key_already_present", StatusCode::BAD_REQUEST)
+                ErrCode::invalid("index_primary_key_already_exists", StatusCode::BAD_REQUEST)
+            }
+            // invalid ranking rule
+            InvalidRankingRule => ErrCode::invalid("invalid_ranking_rule", StatusCode::BAD_REQUEST),
+
+            // invalid database
+            InvalidStore => {
+                ErrCode::internal("invalid_store_file", StatusCode::INTERNAL_SERVER_ERROR)
             }
 
             // invalid document
@@ -112,9 +207,8 @@ impl Code {
                 ErrCode::invalid("max_fields_limit_exceeded", StatusCode::BAD_REQUEST)
             }
             MissingDocumentId => ErrCode::invalid("missing_document_id", StatusCode::BAD_REQUEST),
+            InvalidDocumentId => ErrCode::invalid("invalid_document_id", StatusCode::BAD_REQUEST),
 
-            // error related to facets
-            Facet => ErrCode::invalid("invalid_facet", StatusCode::BAD_REQUEST),
             // error related to filters
             Filter => ErrCode::invalid("invalid_filter", StatusCode::BAD_REQUEST),
             // error related to sorts
@@ -122,13 +216,22 @@ impl Code {
 
             BadParameter => ErrCode::invalid("bad_parameter", StatusCode::BAD_REQUEST),
             BadRequest => ErrCode::invalid("bad_request", StatusCode::BAD_REQUEST),
+            DatabaseSizeLimitReached => ErrCode::internal(
+                "database_size_limit_reached",
+                StatusCode::INTERNAL_SERVER_ERROR,
+            ),
             DocumentNotFound => ErrCode::invalid("document_not_found", StatusCode::NOT_FOUND),
             Internal => ErrCode::internal("internal", StatusCode::INTERNAL_SERVER_ERROR),
-            InvalidToken => ErrCode::authentication("invalid_token", StatusCode::FORBIDDEN),
+            InvalidGeoField => ErrCode::invalid("invalid_geo_field", StatusCode::BAD_REQUEST),
+            InvalidToken => ErrCode::authentication("invalid_api_key", StatusCode::FORBIDDEN),
             MissingAuthorizationHeader => {
                 ErrCode::authentication("missing_authorization_header", StatusCode::UNAUTHORIZED)
             }
-            NotFound => ErrCode::invalid("not_found", StatusCode::NOT_FOUND),
+            TaskNotFound => ErrCode::invalid("task_not_found", StatusCode::NOT_FOUND),
+            DumpNotFound => ErrCode::invalid("dump_not_found", StatusCode::NOT_FOUND),
+            NoSpaceLeftOnDevice => {
+                ErrCode::internal("no_space_left_on_device", StatusCode::INTERNAL_SERVER_ERROR)
+            }
             PayloadTooLarge => ErrCode::invalid("payload_too_large", StatusCode::PAYLOAD_TOO_LARGE),
             RetrieveDocument => {
                 ErrCode::internal("unretrievable_document", StatusCode::BAD_REQUEST)
@@ -140,11 +243,35 @@ impl Code {
 
             // error related to dump
             DumpAlreadyInProgress => {
-                ErrCode::invalid("dump_already_in_progress", StatusCode::CONFLICT)
+                ErrCode::invalid("dump_already_processing", StatusCode::CONFLICT)
             }
             DumpProcessFailed => {
                 ErrCode::internal("dump_process_failed", StatusCode::INTERNAL_SERVER_ERROR)
             }
+            MissingContentType => {
+                ErrCode::invalid("missing_content_type", StatusCode::UNSUPPORTED_MEDIA_TYPE)
+            }
+            MalformedPayload => ErrCode::invalid("malformed_payload", StatusCode::BAD_REQUEST),
+            InvalidContentType => {
+                ErrCode::invalid("invalid_content_type", StatusCode::UNSUPPORTED_MEDIA_TYPE)
+            }
+            MissingPayload => ErrCode::invalid("missing_payload", StatusCode::BAD_REQUEST),
+
+            // error related to keys
+            ApiKeyNotFound => ErrCode::invalid("api_key_not_found", StatusCode::NOT_FOUND),
+            MissingParameter => ErrCode::invalid("missing_parameter", StatusCode::BAD_REQUEST),
+            InvalidApiKeyActions => {
+                ErrCode::invalid("invalid_api_key_actions", StatusCode::BAD_REQUEST)
+            }
+            InvalidApiKeyIndexes => {
+                ErrCode::invalid("invalid_api_key_indexes", StatusCode::BAD_REQUEST)
+            }
+            InvalidApiKeyExpiresAt => {
+                ErrCode::invalid("invalid_api_key_expires_at", StatusCode::BAD_REQUEST)
+            }
+            InvalidApiKeyDescription => {
+                ErrCode::invalid("invalid_api_key_description", StatusCode::BAD_REQUEST)
+            }
         }
     }
 
@@ -201,3 +328,27 @@ impl ErrCode {
         }
     }
 }
+
+#[cfg(feature = "test-traits")]
+mod strategy {
+    use proptest::strategy::Strategy;
+
+    use super::*;
+
+    pub(super) fn status_code_strategy() -> impl Strategy<Value = StatusCode> {
+        (100..999u16).prop_map(|i| StatusCode::from_u16(i).unwrap())
+    }
+}
+
+#[macro_export]
+macro_rules! internal_error {
+    ($target:ty : $($other:path), *) => {
+        $(
+            impl From<$other> for $target {
+                fn from(other: $other) -> Self {
+                    Self::Internal(Box::new(other))
+                }
+            }
+        )*
+    }
+}

meilisearch-http/Cargo.toml

@@ -4,88 +4,86 @@ description = "MeiliSearch HTTP server"
 edition = "2018"
 license = "MIT"
 name = "meilisearch-http"
-version = "0.22.0"
+version = "0.25.2"
 
 [[bin]]
 name = "meilisearch"
 path = "src/main.rs"
 
 [build-dependencies]
-actix-web-static-files = { git = "https://github.com/MarinPostma/actix-web-static-files.git", rev = "6db8c3e", optional = true }
-anyhow = { version = "*", optional = true }
-cargo_toml = { version = "0.9.0", optional = true }
+actix-web-static-files = { git = "https://github.com/MarinPostma/actix-web-static-files.git", rev = "39d8006", optional = true }
+anyhow = { version = "1.0.43", optional = true }
+cargo_toml = { version = "0.9", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.3", features = ["blocking", "rustls-tls"], default-features = false, optional = true }
-sha-1 = { version = "0.9.4", optional = true }
-tempfile = { version = "3.1.0", optional = true }
+reqwest = { version = "0.11.4", features = ["blocking", "rustls-tls"], default-features = false, optional = true }
+sha-1 = { version = "0.9.8", optional = true }
+tempfile = { version = "3.2.0", optional = true }
 vergen = { version = "5.1.15", default-features = false, features = ["git"] }
-zip = { version = "0.5.12", optional = true }
+zip = { version = "0.5.13", optional = true }
 
 [dependencies]
-actix-cors = { git = "https://github.com/MarinPostma/actix-extras.git", rev = "2dac1a4"}
-actix-http = { version = "=3.0.0-beta.6" }
-actix-service = "2.0.0"
-actix-web = { version = "=4.0.0-beta.6", features = ["rustls"] }
-actix-web-static-files = { git = "https://github.com/MarinPostma/actix-web-static-files.git", rev = "6db8c3e", optional = true }
-anyhow = "1.0.36"
-async-stream = "0.3.0"
-async-trait = "0.1.42"
-arc-swap = "1.2.0"
-byte-unit = { version = "4.0.9", default-features = false, features = ["std"] }
-bytes = "0.6.0"
+actix-cors = { git = "https://github.com/MarinPostma/actix-extras.git", rev = "963ac94d" }
+actix-web = { version = "4.0.0-beta.9", features = ["rustls"] }
+actix-web-static-files = { git = "https://github.com/MarinPostma/actix-web-static-files.git", rev = "39d8006", optional = true }
+# TODO: specifying this dependency so semver doesn't bump to next beta
+actix-tls = "=3.0.0-beta.5"
+anyhow = { version = "1.0.43", features = ["backtrace"] }
+arc-swap = "1.3.2"
+async-stream = "0.3.2"
+async-trait = "0.1.51"
+bstr = "0.2.17"
+byte-unit = { version = "4.0.12", default-features = false, features = ["std"] }
+bytes = "1.1.0"
 chrono = { version = "0.4.19", features = ["serde"] }
-crossbeam-channel = "0.5.0"
+crossbeam-channel = "0.5.1"
 either = "1.6.1"
-env_logger = "0.8.2"
-flate2 = "1.0.19"
-fst = "0.4.5"
-futures = "0.3.7"
-futures-util = "0.3.8"
+env_logger = "0.9.0"
+flate2 = "1.0.21"
+fst = "0.4.7"
+futures = "0.3.17"
+futures-util = "0.3.17"
 heed = { git = "https://github.com/Kerollmops/heed", tag = "v0.12.1" }
-http = "0.2.1"
-indexmap = { version = "1.3.2", features = ["serde-1"] }
-itertools = "0.10.0"
-log = "0.4.8"
-main_error = "0.1.0"
+http = "0.2.4"
+indexmap = { version = "1.7.0", features = ["serde-1"] }
+itertools = "0.10.1"
+log = "0.4.14"
+meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-error = { path = "../meilisearch-error" }
-meilisearch-tokenizer = { git = "https://github.com/meilisearch/tokenizer.git", tag = "v0.2.5" }
-memmap = "0.7.0"
-milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.13.1" }
+meilisearch-lib = { path = "../meilisearch-lib" }
 mime = "0.3.16"
 num_cpus = "1.13.0"
-once_cell = "1.5.2"
-parking_lot = "0.11.1"
-rand = "0.7.3"
-rayon = "1.5.0"
-regex = "1.4.2"
-rustls = "0.19"
-serde = { version = "1.0", features = ["derive"] }
-serde_json = { version = "1.0.59", features = ["preserve_order"] }
-sha2 = "0.9.1"
-siphasher = "0.3.2"
-slice-group-by = "0.2.6"
-structopt = "0.3.20"
-tar = "0.4.29"
-tempfile = "3.1.0"
-thiserror = "1.0.24"
-tokio = { version = "1", features = ["full"] }
-uuid = { version =  "0.8.2", features = ["serde"] }
-walkdir = "2.3.2"
 obkv = "0.2.0"
-pin-project = "1.0.7"
-whoami = { version = "1.1.2", optional = true }
-reqwest = { version = "0.11.3", features = ["json", "rustls-tls"], default-features = false, optional = true }
-serdeval = "0.1.0"
-sysinfo = "0.20.0"
+once_cell = "1.8.0"
+parking_lot = "0.11.2"
+pin-project = "1.0.8"
+platform-dirs = "0.3.0"
+rand = "0.8.4"
+rayon = "1.5.1"
+regex = "1.5.4"
+rustls = "0.19.1"
+segment = { version = "0.1.2", optional = true }
+serde = { version = "1.0.130", features = ["derive"] }
+serde_json = { version = "1.0.67", features = ["preserve_order"] }
+sha2 = "0.9.6"
+siphasher = "0.3.7"
+slice-group-by = "0.2.6"
+structopt = "0.3.25"
+sysinfo = "0.20.2"
+tar = "0.4.37"
+tempfile = "3.2.0"
+thiserror = "1.0.28"
+tokio = { version = "1.11.0", features = ["full"] }
+tokio-stream = "0.1.7"
+uuid = { version = "0.8.2", features = ["serde"] }
+walkdir = "2.3.2"
 
 [dev-dependencies]
-actix-rt = "2.1.0"
-assert-json-diff = { branch = "master", git = "https://github.com/qdequele/assert-json-diff" }
-mockall = "0.9.1"
+actix-rt = "2.2.0"
+assert-json-diff = "2.0.1"
+maplit = "1.0.2"
 paste = "1.0.5"
 serde_url_params = "0.2.1"
-tempdir = "0.3.7"
-urlencoding = "1.1.1"
+urlencoding = "2.1.0"
 
 [features]
 mini-dashboard = [
@@ -98,12 +96,12 @@ mini-dashboard = [
     "tempfile",
     "zip",
 ]
-analytics = ["whoami", "reqwest"]
+analytics = ["segment"]
 default = ["analytics", "mini-dashboard"]
 
 [target.'cfg(target_os = "linux")'.dependencies]
-jemallocator = "0.3.2"
+tikv-jemallocator = "0.4.1"
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.1.4/build.zip"
-sha1 = "750e8a8e56cfa61fbf9ead14b08a5f17ad3f3d37"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.1.7/build.zip"
+sha1 = "e2feedf271917c4b7b88998eff5aaaea1d3925b9"

meilisearch-http/src/analytics.rs

@@ -1,126 +0,0 @@
-use std::hash::{Hash, Hasher};
-use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
-
-use log::debug;
-use serde::Serialize;
-use siphasher::sip::SipHasher;
-
-use crate::Data;
-use crate::Opt;
-
-const AMPLITUDE_API_KEY: &str = "f7fba398780e06d8fe6666a9be7e3d47";
-
-#[derive(Debug, Serialize)]
-struct EventProperties {
-    database_size: u64,
-    last_update_timestamp: Option<i64>, //timestamp
-    number_of_documents: Vec<u64>,
-}
-
-impl EventProperties {
-    async fn from(data: Data) -> anyhow::Result<EventProperties> {
-        let stats = data.index_controller.get_all_stats().await?;
-
-        let database_size = stats.database_size;
-        let last_update_timestamp = stats.last_update.map(|u| u.timestamp());
-        let number_of_documents = stats
-            .indexes
-            .values()
-            .map(|index| index.number_of_documents)
-            .collect();
-
-        Ok(EventProperties {
-            database_size,
-            last_update_timestamp,
-            number_of_documents,
-        })
-    }
-}
-
-#[derive(Debug, Serialize)]
-struct UserProperties<'a> {
-    env: &'a str,
-    start_since_days: u64,
-    user_email: Option<String>,
-    server_provider: Option<String>,
-}
-
-#[derive(Debug, Serialize)]
-struct Event<'a> {
-    user_id: &'a str,
-    event_type: &'a str,
-    device_id: &'a str,
-    time: u64,
-    app_version: &'a str,
-    user_properties: UserProperties<'a>,
-    event_properties: Option<EventProperties>,
-}
-
-#[derive(Debug, Serialize)]
-struct AmplitudeRequest<'a> {
-    api_key: &'a str,
-    events: Vec<Event<'a>>,
-}
-
-pub async fn analytics_sender(data: Data, opt: Opt) {
-    let username = whoami::username();
-    let hostname = whoami::hostname();
-    let platform = whoami::platform();
-
-    let uid = username + &hostname + &platform.to_string();
-
-    let mut hasher = SipHasher::new();
-    uid.hash(&mut hasher);
-    let hash = hasher.finish();
-
-    let uid = format!("{:X}", hash);
-    let platform = platform.to_string();
-    let first_start = Instant::now();
-
-    loop {
-        let n = SystemTime::now().duration_since(UNIX_EPOCH).unwrap();
-        let user_id = &uid;
-        let device_id = &platform;
-        let time = n.as_secs();
-        let event_type = "runtime_tick";
-        let elapsed_since_start = first_start.elapsed().as_secs() / 86_400; // One day
-        let event_properties = EventProperties::from(data.clone()).await.ok();
-        let app_version = env!("CARGO_PKG_VERSION").to_string();
-        let app_version = app_version.as_str();
-        let user_email = std::env::var("MEILI_USER_EMAIL").ok();
-        let server_provider = std::env::var("MEILI_SERVER_PROVIDER").ok();
-        let user_properties = UserProperties {
-            env: &opt.env,
-            start_since_days: elapsed_since_start,
-            user_email,
-            server_provider,
-        };
-
-        let event = Event {
-            user_id,
-            event_type,
-            device_id,
-            time,
-            app_version,
-            user_properties,
-            event_properties,
-        };
-
-        let request = AmplitudeRequest {
-            api_key: AMPLITUDE_API_KEY,
-            events: vec![event],
-        };
-
-        let response = reqwest::Client::new()
-            .post("https://api2.amplitude.com/2/httpapi")
-            .timeout(Duration::from_secs(60)) // 1 minute max
-            .json(&request)
-            .send()
-            .await;
-        if let Err(e) = response {
-            debug!("Unsuccessful call to Amplitude: {}", e);
-        }
-
-        tokio::time::sleep(Duration::from_secs(3600)).await;
-    }
-}

meilisearch-http/src/analytics/mock_analytics.rs

@@ -0,0 +1,51 @@
+use std::{any::Any, sync::Arc};
+
+use actix_web::HttpRequest;
+use serde_json::Value;
+
+use crate::{routes::indexes::documents::UpdateDocumentsQuery, Opt};
+
+use super::{find_user_id, Analytics};
+
+pub struct MockAnalytics;
+
+#[derive(Default)]
+pub struct SearchAggregator {}
+
+#[allow(dead_code)]
+impl SearchAggregator {
+    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
+        Self::default()
+    }
+
+    pub fn succeed(&mut self, _: &dyn Any) {}
+}
+
+impl MockAnalytics {
+    #[allow(clippy::new_ret_no_self)]
+    pub fn new(opt: &Opt) -> (Arc<dyn Analytics>, String) {
+        let user = find_user_id(&opt.db_path).unwrap_or_default();
+        (Arc::new(Self), user)
+    }
+}
+
+impl Analytics for MockAnalytics {
+    // These methods are noop and should be optimized out
+    fn publish(&self, _event_name: String, _send: Value, _request: Option<&HttpRequest>) {}
+    fn get_search(&self, _aggregate: super::SearchAggregator) {}
+    fn post_search(&self, _aggregate: super::SearchAggregator) {}
+    fn add_documents(
+        &self,
+        _documents_query: &UpdateDocumentsQuery,
+        _index_creation: bool,
+        _request: &HttpRequest,
+    ) {
+    }
+    fn update_documents(
+        &self,
+        _documents_query: &UpdateDocumentsQuery,
+        _index_creation: bool,
+        _request: &HttpRequest,
+    ) {
+    }
+}

meilisearch-http/src/analytics/mod.rs

@@ -0,0 +1,84 @@
+mod mock_analytics;
+// if we are in release mode and the feature analytics was enabled
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+mod segment_analytics;
+
+use std::fs;
+use std::path::{Path, PathBuf};
+
+use actix_web::HttpRequest;
+use once_cell::sync::Lazy;
+use platform_dirs::AppDirs;
+use serde_json::Value;
+
+use crate::routes::indexes::documents::UpdateDocumentsQuery;
+
+pub use mock_analytics::MockAnalytics;
+
+// if we are in debug mode OR the analytics feature is disabled
+// the `SegmentAnalytics` point to the mock instead of the real analytics
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
+pub type SegmentAnalytics = mock_analytics::MockAnalytics;
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
+pub type SearchAggregator = mock_analytics::SearchAggregator;
+
+// if we are in release mode and the feature analytics was enabled
+// we use the real analytics
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+pub type SearchAggregator = segment_analytics::SearchAggregator;
+
+/// The MeiliSearch config dir:
+/// `~/.config/MeiliSearch` on *NIX or *BSD.
+/// `~/Library/ApplicationSupport` on macOS.
+/// `%APPDATA` (= `C:\Users%USERNAME%\AppData\Roaming`) on windows.
+static MEILISEARCH_CONFIG_PATH: Lazy<Option<PathBuf>> =
+    Lazy::new(|| AppDirs::new(Some("MeiliSearch"), false).map(|appdir| appdir.config_dir));
+
+fn config_user_id_path(db_path: &Path) -> Option<PathBuf> {
+    db_path
+        .canonicalize()
+        .ok()
+        .map(|path| {
+            path.join("instance-uid")
+                .display()
+                .to_string()
+                .replace("/", "-")
+        })
+        .zip(MEILISEARCH_CONFIG_PATH.as_ref())
+        .map(|(filename, config_path)| config_path.join(filename.trim_start_matches('-')))
+}
+
+/// Look for the instance-uid in the `data.ms` or in `~/.config/MeiliSearch/path-to-db-instance-uid`
+fn find_user_id(db_path: &Path) -> Option<String> {
+    fs::read_to_string(db_path.join("instance-uid"))
+        .ok()
+        .or_else(|| fs::read_to_string(&config_user_id_path(db_path)?).ok())
+}
+
+pub trait Analytics: Sync + Send {
+    /// The method used to publish most analytics that do not need to be batched every hours
+    fn publish(&self, event_name: String, send: Value, request: Option<&HttpRequest>);
+
+    /// This method should be called to aggergate a get search
+    fn get_search(&self, aggregate: SearchAggregator);
+
+    /// This method should be called to aggregate a post search
+    fn post_search(&self, aggregate: SearchAggregator);
+
+    // this method should be called to aggregate a add documents request
+    fn add_documents(
+        &self,
+        documents_query: &UpdateDocumentsQuery,
+        index_creation: bool,
+        request: &HttpRequest,
+    );
+    // this method should be called to batch a update documents request
+    fn update_documents(
+        &self,
+        documents_query: &UpdateDocumentsQuery,
+        index_creation: bool,
+        request: &HttpRequest,
+    );
+}

meilisearch-http/src/analytics/segment_analytics.rs

@@ -0,0 +1,547 @@
+use std::collections::{BinaryHeap, HashMap, HashSet};
+use std::fs;
+use std::path::Path;
+use std::sync::Arc;
+use std::time::{Duration, Instant};
+
+use actix_web::http::header::USER_AGENT;
+use actix_web::HttpRequest;
+use http::header::CONTENT_TYPE;
+use meilisearch_lib::index::{SearchQuery, SearchResult};
+use meilisearch_lib::index_controller::Stats;
+use meilisearch_lib::MeiliSearch;
+use once_cell::sync::Lazy;
+use regex::Regex;
+use segment::message::{Identify, Track, User};
+use segment::{AutoBatcher, Batcher, HttpClient};
+use serde_json::{json, Value};
+use sysinfo::{DiskExt, System, SystemExt};
+use tokio::select;
+use tokio::sync::mpsc::{self, Receiver, Sender};
+use uuid::Uuid;
+
+use crate::analytics::Analytics;
+use crate::routes::indexes::documents::UpdateDocumentsQuery;
+use crate::Opt;
+
+use super::{config_user_id_path, MEILISEARCH_CONFIG_PATH};
+
+/// Write the instance-uid in the `data.ms` and in `~/.config/MeiliSearch/path-to-db-instance-uid`. Ignore the errors.
+fn write_user_id(db_path: &Path, user_id: &str) {
+    let _ = fs::write(db_path.join("instance-uid"), user_id.as_bytes());
+    if let Some((meilisearch_config_path, user_id_path)) = MEILISEARCH_CONFIG_PATH
+        .as_ref()
+        .zip(config_user_id_path(db_path))
+    {
+        let _ = fs::create_dir_all(&meilisearch_config_path);
+        let _ = fs::write(user_id_path, user_id.as_bytes());
+    }
+}
+
+const SEGMENT_API_KEY: &str = "P3FWhhEsJiEDCuEHpmcN9DHcK4hVfBvb";
+
+pub fn extract_user_agents(request: &HttpRequest) -> Vec<String> {
+    request
+        .headers()
+        .get(USER_AGENT)
+        .map(|header| header.to_str().ok())
+        .flatten()
+        .unwrap_or("unknown")
+        .split(';')
+        .map(str::trim)
+        .map(ToString::to_string)
+        .collect()
+}
+
+pub enum AnalyticsMsg {
+    BatchMessage(Track),
+    AggregateGetSearch(SearchAggregator),
+    AggregatePostSearch(SearchAggregator),
+    AggregateAddDocuments(DocumentsAggregator),
+    AggregateUpdateDocuments(DocumentsAggregator),
+}
+
+pub struct SegmentAnalytics {
+    sender: Sender<AnalyticsMsg>,
+    user: User,
+}
+
+impl SegmentAnalytics {
+    pub async fn new(opt: &Opt, meilisearch: &MeiliSearch) -> (Arc<dyn Analytics>, String) {
+        let user_id = super::find_user_id(&opt.db_path);
+        let first_time_run = user_id.is_none();
+        let user_id = user_id.unwrap_or_else(|| Uuid::new_v4().to_string());
+        write_user_id(&opt.db_path, &user_id);
+
+        let client = HttpClient::default();
+        let user = User::UserId { user_id };
+        let mut batcher = AutoBatcher::new(client, Batcher::new(None), SEGMENT_API_KEY.to_string());
+
+        // If MeiliSearch is Launched for the first time:
+        // 1. Send an event Launched associated to the user `total_launch`.
+        // 2. Batch an event Launched with the real instance-id and send it in one hour.
+        if first_time_run {
+            let _ = batcher
+                .push(Track {
+                    user: User::UserId {
+                        user_id: "total_launch".to_string(),
+                    },
+                    event: "Launched".to_string(),
+                    ..Default::default()
+                })
+                .await;
+            let _ = batcher.flush().await;
+            let _ = batcher
+                .push(Track {
+                    user: user.clone(),
+                    event: "Launched".to_string(),
+                    ..Default::default()
+                })
+                .await;
+        }
+
+        let (sender, inbox) = mpsc::channel(100); // How many analytics can we bufferize
+
+        let segment = Box::new(Segment {
+            inbox,
+            user: user.clone(),
+            opt: opt.clone(),
+            batcher,
+            post_search_aggregator: SearchAggregator::default(),
+            get_search_aggregator: SearchAggregator::default(),
+            add_documents_aggregator: DocumentsAggregator::default(),
+            update_documents_aggregator: DocumentsAggregator::default(),
+        });
+        tokio::spawn(segment.run(meilisearch.clone()));
+
+        let this = Self {
+            sender,
+            user: user.clone(),
+        };
+
+        (Arc::new(this), user.to_string())
+    }
+}
+
+impl super::Analytics for SegmentAnalytics {
+    fn publish(&self, event_name: String, mut send: Value, request: Option<&HttpRequest>) {
+        let user_agent = request
+            .map(|req| req.headers().get(USER_AGENT))
+            .flatten()
+            .map(|header| header.to_str().unwrap_or("unknown"))
+            .map(|s| s.split(';').map(str::trim).collect::<Vec<&str>>());
+
+        send["user-agent"] = json!(user_agent);
+        let event = Track {
+            user: self.user.clone(),
+            event: event_name.clone(),
+            properties: send,
+            ..Default::default()
+        };
+        let _ = self
+            .sender
+            .try_send(AnalyticsMsg::BatchMessage(event.into()));
+    }
+
+    fn get_search(&self, aggregate: SearchAggregator) {
+        let _ = self
+            .sender
+            .try_send(AnalyticsMsg::AggregateGetSearch(aggregate));
+    }
+
+    fn post_search(&self, aggregate: SearchAggregator) {
+        let _ = self
+            .sender
+            .try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
+    }
+
+    fn add_documents(
+        &self,
+        documents_query: &UpdateDocumentsQuery,
+        index_creation: bool,
+        request: &HttpRequest,
+    ) {
+        let aggregate = DocumentsAggregator::from_query(documents_query, index_creation, request);
+        let _ = self
+            .sender
+            .try_send(AnalyticsMsg::AggregateAddDocuments(aggregate));
+    }
+
+    fn update_documents(
+        &self,
+        documents_query: &UpdateDocumentsQuery,
+        index_creation: bool,
+        request: &HttpRequest,
+    ) {
+        let aggregate = DocumentsAggregator::from_query(documents_query, index_creation, request);
+        let _ = self
+            .sender
+            .try_send(AnalyticsMsg::AggregateUpdateDocuments(aggregate));
+    }
+}
+
+pub struct Segment {
+    inbox: Receiver<AnalyticsMsg>,
+    user: User,
+    opt: Opt,
+    batcher: AutoBatcher,
+    get_search_aggregator: SearchAggregator,
+    post_search_aggregator: SearchAggregator,
+    add_documents_aggregator: DocumentsAggregator,
+    update_documents_aggregator: DocumentsAggregator,
+}
+
+impl Segment {
+    fn compute_traits(opt: &Opt, stats: Stats) -> Value {
+        static FIRST_START_TIMESTAMP: Lazy<Instant> = Lazy::new(Instant::now);
+        static SYSTEM: Lazy<Value> = Lazy::new(|| {
+            let mut sys = System::new_all();
+            sys.refresh_all();
+            let kernel_version = sys
+                .kernel_version()
+                .map(|k| k.split_once("-").map(|(k, _)| k.to_string()))
+                .flatten();
+            json!({
+                    "distribution": sys.name(),
+                    "kernel_version": kernel_version,
+                    "cores": sys.processors().len(),
+                    "ram_size": sys.total_memory(),
+                    "disk_size": sys.disks().iter().map(|disk| disk.total_space()).max(),
+                    "server_provider": std::env::var("MEILI_SERVER_PROVIDER").ok(),
+            })
+        });
+        let infos = json!({
+            "env": opt.env.clone(),
+            "has_snapshot": opt.schedule_snapshot,
+        });
+
+        let number_of_documents = stats
+            .indexes
+            .values()
+            .map(|index| index.number_of_documents)
+            .collect::<Vec<u64>>();
+
+        json!({
+            "start_since_days": FIRST_START_TIMESTAMP.elapsed().as_secs() / (60 * 60 * 24), // one day
+            "system": *SYSTEM,
+            "stats": {
+                "database_size": stats.database_size,
+                "indexes_number": stats.indexes.len(),
+                "documents_number": number_of_documents,
+            },
+            "infos": infos,
+        })
+    }
+
+    async fn run(mut self, meilisearch: MeiliSearch) {
+        const INTERVAL: Duration = Duration::from_secs(60 * 60); // one hour
+                                                                 // The first batch must be sent after one hour.
+        let mut interval =
+            tokio::time::interval_at(tokio::time::Instant::now() + INTERVAL, INTERVAL);
+
+        loop {
+            select! {
+                _ = interval.tick() => {
+                    self.tick(meilisearch.clone()).await;
+                },
+                msg = self.inbox.recv() => {
+                    match msg {
+                        Some(AnalyticsMsg::BatchMessage(msg)) => drop(self.batcher.push(msg).await),
+                        Some(AnalyticsMsg::AggregateGetSearch(agreg)) => self.get_search_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregatePostSearch(agreg)) => self.post_search_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
+                        None => (),
+                    }
+                }
+            }
+        }
+    }
+
+    async fn tick(&mut self, meilisearch: MeiliSearch) {
+        if let Ok(stats) = meilisearch.get_all_stats(&None).await {
+            let _ = self
+                .batcher
+                .push(Identify {
+                    context: Some(json!({
+                        "app": {
+                            "version": env!("CARGO_PKG_VERSION").to_string(),
+                        },
+                    })),
+                    user: self.user.clone(),
+                    traits: Self::compute_traits(&self.opt, stats),
+                    ..Default::default()
+                })
+                .await;
+        }
+        let get_search = std::mem::take(&mut self.get_search_aggregator)
+            .into_event(&self.user, "Documents Searched GET");
+        let post_search = std::mem::take(&mut self.post_search_aggregator)
+            .into_event(&self.user, "Documents Searched POST");
+        let add_documents = std::mem::take(&mut self.add_documents_aggregator)
+            .into_event(&self.user, "Documents Added");
+        let update_documents = std::mem::take(&mut self.update_documents_aggregator)
+            .into_event(&self.user, "Documents Updated");
+
+        if let Some(get_search) = get_search {
+            let _ = self.batcher.push(get_search).await;
+        }
+        if let Some(post_search) = post_search {
+            let _ = self.batcher.push(post_search).await;
+        }
+        if let Some(add_documents) = add_documents {
+            let _ = self.batcher.push(add_documents).await;
+        }
+        if let Some(update_documents) = update_documents {
+            let _ = self.batcher.push(update_documents).await;
+        }
+        let _ = self.batcher.flush().await;
+    }
+}
+
+#[derive(Default)]
+pub struct SearchAggregator {
+    // context
+    user_agents: HashSet<String>,
+
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // sort
+    sort_with_geo_point: bool,
+    // everytime a request has a filter, this field must be incremented by the number of terms it contains
+    sort_sum_of_criteria_terms: usize,
+    // everytime a request has a filter, this field must be incremented by one
+    sort_total_number_of_criteria: usize,
+
+    // filter
+    filter_with_geo_radius: bool,
+    // everytime a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // everytime a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // q
+    // The maximum number of terms in a q request
+    max_terms_number: usize,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+}
+
+impl SearchAggregator {
+    pub fn from_query(query: &SearchQuery, request: &HttpRequest) -> Self {
+        let mut ret = Self::default();
+        ret.total_received = 1;
+        ret.user_agents = extract_user_agents(request).into_iter().collect();
+
+        if let Some(ref sort) = query.sort {
+            ret.sort_total_number_of_criteria = 1;
+            ret.sort_with_geo_point = sort.iter().any(|s| s.contains("_geoPoint("));
+            ret.sort_sum_of_criteria_terms = sort.len();
+        }
+
+        if let Some(ref filter) = query.filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values
+                        .iter()
+                        .map(|v| v.to_string())
+                        .any(|s| RE.is_match(&s))
+                    {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        if let Some(ref q) = query.q {
+            ret.max_terms_number = q.split_whitespace().count();
+        }
+
+        ret.max_limit = query.limit;
+        ret.max_offset = query.offset.unwrap_or_default();
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SearchResult) {
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+        self.time_spent.push(result.processing_time_ms as usize);
+    }
+
+    /// Aggregate one [SearchAggregator] into another.
+    pub fn aggregate(&mut self, mut other: Self) {
+        // context
+        for user_agent in other.user_agents.into_iter() {
+            self.user_agents.insert(user_agent);
+        }
+        // request
+        self.total_received = self.total_received.saturating_add(other.total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(other.total_succeeded);
+        self.time_spent.append(&mut other.time_spent);
+        // sort
+        self.sort_with_geo_point |= other.sort_with_geo_point;
+        self.sort_sum_of_criteria_terms = self
+            .sort_sum_of_criteria_terms
+            .saturating_add(other.sort_sum_of_criteria_terms);
+        self.sort_total_number_of_criteria = self
+            .sort_total_number_of_criteria
+            .saturating_add(other.sort_total_number_of_criteria);
+        // filter
+        self.filter_with_geo_radius |= other.filter_with_geo_radius;
+        self.filter_sum_of_criteria_terms = self
+            .filter_sum_of_criteria_terms
+            .saturating_add(other.filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria = self
+            .filter_total_number_of_criteria
+            .saturating_add(other.filter_total_number_of_criteria);
+        for (key, value) in other.used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+        // q
+        self.max_terms_number = self.max_terms_number.max(other.max_terms_number);
+        // pagination
+        self.max_limit = self.max_limit.max(other.max_limit);
+        self.max_offset = self.max_offset.max(other.max_offset);
+    }
+
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
+        if self.total_received == 0 {
+            None
+        } else {
+            // the index of the 99th percentage of value
+            let percentile_99th = 0.99 * (self.total_succeeded as f64 - 1.) + 1.;
+            // we get all the values in a sorted manner
+            let time_spent = self.time_spent.into_sorted_vec();
+            // We are only intersted by the slowest value of the 99th fastest results
+            let time_spent = time_spent.get(percentile_99th as usize);
+
+            let properties = json!({
+                "user-agent": self.user_agents,
+                "requests": {
+                    "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
+                    "total_succeeded": self.total_succeeded,
+                    "total_failed": self.total_received.saturating_sub(self.total_succeeded), // just to be sure we never panics
+                    "total_received": self.total_received,
+                },
+                "sort": {
+                    "with_geoPoint": self.sort_with_geo_point,
+                    "avg_criteria_number": format!("{:.2}", self.sort_sum_of_criteria_terms as f64 / self.sort_total_number_of_criteria as f64),
+                },
+                "filter": {
+                   "with_geoRadius": self.filter_with_geo_radius,
+                   "avg_criteria_number": format!("{:.2}", self.filter_sum_of_criteria_terms as f64 / self.filter_total_number_of_criteria as f64),
+                   "most_used_syntax": self.used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+                },
+                "q": {
+                   "max_terms_number": self.max_terms_number,
+                },
+                "pagination": {
+                   "max_limit": self.max_limit,
+                   "max_offset": self.max_offset,
+                },
+            });
+
+            Some(Track {
+                user: user.clone(),
+                event: event_name.to_string(),
+                properties,
+                ..Default::default()
+            })
+        }
+    }
+}
+
+#[derive(Default)]
+pub struct DocumentsAggregator {
+    // set to true when at least one request was received
+    updated: bool,
+
+    // context
+    user_agents: HashSet<String>,
+
+    content_types: HashSet<String>,
+    primary_keys: HashSet<String>,
+    index_creation: bool,
+}
+
+impl DocumentsAggregator {
+    pub fn from_query(
+        documents_query: &UpdateDocumentsQuery,
+        index_creation: bool,
+        request: &HttpRequest,
+    ) -> Self {
+        let mut ret = Self::default();
+
+        ret.updated = true;
+        ret.user_agents = extract_user_agents(request).into_iter().collect();
+        if let Some(primary_key) = documents_query.primary_key.clone() {
+            ret.primary_keys.insert(primary_key);
+        }
+        let content_type = request
+            .headers()
+            .get(CONTENT_TYPE)
+            .map(|s| s.to_str().unwrap_or("unkown"))
+            .unwrap()
+            .to_string();
+        ret.content_types.insert(content_type);
+        ret.index_creation = index_creation;
+
+        ret
+    }
+
+    /// Aggregate one [DocumentsAggregator] into another.
+    pub fn aggregate(&mut self, other: Self) {
+        self.updated |= other.updated;
+        // we can't create a union because there is no `into_union` method
+        for user_agent in other.user_agents.into_iter() {
+            self.user_agents.insert(user_agent);
+        }
+        for primary_key in other.primary_keys.into_iter() {
+            self.primary_keys.insert(primary_key);
+        }
+        for content_type in other.content_types.into_iter() {
+            self.content_types.insert(content_type);
+        }
+        self.index_creation |= other.index_creation;
+    }
+
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
+        if !self.updated {
+            None
+        } else {
+            let properties = json!({
+                "user-agent": self.user_agents,
+                "payload_type": self.content_types,
+                "primary_key": self.primary_keys,
+                "index_creation": self.index_creation,
+            });
+
+            Some(Track {
+                user: user.clone(),
+                event: event_name.to_string(),
+                properties,
+                ..Default::default()
+            })
+        }
+    }
+}

meilisearch-http/src/data/mod.rs

@@ -1,133 +0,0 @@
-use std::ops::Deref;
-use std::sync::Arc;
-
-use sha2::Digest;
-
-use crate::index::{Checked, Settings};
-use crate::index_controller::{
-    error::Result, DumpInfo, IndexController, IndexMetadata, IndexSettings, IndexStats, Stats,
-};
-use crate::option::Opt;
-
-pub mod search;
-mod updates;
-
-#[derive(Clone)]
-pub struct Data {
-    inner: Arc<DataInner>,
-}
-
-impl Deref for Data {
-    type Target = DataInner;
-
-    fn deref(&self) -> &Self::Target {
-        &self.inner
-    }
-}
-
-pub struct DataInner {
-    pub index_controller: IndexController,
-    pub api_keys: ApiKeys,
-    options: Opt,
-}
-
-#[derive(Clone)]
-pub struct ApiKeys {
-    pub public: Option<String>,
-    pub private: Option<String>,
-    pub master: Option<String>,
-}
-
-impl ApiKeys {
-    pub fn generate_missing_api_keys(&mut self) {
-        if let Some(master_key) = &self.master {
-            if self.private.is_none() {
-                let key = format!("{}-private", master_key);
-                let sha = sha2::Sha256::digest(key.as_bytes());
-                self.private = Some(format!("{:x}", sha));
-            }
-            if self.public.is_none() {
-                let key = format!("{}-public", master_key);
-                let sha = sha2::Sha256::digest(key.as_bytes());
-                self.public = Some(format!("{:x}", sha));
-            }
-        }
-    }
-}
-
-impl Data {
-    pub fn new(options: Opt) -> anyhow::Result<Data> {
-        let path = options.db_path.clone();
-
-        let index_controller = IndexController::new(&path, &options)?;
-
-        let mut api_keys = ApiKeys {
-            master: options.clone().master_key,
-            private: None,
-            public: None,
-        };
-
-        api_keys.generate_missing_api_keys();
-
-        let inner = DataInner {
-            index_controller,
-            api_keys,
-            options,
-        };
-        let inner = Arc::new(inner);
-
-        Ok(Data { inner })
-    }
-
-    pub async fn settings(&self, uid: String) -> Result<Settings<Checked>> {
-        self.index_controller.settings(uid).await
-    }
-
-    pub async fn list_indexes(&self) -> Result<Vec<IndexMetadata>> {
-        self.index_controller.list_indexes().await
-    }
-
-    pub async fn index(&self, uid: String) -> Result<IndexMetadata> {
-        self.index_controller.get_index(uid).await
-    }
-
-    pub async fn create_index(
-        &self,
-        uid: String,
-        primary_key: Option<String>,
-    ) -> Result<IndexMetadata> {
-        let settings = IndexSettings {
-            uid: Some(uid),
-            primary_key,
-        };
-
-        let meta = self.index_controller.create_index(settings).await?;
-        Ok(meta)
-    }
-
-    pub async fn get_index_stats(&self, uid: String) -> Result<IndexStats> {
-        Ok(self.index_controller.get_index_stats(uid).await?)
-    }
-
-    pub async fn get_all_stats(&self) -> Result<Stats> {
-        Ok(self.index_controller.get_all_stats().await?)
-    }
-
-    pub async fn create_dump(&self) -> Result<DumpInfo> {
-        Ok(self.index_controller.create_dump().await?)
-    }
-
-    pub async fn dump_status(&self, uid: String) -> Result<DumpInfo> {
-        Ok(self.index_controller.dump_info(uid).await?)
-    }
-
-    #[inline]
-    pub fn http_payload_size_limit(&self) -> usize {
-        self.options.http_payload_size_limit.get_bytes() as usize
-    }
-
-    #[inline]
-    pub fn api_keys(&self) -> &ApiKeys {
-        &self.api_keys
-    }
-}

meilisearch-http/src/data/search.rs

@@ -1,34 +0,0 @@
-use serde_json::{Map, Value};
-
-use super::Data;
-use crate::index::{SearchQuery, SearchResult};
-use crate::index_controller::error::Result;
-
-impl Data {
-    pub async fn search(&self, index: String, search_query: SearchQuery) -> Result<SearchResult> {
-        self.index_controller.search(index, search_query).await
-    }
-
-    pub async fn retrieve_documents(
-        &self,
-        index: String,
-        offset: usize,
-        limit: usize,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Vec<Map<String, Value>>> {
-        self.index_controller
-            .documents(index, offset, limit, attributes_to_retrieve)
-            .await
-    }
-
-    pub async fn retrieve_document(
-        &self,
-        index: String,
-        document_id: String,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Map<String, Value>> {
-        self.index_controller
-            .document(index, document_id, attributes_to_retrieve)
-            .await
-    }
-}

meilisearch-http/src/data/updates.rs

@@ -1,80 +0,0 @@
-use milli::update::{IndexDocumentsMethod, UpdateFormat};
-
-use crate::extractors::payload::Payload;
-use crate::index::{Checked, Settings};
-use crate::index_controller::{error::Result, IndexMetadata, IndexSettings, UpdateStatus};
-use crate::Data;
-
-impl Data {
-    pub async fn add_documents(
-        &self,
-        index: String,
-        method: IndexDocumentsMethod,
-        format: UpdateFormat,
-        stream: Payload,
-        primary_key: Option<String>,
-    ) -> Result<UpdateStatus> {
-        let update_status = self
-            .index_controller
-            .add_documents(index, method, format, stream, primary_key)
-            .await?;
-        Ok(update_status)
-    }
-
-    pub async fn update_settings(
-        &self,
-        index: String,
-        settings: Settings<Checked>,
-        create: bool,
-    ) -> Result<UpdateStatus> {
-        let update = self
-            .index_controller
-            .update_settings(index, settings, create)
-            .await?;
-        Ok(update)
-    }
-
-    pub async fn clear_documents(&self, index: String) -> Result<UpdateStatus> {
-        let update = self.index_controller.clear_documents(index).await?;
-        Ok(update)
-    }
-
-    pub async fn delete_documents(
-        &self,
-        index: String,
-        document_ids: Vec<String>,
-    ) -> Result<UpdateStatus> {
-        let update = self
-            .index_controller
-            .delete_documents(index, document_ids)
-            .await?;
-        Ok(update)
-    }
-
-    pub async fn delete_index(&self, index: String) -> Result<()> {
-        self.index_controller.delete_index(index).await?;
-        Ok(())
-    }
-
-    pub async fn get_update_status(&self, index: String, uid: u64) -> Result<UpdateStatus> {
-        self.index_controller.update_status(index, uid).await
-    }
-
-    pub async fn get_updates_status(&self, index: String) -> Result<Vec<UpdateStatus>> {
-        self.index_controller.all_update_status(index).await
-    }
-
-    pub async fn update_index(
-        &self,
-        uid: String,
-        primary_key: Option<String>,
-        new_uid: Option<String>,
-    ) -> Result<IndexMetadata> {
-        let settings = IndexSettings {
-            uid: new_uid,
-            primary_key,
-        };
-
-        self.index_controller.update_index(uid, settings).await
-    }
-}

meilisearch-http/src/error.rs

@@ -1,145 +1,57 @@
-use std::error::Error;
-use std::fmt;
-
 use actix_web as aweb;
-use actix_web::body::Body;
-use actix_web::dev::BaseHttpResponseBuilder;
-use actix_web::http::StatusCode;
 use aweb::error::{JsonPayloadError, QueryPayloadError};
-use meilisearch_error::{Code, ErrorCode};
-use milli::UserError;
-use serde::{Deserialize, Serialize};
+use meilisearch_error::{Code, ErrorCode, ResponseError};
 
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct ResponseError {
-    #[serde(skip)]
-    code: StatusCode,
-    message: String,
-    error_code: String,
-    error_type: String,
-    error_link: String,
+#[derive(Debug, thiserror::Error)]
+pub enum MeilisearchHttpError {
+    #[error("A Content-Type header is missing. Accepted values for the Content-Type header are: {}",
+            .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", "))]
+    MissingContentType(Vec<String>),
+    #[error(
+        "The Content-Type `{0}` is invalid. Accepted values for the Content-Type header are: {}",
+        .1.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", ")
+    )]
+    InvalidContentType(String, Vec<String>),
 }
 
-impl fmt::Display for ResponseError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        self.message.fmt(f)
-    }
-}
-
-impl<T> From<T> for ResponseError
-where
-    T: ErrorCode,
-{
-    fn from(other: T) -> Self {
-        Self {
-            code: other.http_status(),
-            message: other.to_string(),
-            error_code: other.error_name(),
-            error_type: other.error_type(),
-            error_link: other.error_url(),
-        }
-    }
-}
-
-impl aweb::error::ResponseError for ResponseError {
-    fn error_response(&self) -> aweb::BaseHttpResponse<Body> {
-        let json = serde_json::to_vec(self).unwrap();
-        BaseHttpResponseBuilder::new(self.status_code())
-            .content_type("application/json")
-            .body(json)
-    }
-
-    fn status_code(&self) -> StatusCode {
-        self.code
-    }
-}
-
-macro_rules! internal_error {
-    ($target:ty : $($other:path), *) => {
-        $(
-            impl From<$other> for $target {
-                fn from(other: $other) -> Self {
-                    Self::Internal(Box::new(other))
-                }
-            }
-        )*
-    }
-}
-
-#[derive(Debug)]
-pub struct MilliError<'a>(pub &'a milli::Error);
-
-impl Error for MilliError<'_> {}
-
-impl fmt::Display for MilliError<'_> {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        self.0.fmt(f)
-    }
-}
-
-impl ErrorCode for MilliError<'_> {
+impl ErrorCode for MeilisearchHttpError {
     fn error_code(&self) -> Code {
-        match self.0 {
-            milli::Error::InternalError(_) => Code::Internal,
-            milli::Error::IoError(_) => Code::Internal,
-            milli::Error::UserError(ref error) => {
-                match error {
-                    // TODO: wait for spec for new error codes.
-                    UserError::Csv(_)
-                    | UserError::SerdeJson(_)
-                    | UserError::MaxDatabaseSizeReached
-                    | UserError::InvalidCriterionName { .. }
-                    | UserError::InvalidDocumentId { .. }
-                    | UserError::InvalidStoreFile
-                    | UserError::NoSpaceLeftOnDevice
-                    | UserError::InvalidAscDescSyntax { .. }
-                    | UserError::DocumentLimitReached => Code::Internal,
-                    UserError::AttributeLimitReached => Code::MaxFieldsLimitExceeded,
-                    UserError::InvalidFilter(_) => Code::Filter,
-                    UserError::InvalidFilterAttribute(_) => Code::Filter,
-                    UserError::InvalidSortName { .. } => Code::Sort,
-                    UserError::MissingDocumentId { .. } => Code::MissingDocumentId,
-                    UserError::MissingPrimaryKey => Code::MissingPrimaryKey,
-                    UserError::PrimaryKeyCannotBeChanged => Code::PrimaryKeyAlreadyPresent,
-                    UserError::PrimaryKeyCannotBeReset => Code::PrimaryKeyAlreadyPresent,
-                    UserError::SortRankingRuleMissing => Code::Sort,
-                    UserError::UnknownInternalDocumentId { .. } => Code::DocumentNotFound,
-                    UserError::InvalidFacetsDistribution { .. } => Code::BadRequest,
-                    UserError::InvalidSortableAttribute { .. } => Code::Sort,
-                }
-            }
-        }
-    }
-}
-
-impl fmt::Display for PayloadError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
-            PayloadError::Json(e) => e.fmt(f),
-            PayloadError::Query(e) => e.fmt(f),
+            MeilisearchHttpError::MissingContentType(_) => Code::MissingContentType,
+            MeilisearchHttpError::InvalidContentType(_, _) => Code::InvalidContentType,
         }
     }
 }
 
-#[derive(Debug)]
-pub enum PayloadError {
-    Json(JsonPayloadError),
-    Query(QueryPayloadError),
+impl From<MeilisearchHttpError> for aweb::Error {
+    fn from(other: MeilisearchHttpError) -> Self {
+        aweb::Error::from(ResponseError::from(other))
+    }
 }
 
-impl Error for PayloadError {}
+#[derive(Debug, thiserror::Error)]
+pub enum PayloadError {
+    #[error("{0}")]
+    Json(JsonPayloadError),
+    #[error("{0}")]
+    Query(QueryPayloadError),
+    #[error("The json payload provided is malformed. `{0}`.")]
+    MalformedPayload(serde_json::error::Error),
+    #[error("A json payload is missing.")]
+    MissingPayload,
+}
 
 impl ErrorCode for PayloadError {
     fn error_code(&self) -> Code {
         match self {
             PayloadError::Json(err) => match err {
-                JsonPayloadError::Overflow => Code::PayloadTooLarge,
+                JsonPayloadError::Overflow { .. } => Code::PayloadTooLarge,
                 JsonPayloadError::ContentType => Code::UnsupportedMediaType,
                 JsonPayloadError::Payload(aweb::error::PayloadError::Overflow) => {
                     Code::PayloadTooLarge
                 }
-                JsonPayloadError::Deserialize(_) | JsonPayloadError::Payload(_) => Code::BadRequest,
+                JsonPayloadError::Payload(_) => Code::BadRequest,
+                JsonPayloadError::Deserialize(_) => Code::BadRequest,
                 JsonPayloadError::Serialize(_) => Code::Internal,
                 _ => Code::Internal,
             },
@@ -147,13 +59,29 @@ impl ErrorCode for PayloadError {
                 QueryPayloadError::Deserialize(_) => Code::BadRequest,
                 _ => Code::Internal,
             },
+            PayloadError::MissingPayload => Code::MissingPayload,
+            PayloadError::MalformedPayload(_) => Code::MalformedPayload,
         }
     }
 }
 
 impl From<JsonPayloadError> for PayloadError {
     fn from(other: JsonPayloadError) -> Self {
-        Self::Json(other)
+        match other {
+            JsonPayloadError::Deserialize(e)
+                if e.classify() == serde_json::error::Category::Eof
+                    && e.line() == 1
+                    && e.column() == 0 =>
+            {
+                Self::MissingPayload
+            }
+            JsonPayloadError::Deserialize(e)
+                if e.classify() != serde_json::error::Category::Data =>
+            {
+                Self::MalformedPayload(e)
+            }
+            _ => Self::Json(other),
+        }
     }
 }
 
@@ -163,9 +91,8 @@ impl From<QueryPayloadError> for PayloadError {
     }
 }
 
-pub fn payload_error_handler<E>(err: E) -> ResponseError
-where
-    E: Into<PayloadError>,
-{
-    err.into().into()
+impl From<PayloadError> for aweb::Error {
+    fn from(other: PayloadError) -> Self {
+        aweb::Error::from(ResponseError::from(other))
+    }
 }

meilisearch-http/src/extractors/authentication/error.rs

@@ -2,15 +2,13 @@ use meilisearch_error::{Code, ErrorCode};
 
 #[derive(Debug, thiserror::Error)]
 pub enum AuthenticationError {
-    #[error("You must have an authorization token")]
+    #[error("The Authorization header is missing. It must use the bearer authorization method.")]
     MissingAuthorizationHeader,
-    #[error("Invalid API key")]
+    #[error("The provided API key is invalid.")]
     InvalidToken(String),
     // Triggered on configuration error.
-    #[error("Irretrievable state")]
+    #[error("An internal error has occurred. `Irretrievable state`.")]
     IrretrievableState,
-    #[error("Unknown authentication policy")]
-    UnknownPolicy,
 }
 
 impl ErrorCode for AuthenticationError {
@@ -19,7 +17,6 @@ impl ErrorCode for AuthenticationError {
             AuthenticationError::MissingAuthorizationHeader => Code::MissingAuthorizationHeader,
             AuthenticationError::InvalidToken(_) => Code::InvalidToken,
             AuthenticationError::IrretrievableState => Code::Internal,
-            AuthenticationError::UnknownPolicy => Code::Internal,
         }
     }
 }

meilisearch-http/src/extractors/authentication/mod.rs

@@ -1,83 +1,28 @@
 mod error;
 
-use std::any::{Any, TypeId};
-use std::collections::HashMap;
 use std::marker::PhantomData;
 use std::ops::Deref;
 
 use actix_web::FromRequest;
 use futures::future::err;
 use futures::future::{ok, Ready};
+use meilisearch_error::ResponseError;
 
-use crate::error::ResponseError;
 use error::AuthenticationError;
-
-macro_rules! create_policies {
-    ($($name:ident), *) => {
-        pub mod policies {
-            use std::collections::HashSet;
-            use crate::extractors::authentication::Policy;
-
-            $(
-                #[derive(Debug, Default)]
-                pub struct $name {
-                    inner: HashSet<Vec<u8>>
-                }
-
-                impl $name {
-                    pub fn new() -> Self {
-                        Self { inner: HashSet::new() }
-                    }
-
-                    pub fn add(&mut self, token: Vec<u8>) {
-                        self.inner.insert(token);
-                    }
-                }
-
-                impl Policy for $name {
-                    fn authenticate(&self, token: &[u8]) -> bool {
-                        self.inner.contains(token)
-                    }
-                }
-            )*
-        }
-    };
-}
-
-create_policies!(Public, Private, Admin);
-
-/// Instanciate a `Policies`, filled with the given policies.
-macro_rules! init_policies {
-    ($($name:ident), *) => {
-        {
-            let mut policies = crate::extractors::authentication::Policies::new();
-            $(
-                let policy = $name::new();
-                policies.insert(policy);
-            )*
-            policies
-        }
-    };
-}
-
-/// Adds user to all specified policies.
-macro_rules! create_users {
-    ($policies:ident, $($user:expr => { $($policy:ty), * }), *) => {
-        {
-            $(
-                $(
-                    $policies.get_mut::<$policy>().map(|p| p.add($user.to_owned()));
-                )*
-            )*
-        }
-    };
-}
+use meilisearch_auth::{AuthController, AuthFilter};
 
 pub struct GuardedData<T, D> {
     data: D,
+    filters: AuthFilter,
     _marker: PhantomData<T>,
 }
 
+impl<T, D> GuardedData<T, D> {
+    pub fn filters(&self) -> &AuthFilter {
+        &self.filters
+    }
+}
+
 impl<T, D> Deref for GuardedData<T, D> {
     type Target = D;
 
@@ -86,58 +31,8 @@ impl<T, D> Deref for GuardedData<T, D> {
     }
 }
 
-pub trait Policy {
-    fn authenticate(&self, token: &[u8]) -> bool;
-}
-
-#[derive(Debug)]
-pub struct Policies {
-    inner: HashMap<TypeId, Box<dyn Any>>,
-}
-
-impl Policies {
-    pub fn new() -> Self {
-        Self {
-            inner: HashMap::new(),
-        }
-    }
-
-    pub fn insert<S: Policy + 'static>(&mut self, policy: S) {
-        self.inner.insert(TypeId::of::<S>(), Box::new(policy));
-    }
-
-    pub fn get<S: Policy + 'static>(&self) -> Option<&S> {
-        self.inner
-            .get(&TypeId::of::<S>())
-            .and_then(|p| p.downcast_ref::<S>())
-    }
-
-    pub fn get_mut<S: Policy + 'static>(&mut self) -> Option<&mut S> {
-        self.inner
-            .get_mut(&TypeId::of::<S>())
-            .and_then(|p| p.downcast_mut::<S>())
-    }
-}
-
-impl Default for Policies {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-pub enum AuthConfig {
-    NoAuth,
-    Auth(Policies),
-}
-
-impl Default for AuthConfig {
-    fn default() -> Self {
-        Self::NoAuth
-    }
-}
-
 impl<P: Policy + 'static, D: 'static + Clone> FromRequest for GuardedData<P, D> {
-    type Config = AuthConfig;
+    type Config = ();
 
     type Error = ResponseError;
 
@@ -145,38 +40,103 @@ impl<P: Policy + 'static, D: 'static + Clone> FromRequest for GuardedData<P, D>
 
     fn from_request(
         req: &actix_web::HttpRequest,
-        _payload: &mut actix_http::Payload,
+        _payload: &mut actix_web::dev::Payload,
     ) -> Self::Future {
-        match req.app_data::<Self::Config>() {
-            Some(config) => match config {
-                AuthConfig::NoAuth => match req.app_data::<D>().cloned() {
-                    Some(data) => ok(Self {
-                        data,
-                        _marker: PhantomData,
-                    }),
-                    None => err(AuthenticationError::IrretrievableState.into()),
-                },
-                AuthConfig::Auth(policies) => match policies.get::<P>() {
-                    Some(policy) => match req.headers().get("x-meili-api-key") {
-                        Some(token) => {
-                            if policy.authenticate(token.as_bytes()) {
-                                match req.app_data::<D>().cloned() {
-                                    Some(data) => ok(Self {
-                                        data,
-                                        _marker: PhantomData,
-                                    }),
-                                    None => err(AuthenticationError::IrretrievableState.into()),
-                                }
-                            } else {
-                                err(AuthenticationError::InvalidToken(String::from("hello")).into())
+        match req.app_data::<AuthController>().cloned() {
+            Some(auth) => match req
+                .headers()
+                .get("Authorization")
+                .map(|type_token| type_token.to_str().unwrap_or_default().splitn(2, ' '))
+            {
+                Some(mut type_token) => match type_token.next() {
+                    Some("Bearer") => {
+                        // TODO: find a less hardcoded way?
+                        let index = req.match_info().get("index_uid");
+                        let token = type_token.next().unwrap_or("unknown");
+                        match P::authenticate(auth, token, index) {
+                            Some(filters) => match req.app_data::<D>().cloned() {
+                                Some(data) => ok(Self {
+                                    data,
+                                    filters,
+                                    _marker: PhantomData,
+                                }),
+                                None => err(AuthenticationError::IrretrievableState.into()),
+                            },
+                            None => {
+                                let token = token.to_string();
+                                err(AuthenticationError::InvalidToken(token).into())
                             }
                         }
-                        None => err(AuthenticationError::MissingAuthorizationHeader.into()),
+                    }
+                    _otherwise => err(AuthenticationError::MissingAuthorizationHeader.into()),
+                },
+                None => match P::authenticate(auth, "", None) {
+                    Some(filters) => match req.app_data::<D>().cloned() {
+                        Some(data) => ok(Self {
+                            data,
+                            filters,
+                            _marker: PhantomData,
+                        }),
+                        None => err(AuthenticationError::IrretrievableState.into()),
                     },
-                    None => err(AuthenticationError::UnknownPolicy.into()),
+                    None => err(AuthenticationError::MissingAuthorizationHeader.into()),
                 },
             },
             None => err(AuthenticationError::IrretrievableState.into()),
         }
     }
 }
+
+pub trait Policy {
+    fn authenticate(auth: AuthController, token: &str, index: Option<&str>) -> Option<AuthFilter>;
+}
+
+pub mod policies {
+    use crate::extractors::authentication::Policy;
+    use meilisearch_auth::{Action, AuthController, AuthFilter};
+    // reexport actions in policies in order to be used in routes configuration.
+    pub use meilisearch_auth::actions;
+
+    pub struct MasterPolicy;
+
+    impl Policy for MasterPolicy {
+        fn authenticate(
+            auth: AuthController,
+            token: &str,
+            _index: Option<&str>,
+        ) -> Option<AuthFilter> {
+            if let Some(master_key) = auth.get_master_key() {
+                if master_key == token {
+                    return Some(AuthFilter::default());
+                }
+            }
+
+            None
+        }
+    }
+
+    pub struct ActionPolicy<const A: u8>;
+
+    impl<const A: u8> Policy for ActionPolicy<A> {
+        fn authenticate(
+            auth: AuthController,
+            token: &str,
+            index: Option<&str>,
+        ) -> Option<AuthFilter> {
+            // authenticate if token is the master key.
+            if auth.get_master_key().map_or(true, |mk| mk == token) {
+                return Some(AuthFilter::default());
+            }
+
+            // authenticate if token is allowed.
+            if let Some(action) = Action::from_repr(A) {
+                let index = index.map(|i| i.as_bytes());
+                if let Ok(true) = auth.authenticate(token.as_bytes(), action, index) {
+                    return auth.get_key_filters(token).ok();
+                }
+            }
+
+            None
+        }
+    }
+}

meilisearch-http/src/extractors/payload.rs

@@ -1,7 +1,7 @@
 use std::pin::Pin;
 use std::task::{Context, Poll};
 
-use actix_http::error::PayloadError;
+use actix_web::error::PayloadError;
 use actix_web::{dev, web, FromRequest, HttpRequest};
 use futures::future::{ready, Ready};
 use futures::Stream;

meilisearch-http/src/helpers/mod.rs

@@ -1,4 +1,3 @@
-pub mod compression;
 mod env;
 
 pub use env::EnvSizer;

meilisearch-http/src/index/dump.rs

@@ -1,170 +0,0 @@
-use std::fs::{create_dir_all, File};
-use std::io::{BufRead, BufReader, Write};
-use std::path::Path;
-use std::sync::Arc;
-
-use anyhow::{bail, Context};
-use heed::RoTxn;
-use indexmap::IndexMap;
-use milli::update::{IndexDocumentsMethod, UpdateFormat::JsonStream};
-use serde::{Deserialize, Serialize};
-use serde_json::Value;
-
-use crate::index_controller::{asc_ranking_rule, desc_ranking_rule};
-use crate::option::IndexerOpts;
-
-use super::error::Result;
-use super::{update_handler::UpdateHandler, Index, Settings, Unchecked};
-
-#[derive(Serialize, Deserialize)]
-struct DumpMeta {
-    settings: Settings<Unchecked>,
-    primary_key: Option<String>,
-}
-
-const META_FILE_NAME: &str = "meta.json";
-const DATA_FILE_NAME: &str = "documents.jsonl";
-
-impl Index {
-    pub fn dump(&self, path: impl AsRef<Path>) -> Result<()> {
-        // acquire write txn make sure any ongoing write is finished before we start.
-        let txn = self.env.write_txn()?;
-
-        self.dump_documents(&txn, &path)?;
-        self.dump_meta(&txn, &path)?;
-
-        Ok(())
-    }
-
-    fn dump_documents(&self, txn: &RoTxn, path: impl AsRef<Path>) -> Result<()> {
-        let document_file_path = path.as_ref().join(DATA_FILE_NAME);
-        let mut document_file = File::create(&document_file_path)?;
-
-        let documents = self.all_documents(txn)?;
-        let fields_ids_map = self.fields_ids_map(txn)?;
-
-        // dump documents
-        let mut json_map = IndexMap::new();
-        for document in documents {
-            let (_, reader) = document?;
-
-            for (fid, bytes) in reader.iter() {
-                if let Some(name) = fields_ids_map.name(fid) {
-                    json_map.insert(name, serde_json::from_slice::<serde_json::Value>(bytes)?);
-                }
-            }
-
-            serde_json::to_writer(&mut document_file, &json_map)?;
-            document_file.write_all(b"\n")?;
-
-            json_map.clear();
-        }
-
-        Ok(())
-    }
-
-    fn dump_meta(&self, txn: &RoTxn, path: impl AsRef<Path>) -> Result<()> {
-        let meta_file_path = path.as_ref().join(META_FILE_NAME);
-        let mut meta_file = File::create(&meta_file_path)?;
-
-        let settings = self.settings_txn(txn)?.into_unchecked();
-        let primary_key = self.primary_key(txn)?.map(String::from);
-        let meta = DumpMeta {
-            settings,
-            primary_key,
-        };
-
-        serde_json::to_writer(&mut meta_file, &meta)?;
-
-        Ok(())
-    }
-
-    pub fn load_dump(
-        src: impl AsRef<Path>,
-        dst: impl AsRef<Path>,
-        size: usize,
-        indexing_options: &IndexerOpts,
-    ) -> anyhow::Result<()> {
-        let dir_name = src
-            .as_ref()
-            .file_name()
-            .with_context(|| format!("invalid dump index: {}", src.as_ref().display()))?;
-
-        let dst_dir_path = dst.as_ref().join("indexes").join(dir_name);
-        create_dir_all(&dst_dir_path)?;
-
-        let meta_path = src.as_ref().join(META_FILE_NAME);
-        let mut meta_file = File::open(meta_path)?;
-
-        // We first deserialize the dump meta into a serde_json::Value and change
-        // the custom ranking rules settings from the old format to the new format.
-        let mut meta: Value = serde_json::from_reader(&mut meta_file)?;
-        if let Some(ranking_rules) = meta.pointer_mut("/settings/rankingRules") {
-            convert_custom_ranking_rules(ranking_rules);
-        }
-
-        // Then we serialize it back into a vec to deserialize it
-        // into a `DumpMeta` struct with the newly patched `rankingRules` format.
-        let patched_meta = serde_json::to_vec(&meta)?;
-
-        let DumpMeta {
-            settings,
-            primary_key,
-        } = serde_json::from_slice(&patched_meta)?;
-        let settings = settings.check();
-        let index = Self::open(&dst_dir_path, size)?;
-        let mut txn = index.write_txn()?;
-
-        let handler = UpdateHandler::new(indexing_options)?;
-
-        index.update_settings_txn(&mut txn, &settings, handler.update_builder(0))?;
-
-        let document_file_path = src.as_ref().join(DATA_FILE_NAME);
-        let reader = File::open(&document_file_path)?;
-        let mut reader = BufReader::new(reader);
-        reader.fill_buf()?;
-        // If the document file is empty, we don't perform the document addition, to prevent
-        // a primary key error to be thrown.
-        if !reader.buffer().is_empty() {
-            index.update_documents_txn(
-                &mut txn,
-                JsonStream,
-                IndexDocumentsMethod::UpdateDocuments,
-                Some(reader),
-                handler.update_builder(0),
-                primary_key.as_deref(),
-            )?;
-        }
-
-        txn.commit()?;
-
-        match Arc::try_unwrap(index.0) {
-            Ok(inner) => inner.prepare_for_closing().wait(),
-            Err(_) => bail!("Could not close index properly."),
-        }
-
-        Ok(())
-    }
-}
-
-/// Converts the ranking rules from the format `asc(_)`, `desc(_)` to the format `_:asc`, `_:desc`.
-///
-/// This is done for compatibility reasons, and to avoid a new dump version,
-/// since the new syntax was introduced soon after the new dump version.
-fn convert_custom_ranking_rules(ranking_rules: &mut Value) {
-    *ranking_rules = match ranking_rules.take() {
-        Value::Array(values) => values
-            .into_iter()
-            .filter_map(|value| match value {
-                Value::String(s) if s.starts_with("asc") => asc_ranking_rule(&s)
-                    .map(|f| format!("{}:asc", f))
-                    .map(Value::String),
-                Value::String(s) if s.starts_with("desc") => desc_ranking_rule(&s)
-                    .map(|f| format!("{}:desc", f))
-                    .map(Value::String),
-                otherwise => Some(otherwise),
-            })
-            .collect(),
-        otherwise => otherwise,
-    }
-}

meilisearch-http/src/index_controller/dump_actor/error.rs

@@ -1,52 +0,0 @@
-use meilisearch_error::{Code, ErrorCode};
-
-use crate::index_controller::update_actor::error::UpdateActorError;
-use crate::index_controller::uuid_resolver::error::UuidResolverError;
-
-pub type Result<T> = std::result::Result<T, DumpActorError>;
-
-#[derive(thiserror::Error, Debug)]
-pub enum DumpActorError {
-    #[error("Another dump is already in progress")]
-    DumpAlreadyRunning,
-    #[error("Dump `{0}` not found")]
-    DumpDoesNotExist(String),
-    #[error("Internal error: {0}")]
-    Internal(Box<dyn std::error::Error + Send + Sync + 'static>),
-    #[error("{0}")]
-    UuidResolver(#[from] UuidResolverError),
-    #[error("{0}")]
-    UpdateActor(#[from] UpdateActorError),
-}
-
-macro_rules! internal_error {
-    ($($other:path), *) => {
-        $(
-            impl From<$other> for DumpActorError {
-                fn from(other: $other) -> Self {
-                    Self::Internal(Box::new(other))
-                }
-            }
-        )*
-    }
-}
-
-internal_error!(
-    heed::Error,
-    std::io::Error,
-    tokio::task::JoinError,
-    serde_json::error::Error,
-    tempfile::PersistError
-);
-
-impl ErrorCode for DumpActorError {
-    fn error_code(&self) -> Code {
-        match self {
-            DumpActorError::DumpAlreadyRunning => Code::DumpAlreadyInProgress,
-            DumpActorError::DumpDoesNotExist(_) => Code::NotFound,
-            DumpActorError::Internal(_) => Code::Internal,
-            DumpActorError::UuidResolver(e) => e.error_code(),
-            DumpActorError::UpdateActor(e) => e.error_code(),
-        }
-    }
-}

meilisearch-http/src/index_controller/dump_actor/handle_impl.rs

@@ -1,53 +0,0 @@
-use std::path::Path;
-
-use actix_web::web::Bytes;
-use tokio::sync::{mpsc, oneshot};
-
-use super::error::Result;
-use super::{DumpActor, DumpActorHandle, DumpInfo, DumpMsg};
-
-#[derive(Clone)]
-pub struct DumpActorHandleImpl {
-    sender: mpsc::Sender<DumpMsg>,
-}
-
-#[async_trait::async_trait]
-impl DumpActorHandle for DumpActorHandleImpl {
-    async fn create_dump(&self) -> Result<DumpInfo> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = DumpMsg::CreateDump { ret };
-        let _ = self.sender.send(msg).await;
-        receiver.await.expect("IndexActor has been killed")
-    }
-
-    async fn dump_info(&self, uid: String) -> Result<DumpInfo> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = DumpMsg::DumpInfo { ret, uid };
-        let _ = self.sender.send(msg).await;
-        receiver.await.expect("IndexActor has been killed")
-    }
-}
-
-impl DumpActorHandleImpl {
-    pub fn new(
-        path: impl AsRef<Path>,
-        uuid_resolver: crate::index_controller::uuid_resolver::UuidResolverHandleImpl,
-        update: crate::index_controller::update_actor::UpdateActorHandleImpl<Bytes>,
-        index_db_size: usize,
-        update_db_size: usize,
-    ) -> anyhow::Result<Self> {
-        let (sender, receiver) = mpsc::channel(10);
-        let actor = DumpActor::new(
-            receiver,
-            uuid_resolver,
-            update,
-            path,
-            index_db_size,
-            update_db_size,
-        );
-
-        tokio::task::spawn(actor.run());
-
-        Ok(Self { sender })
-    }
-}

meilisearch-http/src/index_controller/dump_actor/loaders/mod.rs

@@ -1,2 +0,0 @@
-pub mod v1;
-pub mod v2;

meilisearch-http/src/index_controller/dump_actor/loaders/v1.rs

@@ -1,228 +0,0 @@
-use std::collections::{BTreeMap, BTreeSet};
-use std::fs::{create_dir_all, File};
-use std::io::BufRead;
-use std::marker::PhantomData;
-use std::path::Path;
-use std::sync::Arc;
-
-use heed::EnvOpenOptions;
-use log::{error, info, warn};
-use milli::update::{IndexDocumentsMethod, Setting, UpdateFormat};
-use serde::{Deserialize, Deserializer, Serialize};
-use uuid::Uuid;
-
-use crate::index_controller::{self, uuid_resolver::HeedUuidStore, IndexMetadata};
-use crate::index_controller::{asc_ranking_rule, desc_ranking_rule};
-use crate::{
-    index::{update_handler::UpdateHandler, Index, Unchecked},
-    option::IndexerOpts,
-};
-
-#[derive(Serialize, Deserialize, Debug)]
-#[serde(rename_all = "camelCase")]
-pub struct MetadataV1 {
-    db_version: String,
-    indexes: Vec<IndexMetadata>,
-}
-
-impl MetadataV1 {
-    pub fn load_dump(
-        self,
-        src: impl AsRef<Path>,
-        dst: impl AsRef<Path>,
-        size: usize,
-        indexer_options: &IndexerOpts,
-    ) -> anyhow::Result<()> {
-        info!(
-            "Loading dump, dump database version: {}, dump version: V1",
-            self.db_version
-        );
-
-        let uuid_store = HeedUuidStore::new(&dst)?;
-        for index in self.indexes {
-            let uuid = Uuid::new_v4();
-            uuid_store.insert(index.uid.clone(), uuid)?;
-            let src = src.as_ref().join(index.uid);
-            load_index(
-                &src,
-                &dst,
-                uuid,
-                index.meta.primary_key.as_deref(),
-                size,
-                indexer_options,
-            )?;
-        }
-
-        Ok(())
-    }
-}
-
-pub 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)
-}
-
-// These are the settings used in legacy meilisearch (<v0.21.0).
-#[derive(Default, Clone, Serialize, Deserialize, Debug)]
-#[serde(rename_all = "camelCase", deny_unknown_fields)]
-struct Settings {
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub ranking_rules: Option<Option<Vec<String>>>,
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub distinct_attribute: Option<Option<String>>,
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub searchable_attributes: Option<Option<Vec<String>>>,
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub displayed_attributes: Option<Option<BTreeSet<String>>>,
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub stop_words: Option<Option<BTreeSet<String>>>,
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub synonyms: Option<Option<BTreeMap<String, Vec<String>>>>,
-    #[serde(default, deserialize_with = "deserialize_some")]
-    pub attributes_for_faceting: Option<Option<Vec<String>>>,
-}
-
-fn load_index(
-    src: impl AsRef<Path>,
-    dst: impl AsRef<Path>,
-    uuid: Uuid,
-    primary_key: Option<&str>,
-    size: usize,
-    indexer_options: &IndexerOpts,
-) -> anyhow::Result<()> {
-    let index_path = dst.as_ref().join(&format!("indexes/index-{}", uuid));
-
-    create_dir_all(&index_path)?;
-    let mut options = EnvOpenOptions::new();
-    options.map_size(size);
-    let index = milli::Index::new(options, index_path)?;
-    let index = Index(Arc::new(index));
-
-    // extract `settings.json` file and import content
-    let settings = import_settings(&src)?;
-    let settings: index_controller::Settings<Unchecked> = settings.into();
-
-    let mut txn = index.write_txn()?;
-
-    let handler = UpdateHandler::new(indexer_options)?;
-
-    index.update_settings_txn(&mut txn, &settings.check(), handler.update_builder(0))?;
-
-    let file = File::open(&src.as_ref().join("documents.jsonl"))?;
-    let mut reader = std::io::BufReader::new(file);
-    reader.fill_buf()?;
-    if !reader.buffer().is_empty() {
-        index.update_documents_txn(
-            &mut txn,
-            UpdateFormat::JsonStream,
-            IndexDocumentsMethod::ReplaceDocuments,
-            Some(reader),
-            handler.update_builder(0),
-            primary_key,
-        )?;
-    }
-
-    txn.commit()?;
-
-    // Finaly, we extract the original milli::Index and close it
-    Arc::try_unwrap(index.0)
-        .map_err(|_e| "Couldn't close the index properly")
-        .unwrap()
-        .prepare_for_closing()
-        .wait();
-
-    // Updates are ignored in dumps V1.
-
-    Ok(())
-}
-
-/// we need to **always** be able to convert the old settings to the settings currently being used
-impl From<Settings> for index_controller::Settings<Unchecked> {
-    fn from(settings: Settings) -> Self {
-        Self {
-            distinct_attribute: match settings.distinct_attribute {
-                Some(Some(attr)) => Setting::Set(attr),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            // we need to convert the old `Vec<String>` into a `BTreeSet<String>`
-            displayed_attributes: match settings.displayed_attributes {
-                Some(Some(attrs)) => Setting::Set(attrs.into_iter().collect()),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            searchable_attributes: match settings.searchable_attributes {
-                Some(Some(attrs)) => Setting::Set(attrs),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            filterable_attributes: match settings.attributes_for_faceting {
-                Some(Some(attrs)) => Setting::Set(attrs.into_iter().collect()),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            sortable_attributes: Setting::NotSet,
-            ranking_rules: match settings.ranking_rules {
-                Some(Some(ranking_rules)) => Setting::Set(ranking_rules.into_iter().filter_map(|criterion| {
-                    match criterion.as_str() {
-                        "words" | "typo" | "proximity" | "attribute" | "exactness" => Some(criterion),
-                        s if s.starts_with("asc") => asc_ranking_rule(s).map(|f| format!("{}:asc", f)),
-                        s if s.starts_with("desc") => desc_ranking_rule(s).map(|f| format!("{}:desc", f)),
-                        "wordsPosition" => {
-                            warn!("The criteria `attribute` and `wordsPosition` have been merged \
-                                into a single criterion `attribute` so `wordsPositon` will be \
-                                ignored");
-                            None
-                        }
-                        s => {
-                            error!("Unknown criterion found in the dump: `{}`, it will be ignored", s);
-                            None
-                        }
-                    }
-                }).collect()),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            // we need to convert the old `Vec<String>` into a `BTreeSet<String>`
-            stop_words: match settings.stop_words {
-                Some(Some(stop_words)) => Setting::Set(stop_words.into_iter().collect()),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            // we need to convert the old `Vec<String>` into a `BTreeMap<String>`
-            synonyms: match settings.synonyms {
-                Some(Some(synonyms)) => Setting::Set(synonyms.into_iter().collect()),
-                Some(None) => Setting::Reset,
-                None => Setting::NotSet
-            },
-            _kind: PhantomData,
-        }
-    }
-}
-
-/// Extract Settings from `settings.json` file present at provided `dir_path`
-fn import_settings(dir_path: impl AsRef<Path>) -> anyhow::Result<Settings> {
-    let path = dir_path.as_ref().join("settings.json");
-    let file = File::open(path)?;
-    let reader = std::io::BufReader::new(file);
-    let metadata = serde_json::from_reader(reader)?;
-
-    Ok(metadata)
-}
-
-#[cfg(test)]
-mod test {
-    use super::*;
-
-    #[test]
-    fn settings_format_regression() {
-        let settings = Settings::default();
-        assert_eq!(
-            r##"{"rankingRules":null,"distinctAttribute":null,"searchableAttributes":null,"displayedAttributes":null,"stopWords":null,"synonyms":null,"attributesForFaceting":null}"##,
-            serde_json::to_string(&settings).unwrap()
-        );
-    }
-}

meilisearch-http/src/index_controller/dump_actor/loaders/v2.rs

@@ -1,59 +0,0 @@
-use std::path::Path;
-
-use chrono::{DateTime, Utc};
-use log::info;
-use serde::{Deserialize, Serialize};
-
-use crate::index::Index;
-use crate::index_controller::{update_actor::UpdateStore, uuid_resolver::HeedUuidStore};
-use crate::option::IndexerOpts;
-
-#[derive(Serialize, Deserialize, Debug)]
-#[serde(rename_all = "camelCase")]
-pub struct MetadataV2 {
-    db_version: String,
-    index_db_size: usize,
-    update_db_size: usize,
-    dump_date: DateTime<Utc>,
-}
-
-impl MetadataV2 {
-    pub fn new(index_db_size: usize, update_db_size: usize) -> Self {
-        Self {
-            db_version: env!("CARGO_PKG_VERSION").to_string(),
-            index_db_size,
-            update_db_size,
-            dump_date: Utc::now(),
-        }
-    }
-
-    pub fn load_dump(
-        self,
-        src: impl AsRef<Path>,
-        dst: impl AsRef<Path>,
-        index_db_size: usize,
-        update_db_size: usize,
-        indexing_options: &IndexerOpts,
-    ) -> anyhow::Result<()> {
-        info!(
-            "Loading dump from {}, dump database version: {}, dump version: V2",
-            self.dump_date, self.db_version
-        );
-
-        info!("Loading index database.");
-        HeedUuidStore::load_dump(src.as_ref(), &dst)?;
-
-        info!("Loading updates.");
-        UpdateStore::load_dump(&src, &dst, update_db_size)?;
-
-        info!("Loading indexes.");
-        let indexes_path = src.as_ref().join("indexes");
-        let indexes = indexes_path.read_dir()?;
-        for index in indexes {
-            let index = index?;
-            Index::load_dump(&index.path(), &dst, index_db_size, indexing_options)?;
-        }
-
-        Ok(())
-    }
-}

meilisearch-http/src/index_controller/dump_actor/mod.rs

@@ -1,203 +0,0 @@
-use std::fs::File;
-use std::path::{Path, PathBuf};
-
-use anyhow::Context;
-use chrono::{DateTime, Utc};
-use log::{info, trace, warn};
-#[cfg(test)]
-use mockall::automock;
-use serde::{Deserialize, Serialize};
-use tokio::fs::create_dir_all;
-
-use loaders::v1::MetadataV1;
-use loaders::v2::MetadataV2;
-
-pub use actor::DumpActor;
-pub use handle_impl::*;
-pub use message::DumpMsg;
-
-use super::{update_actor::UpdateActorHandle, uuid_resolver::UuidResolverHandle};
-use crate::index_controller::dump_actor::error::DumpActorError;
-use crate::{helpers::compression, option::IndexerOpts};
-use error::Result;
-
-mod actor;
-pub mod error;
-mod handle_impl;
-mod loaders;
-mod message;
-
-const META_FILE_NAME: &str = "metadata.json";
-
-#[async_trait::async_trait]
-#[cfg_attr(test, automock)]
-pub trait DumpActorHandle {
-    /// Start the creation of a dump
-    /// Implementation: [handle_impl::DumpActorHandleImpl::create_dump]
-    async fn create_dump(&self) -> Result<DumpInfo>;
-
-    /// Return the status of an already created dump
-    /// Implementation: [handle_impl::DumpActorHandleImpl::dump_info]
-    async fn dump_info(&self, uid: String) -> Result<DumpInfo>;
-}
-
-#[derive(Debug, Serialize, Deserialize)]
-#[serde(tag = "dumpVersion")]
-pub enum Metadata {
-    V1(MetadataV1),
-    V2(MetadataV2),
-}
-
-impl Metadata {
-    pub fn new_v2(index_db_size: usize, update_db_size: usize) -> Self {
-        let meta = MetadataV2::new(index_db_size, update_db_size);
-        Self::V2(meta)
-    }
-}
-
-#[derive(Debug, Serialize, Deserialize, PartialEq, Clone)]
-#[serde(rename_all = "snake_case")]
-pub enum DumpStatus {
-    Done,
-    InProgress,
-    Failed,
-}
-
-#[derive(Debug, Serialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct DumpInfo {
-    pub uid: String,
-    pub status: DumpStatus,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub error: Option<String>,
-    started_at: DateTime<Utc>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    finished_at: Option<DateTime<Utc>>,
-}
-
-impl DumpInfo {
-    pub fn new(uid: String, status: DumpStatus) -> Self {
-        Self {
-            uid,
-            status,
-            error: None,
-            started_at: Utc::now(),
-            finished_at: None,
-        }
-    }
-
-    pub fn with_error(&mut self, error: String) {
-        self.status = DumpStatus::Failed;
-        self.finished_at = Some(Utc::now());
-        self.error = Some(error);
-    }
-
-    pub fn done(&mut self) {
-        self.finished_at = Some(Utc::now());
-        self.status = DumpStatus::Done;
-    }
-
-    pub fn dump_already_in_progress(&self) -> bool {
-        self.status == DumpStatus::InProgress
-    }
-}
-
-pub fn load_dump(
-    dst_path: impl AsRef<Path>,
-    src_path: impl AsRef<Path>,
-    index_db_size: usize,
-    update_db_size: usize,
-    indexer_opts: &IndexerOpts,
-) -> anyhow::Result<()> {
-    let tmp_src = tempfile::tempdir_in(".")?;
-    let tmp_src_path = tmp_src.path();
-
-    compression::from_tar_gz(&src_path, tmp_src_path)?;
-
-    let meta_path = tmp_src_path.join(META_FILE_NAME);
-    let mut meta_file = File::open(&meta_path)?;
-    let meta: Metadata = serde_json::from_reader(&mut meta_file)?;
-
-    let dst_dir = dst_path
-        .as_ref()
-        .parent()
-        .with_context(|| format!("Invalid db path: {}", dst_path.as_ref().display()))?;
-
-    let tmp_dst = tempfile::tempdir_in(dst_dir)?;
-
-    match meta {
-        Metadata::V1(meta) => {
-            meta.load_dump(&tmp_src_path, tmp_dst.path(), index_db_size, indexer_opts)?
-        }
-        Metadata::V2(meta) => meta.load_dump(
-            &tmp_src_path,
-            tmp_dst.path(),
-            index_db_size,
-            update_db_size,
-            indexer_opts,
-        )?,
-    }
-    // Persist and atomically rename the db
-    let persisted_dump = tmp_dst.into_path();
-    if dst_path.as_ref().exists() {
-        warn!("Overwriting database at {}", dst_path.as_ref().display());
-        std::fs::remove_dir_all(&dst_path)?;
-    }
-
-    std::fs::rename(&persisted_dump, &dst_path)?;
-
-    Ok(())
-}
-
-struct DumpTask<U, P> {
-    path: PathBuf,
-    uuid_resolver: U,
-    update_handle: P,
-    uid: String,
-    update_db_size: usize,
-    index_db_size: usize,
-}
-
-impl<U, P> DumpTask<U, P>
-where
-    U: UuidResolverHandle + Send + Sync + Clone + 'static,
-    P: UpdateActorHandle + Send + Sync + Clone + 'static,
-{
-    async fn run(self) -> Result<()> {
-        trace!("Performing dump.");
-
-        create_dir_all(&self.path).await?;
-
-        let path_clone = self.path.clone();
-        let temp_dump_dir =
-            tokio::task::spawn_blocking(|| tempfile::TempDir::new_in(path_clone)).await??;
-        let temp_dump_path = temp_dump_dir.path().to_owned();
-
-        let meta = Metadata::new_v2(self.index_db_size, self.update_db_size);
-        let meta_path = temp_dump_path.join(META_FILE_NAME);
-        let mut meta_file = File::create(&meta_path)?;
-        serde_json::to_writer(&mut meta_file, &meta)?;
-
-        let uuids = self.uuid_resolver.dump(temp_dump_path.clone()).await?;
-
-        self.update_handle
-            .dump(uuids, temp_dump_path.clone())
-            .await?;
-
-        let dump_path = tokio::task::spawn_blocking(move || -> Result<PathBuf> {
-            let temp_dump_file = tempfile::NamedTempFile::new_in(&self.path)?;
-            compression::to_tar_gz(temp_dump_path, temp_dump_file.path())
-                .map_err(|e| DumpActorError::Internal(e.into()))?;
-
-            let dump_path = self.path.join(self.uid).with_extension("dump");
-            temp_dump_file.persist(&dump_path)?;
-
-            Ok(dump_path)
-        })
-        .await??;
-
-        info!("Created dump in {:?}.", dump_path);
-
-        Ok(())
-    }
-}

meilisearch-http/src/index_controller/error.rs

@@ -1,40 +0,0 @@
-use meilisearch_error::Code;
-use meilisearch_error::ErrorCode;
-
-use crate::index::error::IndexError;
-
-use super::dump_actor::error::DumpActorError;
-use super::index_actor::error::IndexActorError;
-use super::update_actor::error::UpdateActorError;
-use super::uuid_resolver::error::UuidResolverError;
-
-pub type Result<T> = std::result::Result<T, IndexControllerError>;
-
-#[derive(Debug, thiserror::Error)]
-pub enum IndexControllerError {
-    #[error("Index creation must have an uid")]
-    MissingUid,
-    #[error("{0}")]
-    Uuid(#[from] UuidResolverError),
-    #[error("{0}")]
-    IndexActor(#[from] IndexActorError),
-    #[error("{0}")]
-    UpdateActor(#[from] UpdateActorError),
-    #[error("{0}")]
-    DumpActor(#[from] DumpActorError),
-    #[error("{0}")]
-    IndexError(#[from] IndexError),
-}
-
-impl ErrorCode for IndexControllerError {
-    fn error_code(&self) -> Code {
-        match self {
-            IndexControllerError::MissingUid => Code::BadRequest,
-            IndexControllerError::Uuid(e) => e.error_code(),
-            IndexControllerError::IndexActor(e) => e.error_code(),
-            IndexControllerError::UpdateActor(e) => e.error_code(),
-            IndexControllerError::DumpActor(e) => e.error_code(),
-            IndexControllerError::IndexError(e) => e.error_code(),
-        }
-    }
-}

meilisearch-http/src/index_controller/index_actor/actor.rs

@@ -1,351 +0,0 @@
-use std::fs::File;
-use std::path::PathBuf;
-use std::sync::Arc;
-
-use async_stream::stream;
-use futures::stream::StreamExt;
-use heed::CompactionOption;
-use log::debug;
-use milli::update::UpdateBuilder;
-use tokio::task::spawn_blocking;
-use tokio::{fs, sync::mpsc};
-use uuid::Uuid;
-
-use crate::index::{
-    update_handler::UpdateHandler, Checked, Document, SearchQuery, SearchResult, Settings,
-};
-use crate::index_controller::{
-    get_arc_ownership_blocking, Failed, IndexStats, Processed, Processing,
-};
-use crate::option::IndexerOpts;
-
-use super::error::{IndexActorError, Result};
-use super::{IndexMeta, IndexMsg, IndexSettings, IndexStore};
-
-pub const CONCURRENT_INDEX_MSG: usize = 10;
-
-pub struct IndexActor<S> {
-    receiver: Option<mpsc::Receiver<IndexMsg>>,
-    update_handler: Arc<UpdateHandler>,
-    store: S,
-}
-
-impl<S: IndexStore + Sync + Send> IndexActor<S> {
-    pub fn new(
-        receiver: mpsc::Receiver<IndexMsg>,
-        store: S,
-        options: &IndexerOpts,
-    ) -> anyhow::Result<Self> {
-        let update_handler = UpdateHandler::new(options)?;
-        let update_handler = Arc::new(update_handler);
-        let receiver = Some(receiver);
-        Ok(Self {
-            receiver,
-            update_handler,
-            store,
-        })
-    }
-
-    /// `run` poll the write_receiver and read_receiver concurrently, but while messages send
-    /// through the read channel are processed concurrently, the messages sent through the write
-    /// channel are processed one at a time.
-    pub async fn run(mut self) {
-        let mut receiver = self
-            .receiver
-            .take()
-            .expect("Index Actor must have a inbox at this point.");
-
-        let stream = stream! {
-            loop {
-                match receiver.recv().await {
-                    Some(msg) => yield msg,
-                    None => break,
-                }
-            }
-        };
-
-        stream
-            .for_each_concurrent(Some(CONCURRENT_INDEX_MSG), |msg| self.handle_message(msg))
-            .await;
-    }
-
-    async fn handle_message(&self, msg: IndexMsg) {
-        use IndexMsg::*;
-        match msg {
-            CreateIndex {
-                uuid,
-                primary_key,
-                ret,
-            } => {
-                let _ = ret.send(self.handle_create_index(uuid, primary_key).await);
-            }
-            Update {
-                ret,
-                meta,
-                data,
-                uuid,
-            } => {
-                let _ = ret.send(self.handle_update(uuid, meta, data).await);
-            }
-            Search { ret, query, uuid } => {
-                let _ = ret.send(self.handle_search(uuid, query).await);
-            }
-            Settings { ret, uuid } => {
-                let _ = ret.send(self.handle_settings(uuid).await);
-            }
-            Documents {
-                ret,
-                uuid,
-                attributes_to_retrieve,
-                offset,
-                limit,
-            } => {
-                let _ = ret.send(
-                    self.handle_fetch_documents(uuid, offset, limit, attributes_to_retrieve)
-                        .await,
-                );
-            }
-            Document {
-                uuid,
-                attributes_to_retrieve,
-                doc_id,
-                ret,
-            } => {
-                let _ = ret.send(
-                    self.handle_fetch_document(uuid, doc_id, attributes_to_retrieve)
-                        .await,
-                );
-            }
-            Delete { uuid, ret } => {
-                let _ = ret.send(self.handle_delete(uuid).await);
-            }
-            GetMeta { uuid, ret } => {
-                let _ = ret.send(self.handle_get_meta(uuid).await);
-            }
-            UpdateIndex {
-                uuid,
-                index_settings,
-                ret,
-            } => {
-                let _ = ret.send(self.handle_update_index(uuid, index_settings).await);
-            }
-            Snapshot { uuid, path, ret } => {
-                let _ = ret.send(self.handle_snapshot(uuid, path).await);
-            }
-            Dump { uuid, path, ret } => {
-                let _ = ret.send(self.handle_dump(uuid, path).await);
-            }
-            GetStats { uuid, ret } => {
-                let _ = ret.send(self.handle_get_stats(uuid).await);
-            }
-        }
-    }
-
-    async fn handle_search(&self, uuid: Uuid, query: SearchQuery) -> Result<SearchResult> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-        let result = spawn_blocking(move || index.perform_search(query)).await??;
-        Ok(result)
-    }
-
-    async fn handle_create_index(
-        &self,
-        uuid: Uuid,
-        primary_key: Option<String>,
-    ) -> Result<IndexMeta> {
-        let index = self.store.create(uuid, primary_key).await?;
-        let meta = spawn_blocking(move || IndexMeta::new(&index)).await??;
-        Ok(meta)
-    }
-
-    async fn handle_update(
-        &self,
-        uuid: Uuid,
-        meta: Processing,
-        data: Option<File>,
-    ) -> Result<std::result::Result<Processed, Failed>> {
-        debug!("Processing update {}", meta.id());
-        let update_handler = self.update_handler.clone();
-        let index = match self.store.get(uuid).await? {
-            Some(index) => index,
-            None => self.store.create(uuid, None).await?,
-        };
-
-        Ok(spawn_blocking(move || update_handler.handle_update(meta, data, index)).await?)
-    }
-
-    async fn handle_settings(&self, uuid: Uuid) -> Result<Settings<Checked>> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-        let result = spawn_blocking(move || index.settings()).await??;
-        Ok(result)
-    }
-
-    async fn handle_fetch_documents(
-        &self,
-        uuid: Uuid,
-        offset: usize,
-        limit: usize,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Vec<Document>> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-        let result =
-            spawn_blocking(move || index.retrieve_documents(offset, limit, attributes_to_retrieve))
-                .await??;
-
-        Ok(result)
-    }
-
-    async fn handle_fetch_document(
-        &self,
-        uuid: Uuid,
-        doc_id: String,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Document> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-
-        let result =
-            spawn_blocking(move || index.retrieve_document(doc_id, attributes_to_retrieve))
-                .await??;
-
-        Ok(result)
-    }
-
-    async fn handle_delete(&self, uuid: Uuid) -> Result<()> {
-        let index = self.store.delete(uuid).await?;
-
-        if let Some(index) = index {
-            tokio::task::spawn(async move {
-                let index = index.0;
-                let store = get_arc_ownership_blocking(index).await;
-                spawn_blocking(move || {
-                    store.prepare_for_closing().wait();
-                    debug!("Index closed");
-                });
-            });
-        }
-
-        Ok(())
-    }
-
-    async fn handle_get_meta(&self, uuid: Uuid) -> Result<IndexMeta> {
-        match self.store.get(uuid).await? {
-            Some(index) => {
-                let meta = spawn_blocking(move || IndexMeta::new(&index)).await??;
-                Ok(meta)
-            }
-            None => Err(IndexActorError::UnexistingIndex),
-        }
-    }
-
-    async fn handle_update_index(
-        &self,
-        uuid: Uuid,
-        index_settings: IndexSettings,
-    ) -> Result<IndexMeta> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-
-        let result = spawn_blocking(move || match index_settings.primary_key {
-            Some(primary_key) => {
-                let mut txn = index.write_txn()?;
-                if index.primary_key(&txn)?.is_some() {
-                    return Err(IndexActorError::ExistingPrimaryKey);
-                }
-                let mut builder = UpdateBuilder::new(0).settings(&mut txn, &index);
-                builder.set_primary_key(primary_key);
-                builder.execute(|_, _| ())?;
-                let meta = IndexMeta::new_txn(&index, &txn)?;
-                txn.commit()?;
-                Ok(meta)
-            }
-            None => {
-                let meta = IndexMeta::new(&index)?;
-                Ok(meta)
-            }
-        })
-        .await??;
-
-        Ok(result)
-    }
-
-    async fn handle_snapshot(&self, uuid: Uuid, mut path: PathBuf) -> Result<()> {
-        use tokio::fs::create_dir_all;
-
-        path.push("indexes");
-        create_dir_all(&path).await?;
-
-        if let Some(index) = self.store.get(uuid).await? {
-            let mut index_path = path.join(format!("index-{}", uuid));
-
-            create_dir_all(&index_path).await?;
-
-            index_path.push("data.mdb");
-            spawn_blocking(move || -> Result<()> {
-                // Get write txn to wait for ongoing write transaction before snapshot.
-                let _txn = index.write_txn()?;
-                index
-                    .env
-                    .copy_to_path(index_path, CompactionOption::Enabled)?;
-                Ok(())
-            })
-            .await??;
-        }
-
-        Ok(())
-    }
-
-    /// Create a `documents.jsonl` and a `settings.json` in `path/uid/` with a dump of all the
-    /// documents and all the settings.
-    async fn handle_dump(&self, uuid: Uuid, path: PathBuf) -> Result<()> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-
-        let path = path.join(format!("indexes/index-{}/", uuid));
-        fs::create_dir_all(&path).await?;
-
-        tokio::task::spawn_blocking(move || index.dump(path)).await??;
-
-        Ok(())
-    }
-
-    async fn handle_get_stats(&self, uuid: Uuid) -> Result<IndexStats> {
-        let index = self
-            .store
-            .get(uuid)
-            .await?
-            .ok_or(IndexActorError::UnexistingIndex)?;
-
-        spawn_blocking(move || {
-            let rtxn = index.read_txn()?;
-
-            Ok(IndexStats {
-                size: index.size(),
-                number_of_documents: index.number_of_documents(&rtxn)?,
-                is_indexing: None,
-                field_distribution: index.field_distribution(&rtxn)?,
-            })
-        })
-        .await?
-    }
-}

meilisearch-http/src/index_controller/index_actor/error.rs

@@ -1,48 +0,0 @@
-use meilisearch_error::{Code, ErrorCode};
-
-use crate::{error::MilliError, index::error::IndexError};
-
-pub type Result<T> = std::result::Result<T, IndexActorError>;
-
-#[derive(thiserror::Error, Debug)]
-pub enum IndexActorError {
-    #[error("{0}")]
-    IndexError(#[from] IndexError),
-    #[error("Index already exists")]
-    IndexAlreadyExists,
-    #[error("Index not found")]
-    UnexistingIndex,
-    #[error("A primary key is already present. It's impossible to update it")]
-    ExistingPrimaryKey,
-    #[error("Internal Error: {0}")]
-    Internal(Box<dyn std::error::Error + Send + Sync + 'static>),
-    #[error("{0}")]
-    Milli(#[from] milli::Error),
-}
-
-macro_rules! internal_error {
-    ($($other:path), *) => {
-        $(
-            impl From<$other> for IndexActorError {
-                fn from(other: $other) -> Self {
-                    Self::Internal(Box::new(other))
-                }
-            }
-        )*
-    }
-}
-
-internal_error!(heed::Error, tokio::task::JoinError, std::io::Error);
-
-impl ErrorCode for IndexActorError {
-    fn error_code(&self) -> Code {
-        match self {
-            IndexActorError::IndexError(e) => e.error_code(),
-            IndexActorError::IndexAlreadyExists => Code::IndexAlreadyExists,
-            IndexActorError::UnexistingIndex => Code::IndexNotFound,
-            IndexActorError::ExistingPrimaryKey => Code::PrimaryKeyAlreadyPresent,
-            IndexActorError::Internal(_) => Code::Internal,
-            IndexActorError::Milli(e) => MilliError(e).error_code(),
-        }
-    }
-}

meilisearch-http/src/index_controller/index_actor/handle_impl.rs

@@ -1,164 +0,0 @@
-use crate::option::IndexerOpts;
-use std::path::{Path, PathBuf};
-
-use tokio::sync::{mpsc, oneshot};
-use uuid::Uuid;
-
-use crate::{
-    index::Checked,
-    index_controller::{IndexSettings, IndexStats, Processing},
-};
-use crate::{
-    index::{Document, SearchQuery, SearchResult, Settings},
-    index_controller::{Failed, Processed},
-};
-
-use super::error::Result;
-use super::{IndexActor, IndexActorHandle, IndexMeta, IndexMsg, MapIndexStore};
-
-#[derive(Clone)]
-pub struct IndexActorHandleImpl {
-    sender: mpsc::Sender<IndexMsg>,
-}
-
-#[async_trait::async_trait]
-impl IndexActorHandle for IndexActorHandleImpl {
-    async fn create_index(&self, uuid: Uuid, primary_key: Option<String>) -> Result<IndexMeta> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::CreateIndex {
-            ret,
-            uuid,
-            primary_key,
-        };
-        let _ = self.sender.send(msg).await;
-        receiver.await.expect("IndexActor has been killed")
-    }
-
-    async fn update(
-        &self,
-        uuid: Uuid,
-        meta: Processing,
-        data: Option<std::fs::File>,
-    ) -> Result<std::result::Result<Processed, Failed>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Update {
-            ret,
-            meta,
-            data,
-            uuid,
-        };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn search(&self, uuid: Uuid, query: SearchQuery) -> Result<SearchResult> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Search { uuid, query, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn settings(&self, uuid: Uuid) -> Result<Settings<Checked>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Settings { uuid, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn documents(
-        &self,
-        uuid: Uuid,
-        offset: usize,
-        limit: usize,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Vec<Document>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Documents {
-            uuid,
-            ret,
-            offset,
-            attributes_to_retrieve,
-            limit,
-        };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn document(
-        &self,
-        uuid: Uuid,
-        doc_id: String,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Document> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Document {
-            uuid,
-            ret,
-            doc_id,
-            attributes_to_retrieve,
-        };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn delete(&self, uuid: Uuid) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Delete { uuid, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn get_index_meta(&self, uuid: Uuid) -> Result<IndexMeta> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::GetMeta { uuid, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn update_index(&self, uuid: Uuid, index_settings: IndexSettings) -> Result<IndexMeta> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::UpdateIndex {
-            uuid,
-            index_settings,
-            ret,
-        };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn snapshot(&self, uuid: Uuid, path: PathBuf) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Snapshot { uuid, path, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn dump(&self, uuid: Uuid, path: PathBuf) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::Dump { uuid, path, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-
-    async fn get_index_stats(&self, uuid: Uuid) -> Result<IndexStats> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = IndexMsg::GetStats { uuid, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver.await.expect("IndexActor has been killed")?)
-    }
-}
-
-impl IndexActorHandleImpl {
-    pub fn new(
-        path: impl AsRef<Path>,
-        index_size: usize,
-        options: &IndexerOpts,
-    ) -> anyhow::Result<Self> {
-        let (sender, receiver) = mpsc::channel(100);
-
-        let store = MapIndexStore::new(path, index_size);
-        let actor = IndexActor::new(receiver, store, options)?;
-        tokio::task::spawn(actor.run());
-        Ok(Self { sender })
-    }
-}

meilisearch-http/src/index_controller/index_actor/message.rs

@@ -1,74 +0,0 @@
-use std::path::PathBuf;
-
-use tokio::sync::oneshot;
-use uuid::Uuid;
-
-use super::error::Result as IndexResult;
-use crate::index::{Checked, Document, SearchQuery, SearchResult, Settings};
-use crate::index_controller::{Failed, IndexStats, Processed, Processing};
-
-use super::{IndexMeta, IndexSettings};
-
-#[allow(clippy::large_enum_variant)]
-pub enum IndexMsg {
-    CreateIndex {
-        uuid: Uuid,
-        primary_key: Option<String>,
-        ret: oneshot::Sender<IndexResult<IndexMeta>>,
-    },
-    Update {
-        uuid: Uuid,
-        meta: Processing,
-        data: Option<std::fs::File>,
-        ret: oneshot::Sender<IndexResult<Result<Processed, Failed>>>,
-    },
-    Search {
-        uuid: Uuid,
-        query: SearchQuery,
-        ret: oneshot::Sender<IndexResult<SearchResult>>,
-    },
-    Settings {
-        uuid: Uuid,
-        ret: oneshot::Sender<IndexResult<Settings<Checked>>>,
-    },
-    Documents {
-        uuid: Uuid,
-        attributes_to_retrieve: Option<Vec<String>>,
-        offset: usize,
-        limit: usize,
-        ret: oneshot::Sender<IndexResult<Vec<Document>>>,
-    },
-    Document {
-        uuid: Uuid,
-        attributes_to_retrieve: Option<Vec<String>>,
-        doc_id: String,
-        ret: oneshot::Sender<IndexResult<Document>>,
-    },
-    Delete {
-        uuid: Uuid,
-        ret: oneshot::Sender<IndexResult<()>>,
-    },
-    GetMeta {
-        uuid: Uuid,
-        ret: oneshot::Sender<IndexResult<IndexMeta>>,
-    },
-    UpdateIndex {
-        uuid: Uuid,
-        index_settings: IndexSettings,
-        ret: oneshot::Sender<IndexResult<IndexMeta>>,
-    },
-    Snapshot {
-        uuid: Uuid,
-        path: PathBuf,
-        ret: oneshot::Sender<IndexResult<()>>,
-    },
-    Dump {
-        uuid: Uuid,
-        path: PathBuf,
-        ret: oneshot::Sender<IndexResult<()>>,
-    },
-    GetStats {
-        uuid: Uuid,
-        ret: oneshot::Sender<IndexResult<IndexStats>>,
-    },
-}

meilisearch-http/src/index_controller/index_actor/mod.rs

@@ -1,169 +0,0 @@
-use std::fs::File;
-use std::path::PathBuf;
-
-use chrono::{DateTime, Utc};
-#[cfg(test)]
-use mockall::automock;
-use serde::{Deserialize, Serialize};
-use uuid::Uuid;
-
-use actor::IndexActor;
-pub use actor::CONCURRENT_INDEX_MSG;
-pub use handle_impl::IndexActorHandleImpl;
-use message::IndexMsg;
-use store::{IndexStore, MapIndexStore};
-
-use crate::index::{Checked, Document, Index, SearchQuery, SearchResult, Settings};
-use crate::index_controller::{Failed, IndexStats, Processed, Processing};
-use error::Result;
-
-use super::IndexSettings;
-
-mod actor;
-pub mod error;
-mod handle_impl;
-mod message;
-mod store;
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct IndexMeta {
-    created_at: DateTime<Utc>,
-    pub updated_at: DateTime<Utc>,
-    pub primary_key: Option<String>,
-}
-
-impl IndexMeta {
-    fn new(index: &Index) -> Result<Self> {
-        let txn = index.read_txn()?;
-        Self::new_txn(index, &txn)
-    }
-
-    fn new_txn(index: &Index, txn: &heed::RoTxn) -> Result<Self> {
-        let created_at = index.created_at(txn)?;
-        let updated_at = index.updated_at(txn)?;
-        let primary_key = index.primary_key(txn)?.map(String::from);
-        Ok(Self {
-            created_at,
-            updated_at,
-            primary_key,
-        })
-    }
-}
-
-#[async_trait::async_trait]
-#[cfg_attr(test, automock)]
-pub trait IndexActorHandle {
-    async fn create_index(&self, uuid: Uuid, primary_key: Option<String>) -> Result<IndexMeta>;
-    async fn update(
-        &self,
-        uuid: Uuid,
-        meta: Processing,
-        data: Option<File>,
-    ) -> Result<std::result::Result<Processed, Failed>>;
-    async fn search(&self, uuid: Uuid, query: SearchQuery) -> Result<SearchResult>;
-    async fn settings(&self, uuid: Uuid) -> Result<Settings<Checked>>;
-
-    async fn documents(
-        &self,
-        uuid: Uuid,
-        offset: usize,
-        limit: usize,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Vec<Document>>;
-    async fn document(
-        &self,
-        uuid: Uuid,
-        doc_id: String,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Document>;
-    async fn delete(&self, uuid: Uuid) -> Result<()>;
-    async fn get_index_meta(&self, uuid: Uuid) -> Result<IndexMeta>;
-    async fn update_index(&self, uuid: Uuid, index_settings: IndexSettings) -> Result<IndexMeta>;
-    async fn snapshot(&self, uuid: Uuid, path: PathBuf) -> Result<()>;
-    async fn dump(&self, uuid: Uuid, path: PathBuf) -> Result<()>;
-    async fn get_index_stats(&self, uuid: Uuid) -> Result<IndexStats>;
-}
-
-#[cfg(test)]
-mod test {
-    use std::sync::Arc;
-
-    use super::*;
-
-    #[async_trait::async_trait]
-    /// Useful for passing around an `Arc<MockIndexActorHandle>` in tests.
-    impl IndexActorHandle for Arc<MockIndexActorHandle> {
-        async fn create_index(&self, uuid: Uuid, primary_key: Option<String>) -> Result<IndexMeta> {
-            self.as_ref().create_index(uuid, primary_key).await
-        }
-
-        async fn update(
-            &self,
-            uuid: Uuid,
-            meta: Processing,
-            data: Option<std::fs::File>,
-        ) -> Result<std::result::Result<Processed, Failed>> {
-            self.as_ref().update(uuid, meta, data).await
-        }
-
-        async fn search(&self, uuid: Uuid, query: SearchQuery) -> Result<SearchResult> {
-            self.as_ref().search(uuid, query).await
-        }
-
-        async fn settings(&self, uuid: Uuid) -> Result<Settings<Checked>> {
-            self.as_ref().settings(uuid).await
-        }
-
-        async fn documents(
-            &self,
-            uuid: Uuid,
-            offset: usize,
-            limit: usize,
-            attributes_to_retrieve: Option<Vec<String>>,
-        ) -> Result<Vec<Document>> {
-            self.as_ref()
-                .documents(uuid, offset, limit, attributes_to_retrieve)
-                .await
-        }
-
-        async fn document(
-            &self,
-            uuid: Uuid,
-            doc_id: String,
-            attributes_to_retrieve: Option<Vec<String>>,
-        ) -> Result<Document> {
-            self.as_ref()
-                .document(uuid, doc_id, attributes_to_retrieve)
-                .await
-        }
-
-        async fn delete(&self, uuid: Uuid) -> Result<()> {
-            self.as_ref().delete(uuid).await
-        }
-
-        async fn get_index_meta(&self, uuid: Uuid) -> Result<IndexMeta> {
-            self.as_ref().get_index_meta(uuid).await
-        }
-
-        async fn update_index(
-            &self,
-            uuid: Uuid,
-            index_settings: IndexSettings,
-        ) -> Result<IndexMeta> {
-            self.as_ref().update_index(uuid, index_settings).await
-        }
-
-        async fn snapshot(&self, uuid: Uuid, path: PathBuf) -> Result<()> {
-            self.as_ref().snapshot(uuid, path).await
-        }
-
-        async fn dump(&self, uuid: Uuid, path: PathBuf) -> Result<()> {
-            self.as_ref().dump(uuid, path).await
-        }
-
-        async fn get_index_stats(&self, uuid: Uuid) -> Result<IndexStats> {
-            self.as_ref().get_index_stats(uuid).await
-        }
-    }
-}

meilisearch-http/src/index_controller/mod.rs

@@ -1,456 +0,0 @@
-use std::collections::BTreeMap;
-use std::path::Path;
-use std::sync::Arc;
-use std::time::Duration;
-
-use actix_web::web::Bytes;
-use chrono::{DateTime, Utc};
-use futures::stream::StreamExt;
-use log::error;
-use log::info;
-use milli::FieldDistribution;
-use serde::{Deserialize, Serialize};
-use tokio::sync::mpsc;
-use tokio::time::sleep;
-use uuid::Uuid;
-
-use dump_actor::DumpActorHandle;
-pub use dump_actor::{DumpInfo, DumpStatus};
-use index_actor::IndexActorHandle;
-use snapshot::{load_snapshot, SnapshotService};
-use update_actor::UpdateActorHandle;
-pub use updates::*;
-use uuid_resolver::{error::UuidResolverError, UuidResolverHandle};
-
-use crate::extractors::payload::Payload;
-use crate::index::{Checked, Document, SearchQuery, SearchResult, Settings};
-use crate::option::Opt;
-use error::Result;
-
-use self::dump_actor::load_dump;
-use self::error::IndexControllerError;
-
-mod dump_actor;
-pub mod error;
-pub mod index_actor;
-mod snapshot;
-mod update_actor;
-mod updates;
-mod uuid_resolver;
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct IndexMetadata {
-    #[serde(skip)]
-    pub uuid: Uuid,
-    pub uid: String,
-    name: String,
-    #[serde(flatten)]
-    pub meta: index_actor::IndexMeta,
-}
-
-#[derive(Clone, Debug)]
-pub struct IndexSettings {
-    pub uid: Option<String>,
-    pub primary_key: Option<String>,
-}
-
-#[derive(Serialize, Debug)]
-#[serde(rename_all = "camelCase")]
-pub struct IndexStats {
-    #[serde(skip)]
-    pub size: u64,
-    pub number_of_documents: u64,
-    /// Whether the current index is performing an update. It is initially `None` when the
-    /// index returns it, since it is the `UpdateStore` that knows what index is currently indexing. It is
-    /// later set to either true or false, we we retrieve the information from the `UpdateStore`
-    pub is_indexing: Option<bool>,
-    pub field_distribution: FieldDistribution,
-}
-
-#[derive(Clone)]
-pub struct IndexController {
-    uuid_resolver: uuid_resolver::UuidResolverHandleImpl,
-    index_handle: index_actor::IndexActorHandleImpl,
-    update_handle: update_actor::UpdateActorHandleImpl<Bytes>,
-    dump_handle: dump_actor::DumpActorHandleImpl,
-}
-
-#[derive(Serialize, Debug)]
-#[serde(rename_all = "camelCase")]
-pub struct Stats {
-    pub database_size: u64,
-    pub last_update: Option<DateTime<Utc>>,
-    pub indexes: BTreeMap<String, IndexStats>,
-}
-
-impl IndexController {
-    pub fn new(path: impl AsRef<Path>, options: &Opt) -> anyhow::Result<Self> {
-        let index_size = options.max_index_size.get_bytes() as usize;
-        let update_store_size = options.max_index_size.get_bytes() as usize;
-
-        if let Some(ref path) = options.import_snapshot {
-            info!("Loading from snapshot {:?}", path);
-            load_snapshot(
-                &options.db_path,
-                path,
-                options.ignore_snapshot_if_db_exists,
-                options.ignore_missing_snapshot,
-            )?;
-        } else if let Some(ref src_path) = options.import_dump {
-            load_dump(
-                &options.db_path,
-                src_path,
-                options.max_index_size.get_bytes() as usize,
-                options.max_udb_size.get_bytes() as usize,
-                &options.indexer_options,
-            )?;
-        }
-
-        std::fs::create_dir_all(&path)?;
-
-        let uuid_resolver = uuid_resolver::UuidResolverHandleImpl::new(&path)?;
-        let index_handle =
-            index_actor::IndexActorHandleImpl::new(&path, index_size, &options.indexer_options)?;
-        let update_handle = update_actor::UpdateActorHandleImpl::new(
-            index_handle.clone(),
-            &path,
-            update_store_size,
-        )?;
-        let dump_handle = dump_actor::DumpActorHandleImpl::new(
-            &options.dumps_dir,
-            uuid_resolver.clone(),
-            update_handle.clone(),
-            options.max_index_size.get_bytes() as usize,
-            options.max_udb_size.get_bytes() as usize,
-        )?;
-
-        if options.schedule_snapshot {
-            let snapshot_service = SnapshotService::new(
-                uuid_resolver.clone(),
-                update_handle.clone(),
-                Duration::from_secs(options.snapshot_interval_sec),
-                options.snapshot_dir.clone(),
-                options
-                    .db_path
-                    .file_name()
-                    .map(|n| n.to_owned().into_string().expect("invalid path"))
-                    .unwrap_or_else(|| String::from("data.ms")),
-            );
-
-            tokio::task::spawn(snapshot_service.run());
-        }
-
-        Ok(Self {
-            uuid_resolver,
-            index_handle,
-            update_handle,
-            dump_handle,
-        })
-    }
-
-    pub async fn add_documents(
-        &self,
-        uid: String,
-        method: milli::update::IndexDocumentsMethod,
-        format: milli::update::UpdateFormat,
-        payload: Payload,
-        primary_key: Option<String>,
-    ) -> Result<UpdateStatus> {
-        let perform_update = |uuid| async move {
-            let meta = UpdateMeta::DocumentsAddition {
-                method,
-                format,
-                primary_key,
-            };
-            let (sender, receiver) = mpsc::channel(10);
-
-            // It is necessary to spawn a local task to send the payload to the update handle to
-            // prevent dead_locking between the update_handle::update that waits for the update to be
-            // registered and the update_actor that waits for the the payload to be sent to it.
-            tokio::task::spawn_local(async move {
-                payload
-                    .for_each(|r| async {
-                        let _ = sender.send(r).await;
-                    })
-                    .await
-            });
-
-            // This must be done *AFTER* spawning the task.
-            self.update_handle.update(meta, receiver, uuid).await
-        };
-
-        match self.uuid_resolver.get(uid).await {
-            Ok(uuid) => Ok(perform_update(uuid).await?),
-            Err(UuidResolverError::UnexistingIndex(name)) => {
-                let uuid = Uuid::new_v4();
-                let status = perform_update(uuid).await?;
-                // ignore if index creation fails now, since it may already have been created
-                let _ = self.index_handle.create_index(uuid, None).await;
-                self.uuid_resolver.insert(name, uuid).await?;
-                Ok(status)
-            }
-            Err(e) => Err(e.into()),
-        }
-    }
-
-    pub async fn clear_documents(&self, uid: String) -> Result<UpdateStatus> {
-        let uuid = self.uuid_resolver.get(uid).await?;
-        let meta = UpdateMeta::ClearDocuments;
-        let (_, receiver) = mpsc::channel(1);
-        let status = self.update_handle.update(meta, receiver, uuid).await?;
-        Ok(status)
-    }
-
-    pub async fn delete_documents(
-        &self,
-        uid: String,
-        documents: Vec<String>,
-    ) -> Result<UpdateStatus> {
-        let uuid = self.uuid_resolver.get(uid).await?;
-        let meta = UpdateMeta::DeleteDocuments { ids: documents };
-        let (_, receiver) = mpsc::channel(1);
-        let status = self.update_handle.update(meta, receiver, uuid).await?;
-        Ok(status)
-    }
-
-    pub async fn update_settings(
-        &self,
-        uid: String,
-        settings: Settings<Checked>,
-        create: bool,
-    ) -> Result<UpdateStatus> {
-        let perform_udpate = |uuid| async move {
-            let meta = UpdateMeta::Settings(settings.into_unchecked());
-            // Nothing so send, drop the sender right away, as not to block the update actor.
-            let (_, receiver) = mpsc::channel(1);
-            self.update_handle.update(meta, receiver, uuid).await
-        };
-
-        match self.uuid_resolver.get(uid).await {
-            Ok(uuid) => Ok(perform_udpate(uuid).await?),
-            Err(UuidResolverError::UnexistingIndex(name)) if create => {
-                let uuid = Uuid::new_v4();
-                let status = perform_udpate(uuid).await?;
-                // ignore if index creation fails now, since it may already have been created
-                let _ = self.index_handle.create_index(uuid, None).await;
-                self.uuid_resolver.insert(name, uuid).await?;
-                Ok(status)
-            }
-            Err(e) => Err(e.into()),
-        }
-    }
-
-    pub async fn create_index(&self, index_settings: IndexSettings) -> Result<IndexMetadata> {
-        let IndexSettings { uid, primary_key } = index_settings;
-        let uid = uid.ok_or(IndexControllerError::MissingUid)?;
-        let uuid = Uuid::new_v4();
-        let meta = self.index_handle.create_index(uuid, primary_key).await?;
-        self.uuid_resolver.insert(uid.clone(), uuid).await?;
-        let meta = IndexMetadata {
-            uuid,
-            name: uid.clone(),
-            uid,
-            meta,
-        };
-
-        Ok(meta)
-    }
-
-    pub async fn delete_index(&self, uid: String) -> Result<()> {
-        let uuid = self.uuid_resolver.delete(uid).await?;
-
-        // We remove the index from the resolver synchronously, and effectively perform the index
-        // deletion as a background task.
-        let update_handle = self.update_handle.clone();
-        let index_handle = self.index_handle.clone();
-        tokio::spawn(async move {
-            if let Err(e) = update_handle.delete(uuid).await {
-                error!("Error while deleting index: {}", e);
-            }
-            if let Err(e) = index_handle.delete(uuid).await {
-                error!("Error while deleting index: {}", e);
-            }
-        });
-
-        Ok(())
-    }
-
-    pub async fn update_status(&self, uid: String, id: u64) -> Result<UpdateStatus> {
-        let uuid = self.uuid_resolver.get(uid).await?;
-        let result = self.update_handle.update_status(uuid, id).await?;
-        Ok(result)
-    }
-
-    pub async fn all_update_status(&self, uid: String) -> Result<Vec<UpdateStatus>> {
-        let uuid = self.uuid_resolver.get(uid).await?;
-        let result = self.update_handle.get_all_updates_status(uuid).await?;
-        Ok(result)
-    }
-
-    pub async fn list_indexes(&self) -> Result<Vec<IndexMetadata>> {
-        let uuids = self.uuid_resolver.list().await?;
-
-        let mut ret = Vec::new();
-
-        for (uid, uuid) in uuids {
-            let meta = self.index_handle.get_index_meta(uuid).await?;
-            let meta = IndexMetadata {
-                uuid,
-                name: uid.clone(),
-                uid,
-                meta,
-            };
-            ret.push(meta);
-        }
-
-        Ok(ret)
-    }
-
-    pub async fn settings(&self, uid: String) -> Result<Settings<Checked>> {
-        let uuid = self.uuid_resolver.get(uid.clone()).await?;
-        let settings = self.index_handle.settings(uuid).await?;
-        Ok(settings)
-    }
-
-    pub async fn documents(
-        &self,
-        uid: String,
-        offset: usize,
-        limit: usize,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Vec<Document>> {
-        let uuid = self.uuid_resolver.get(uid.clone()).await?;
-        let documents = self
-            .index_handle
-            .documents(uuid, offset, limit, attributes_to_retrieve)
-            .await?;
-        Ok(documents)
-    }
-
-    pub async fn document(
-        &self,
-        uid: String,
-        doc_id: String,
-        attributes_to_retrieve: Option<Vec<String>>,
-    ) -> Result<Document> {
-        let uuid = self.uuid_resolver.get(uid.clone()).await?;
-        let document = self
-            .index_handle
-            .document(uuid, doc_id, attributes_to_retrieve)
-            .await?;
-        Ok(document)
-    }
-
-    pub async fn update_index(
-        &self,
-        uid: String,
-        mut index_settings: IndexSettings,
-    ) -> Result<IndexMetadata> {
-        if index_settings.uid.is_some() {
-            index_settings.uid.take();
-        }
-
-        let uuid = self.uuid_resolver.get(uid.clone()).await?;
-        let meta = self.index_handle.update_index(uuid, index_settings).await?;
-        let meta = IndexMetadata {
-            uuid,
-            name: uid.clone(),
-            uid,
-            meta,
-        };
-        Ok(meta)
-    }
-
-    pub async fn search(&self, uid: String, query: SearchQuery) -> Result<SearchResult> {
-        let uuid = self.uuid_resolver.get(uid).await?;
-        let result = self.index_handle.search(uuid, query).await?;
-        Ok(result)
-    }
-
-    pub async fn get_index(&self, uid: String) -> Result<IndexMetadata> {
-        let uuid = self.uuid_resolver.get(uid.clone()).await?;
-        let meta = self.index_handle.get_index_meta(uuid).await?;
-        let meta = IndexMetadata {
-            uuid,
-            name: uid.clone(),
-            uid,
-            meta,
-        };
-        Ok(meta)
-    }
-
-    pub async fn get_uuids_size(&self) -> Result<u64> {
-        Ok(self.uuid_resolver.get_size().await?)
-    }
-
-    pub async fn get_index_stats(&self, uid: String) -> Result<IndexStats> {
-        let uuid = self.uuid_resolver.get(uid).await?;
-        let update_infos = self.update_handle.get_info().await?;
-        let mut stats = self.index_handle.get_index_stats(uuid).await?;
-        // Check if the currently indexing update is from out index.
-        stats.is_indexing = Some(Some(uuid) == update_infos.processing);
-        Ok(stats)
-    }
-
-    pub async fn get_all_stats(&self) -> Result<Stats> {
-        let update_infos = self.update_handle.get_info().await?;
-        let mut database_size = self.get_uuids_size().await? + update_infos.size;
-        let mut last_update: Option<DateTime<_>> = None;
-        let mut indexes = BTreeMap::new();
-
-        for index in self.list_indexes().await? {
-            let mut index_stats = self.index_handle.get_index_stats(index.uuid).await?;
-            database_size += index_stats.size;
-
-            last_update = last_update.map_or(Some(index.meta.updated_at), |last| {
-                Some(last.max(index.meta.updated_at))
-            });
-
-            index_stats.is_indexing = Some(Some(index.uuid) == update_infos.processing);
-
-            indexes.insert(index.uid, index_stats);
-        }
-
-        Ok(Stats {
-            database_size,
-            last_update,
-            indexes,
-        })
-    }
-
-    pub async fn create_dump(&self) -> Result<DumpInfo> {
-        Ok(self.dump_handle.create_dump().await?)
-    }
-
-    pub async fn dump_info(&self, uid: String) -> Result<DumpInfo> {
-        Ok(self.dump_handle.dump_info(uid).await?)
-    }
-}
-
-pub async fn get_arc_ownership_blocking<T>(mut item: Arc<T>) -> T {
-    loop {
-        match Arc::try_unwrap(item) {
-            Ok(item) => return item,
-            Err(item_arc) => {
-                item = item_arc;
-                sleep(Duration::from_millis(100)).await;
-                continue;
-            }
-        }
-    }
-}
-
-/// Parses the v1 version of the Asc ranking rules `asc(price)`and returns the field name.
-pub fn asc_ranking_rule(text: &str) -> Option<&str> {
-    text.split_once("asc(")
-        .and_then(|(_, tail)| tail.rsplit_once(")"))
-        .map(|(field, _)| field)
-}
-
-/// Parses the v1 version of the Desc ranking rules `asc(price)`and returns the field name.
-pub fn desc_ranking_rule(text: &str) -> Option<&str> {
-    text.split_once("desc(")
-        .and_then(|(_, tail)| tail.rsplit_once(")"))
-        .map(|(field, _)| field)
-}

meilisearch-http/src/index_controller/snapshot.rs

@@ -1,268 +0,0 @@
-use std::path::{Path, PathBuf};
-use std::time::Duration;
-
-use anyhow::bail;
-use log::{error, info, trace};
-use tokio::fs;
-use tokio::task::spawn_blocking;
-use tokio::time::sleep;
-
-use super::update_actor::UpdateActorHandle;
-use super::uuid_resolver::UuidResolverHandle;
-use crate::helpers::compression;
-
-pub struct SnapshotService<U, R> {
-    uuid_resolver_handle: R,
-    update_handle: U,
-    snapshot_period: Duration,
-    snapshot_path: PathBuf,
-    db_name: String,
-}
-
-impl<U, R> SnapshotService<U, R>
-where
-    U: UpdateActorHandle,
-    R: UuidResolverHandle,
-{
-    pub fn new(
-        uuid_resolver_handle: R,
-        update_handle: U,
-        snapshot_period: Duration,
-        snapshot_path: PathBuf,
-        db_name: String,
-    ) -> Self {
-        Self {
-            uuid_resolver_handle,
-            update_handle,
-            snapshot_period,
-            snapshot_path,
-            db_name,
-        }
-    }
-
-    pub async fn run(self) {
-        info!(
-            "Snapshot scheduled every {}s.",
-            self.snapshot_period.as_secs()
-        );
-        loop {
-            if let Err(e) = self.perform_snapshot().await {
-                error!("Error while performing snapshot: {}", e);
-            }
-            sleep(self.snapshot_period).await;
-        }
-    }
-
-    async fn perform_snapshot(&self) -> anyhow::Result<()> {
-        trace!("Performing snapshot.");
-
-        let snapshot_dir = self.snapshot_path.clone();
-        fs::create_dir_all(&snapshot_dir).await?;
-        let temp_snapshot_dir =
-            spawn_blocking(move || tempfile::tempdir_in(snapshot_dir)).await??;
-        let temp_snapshot_path = temp_snapshot_dir.path().to_owned();
-
-        let uuids = self
-            .uuid_resolver_handle
-            .snapshot(temp_snapshot_path.clone())
-            .await?;
-
-        if uuids.is_empty() {
-            return Ok(());
-        }
-
-        self.update_handle
-            .snapshot(uuids, temp_snapshot_path.clone())
-            .await?;
-        let snapshot_dir = self.snapshot_path.clone();
-        let snapshot_path = self
-            .snapshot_path
-            .join(format!("{}.snapshot", self.db_name));
-        let snapshot_path = spawn_blocking(move || -> anyhow::Result<PathBuf> {
-            let temp_snapshot_file = tempfile::NamedTempFile::new_in(snapshot_dir)?;
-            let temp_snapshot_file_path = temp_snapshot_file.path().to_owned();
-            compression::to_tar_gz(temp_snapshot_path, temp_snapshot_file_path)?;
-            temp_snapshot_file.persist(&snapshot_path)?;
-            Ok(snapshot_path)
-        })
-        .await??;
-
-        trace!("Created snapshot in {:?}.", snapshot_path);
-
-        Ok(())
-    }
-}
-
-pub fn load_snapshot(
-    db_path: impl AsRef<Path>,
-    snapshot_path: impl AsRef<Path>,
-    ignore_snapshot_if_db_exists: bool,
-    ignore_missing_snapshot: bool,
-) -> anyhow::Result<()> {
-    if !db_path.as_ref().exists() && snapshot_path.as_ref().exists() {
-        match compression::from_tar_gz(snapshot_path, &db_path) {
-            Ok(()) => Ok(()),
-            Err(e) => {
-                // clean created db folder
-                std::fs::remove_dir_all(&db_path)?;
-                Err(e)
-            }
-        }
-    } else if db_path.as_ref().exists() && !ignore_snapshot_if_db_exists {
-        bail!(
-            "database already exists at {:?}, try to delete it or rename it",
-            db_path
-                .as_ref()
-                .canonicalize()
-                .unwrap_or_else(|_| db_path.as_ref().to_owned())
-        )
-    } else if !snapshot_path.as_ref().exists() && !ignore_missing_snapshot {
-        bail!(
-            "snapshot doesn't exist at {:?}",
-            snapshot_path
-                .as_ref()
-                .canonicalize()
-                .unwrap_or_else(|_| snapshot_path.as_ref().to_owned())
-        )
-    } else {
-        Ok(())
-    }
-}
-
-#[cfg(test)]
-mod test {
-    use std::iter::FromIterator;
-    use std::{collections::HashSet, sync::Arc};
-
-    use futures::future::{err, ok};
-    use rand::Rng;
-    use tokio::time::timeout;
-    use uuid::Uuid;
-
-    use super::*;
-    use crate::index_controller::index_actor::MockIndexActorHandle;
-    use crate::index_controller::update_actor::{
-        error::UpdateActorError, MockUpdateActorHandle, UpdateActorHandleImpl,
-    };
-    use crate::index_controller::uuid_resolver::{
-        error::UuidResolverError, MockUuidResolverHandle,
-    };
-
-    #[actix_rt::test]
-    async fn test_normal() {
-        let mut rng = rand::thread_rng();
-        let uuids_num: usize = rng.gen_range(5, 10);
-        let uuids = (0..uuids_num)
-            .map(|_| Uuid::new_v4())
-            .collect::<HashSet<_>>();
-
-        let mut uuid_resolver = MockUuidResolverHandle::new();
-        let uuids_clone = uuids.clone();
-        uuid_resolver
-            .expect_snapshot()
-            .times(1)
-            .returning(move |_| Box::pin(ok(uuids_clone.clone())));
-
-        let uuids_clone = uuids.clone();
-        let mut index_handle = MockIndexActorHandle::new();
-        index_handle
-            .expect_snapshot()
-            .withf(move |uuid, _path| uuids_clone.contains(uuid))
-            .times(uuids_num)
-            .returning(move |_, _| Box::pin(ok(())));
-
-        let dir = tempfile::tempdir_in(".").unwrap();
-        let handle = Arc::new(index_handle);
-        let update_handle =
-            UpdateActorHandleImpl::<Vec<u8>>::new(handle.clone(), dir.path(), 4096 * 100).unwrap();
-
-        let snapshot_path = tempfile::tempdir_in(".").unwrap();
-        let snapshot_service = SnapshotService::new(
-            uuid_resolver,
-            update_handle,
-            Duration::from_millis(100),
-            snapshot_path.path().to_owned(),
-            "data.ms".to_string(),
-        );
-
-        snapshot_service.perform_snapshot().await.unwrap();
-    }
-
-    #[actix_rt::test]
-    async fn error_performing_uuid_snapshot() {
-        let mut uuid_resolver = MockUuidResolverHandle::new();
-        uuid_resolver
-            .expect_snapshot()
-            .times(1)
-            // abitrary error
-            .returning(|_| Box::pin(err(UuidResolverError::NameAlreadyExist)));
-
-        let update_handle = MockUpdateActorHandle::new();
-
-        let snapshot_path = tempfile::tempdir_in(".").unwrap();
-        let snapshot_service = SnapshotService::new(
-            uuid_resolver,
-            update_handle,
-            Duration::from_millis(100),
-            snapshot_path.path().to_owned(),
-            "data.ms".to_string(),
-        );
-
-        assert!(snapshot_service.perform_snapshot().await.is_err());
-        // Nothing was written to the file
-        assert!(!snapshot_path.path().join("data.ms.snapshot").exists());
-    }
-
-    #[actix_rt::test]
-    async fn error_performing_index_snapshot() {
-        let uuid = Uuid::new_v4();
-        let mut uuid_resolver = MockUuidResolverHandle::new();
-        uuid_resolver
-            .expect_snapshot()
-            .times(1)
-            .returning(move |_| Box::pin(ok(HashSet::from_iter(Some(uuid)))));
-
-        let mut update_handle = MockUpdateActorHandle::new();
-        update_handle
-            .expect_snapshot()
-            // abitrary error
-            .returning(|_, _| Box::pin(err(UpdateActorError::UnexistingUpdate(0))));
-
-        let snapshot_path = tempfile::tempdir_in(".").unwrap();
-        let snapshot_service = SnapshotService::new(
-            uuid_resolver,
-            update_handle,
-            Duration::from_millis(100),
-            snapshot_path.path().to_owned(),
-            "data.ms".to_string(),
-        );
-
-        assert!(snapshot_service.perform_snapshot().await.is_err());
-        // Nothing was written to the file
-        assert!(!snapshot_path.path().join("data.ms.snapshot").exists());
-    }
-
-    #[actix_rt::test]
-    async fn test_loop() {
-        let mut uuid_resolver = MockUuidResolverHandle::new();
-        uuid_resolver
-            .expect_snapshot()
-            // we expect the funtion to be called between 2 and 3 time in the given interval.
-            .times(2..4)
-            // abitrary error, to short-circuit the function
-            .returning(move |_| Box::pin(err(UuidResolverError::NameAlreadyExist)));
-
-        let update_handle = MockUpdateActorHandle::new();
-
-        let snapshot_path = tempfile::tempdir_in(".").unwrap();
-        let snapshot_service = SnapshotService::new(
-            uuid_resolver,
-            update_handle,
-            Duration::from_millis(100),
-            snapshot_path.path().to_owned(),
-            "data.ms".to_string(),
-        );
-
-        let _ = timeout(Duration::from_millis(300), snapshot_service.run()).await;
-    }
-}

meilisearch-http/src/index_controller/update_actor/actor.rs

@@ -1,270 +0,0 @@
-use std::collections::HashSet;
-use std::io::SeekFrom;
-use std::path::{Path, PathBuf};
-use std::sync::atomic::AtomicBool;
-use std::sync::Arc;
-
-use async_stream::stream;
-use futures::StreamExt;
-use log::trace;
-use serdeval::*;
-use tokio::fs;
-use tokio::io::AsyncWriteExt;
-use tokio::sync::mpsc;
-use uuid::Uuid;
-
-use super::error::{Result, UpdateActorError};
-use super::{PayloadData, UpdateMsg, UpdateStore, UpdateStoreInfo};
-use crate::index_controller::index_actor::IndexActorHandle;
-use crate::index_controller::{UpdateMeta, UpdateStatus};
-
-pub struct UpdateActor<D, I> {
-    path: PathBuf,
-    store: Arc<UpdateStore>,
-    inbox: Option<mpsc::Receiver<UpdateMsg<D>>>,
-    index_handle: I,
-    must_exit: Arc<AtomicBool>,
-}
-
-impl<D, I> UpdateActor<D, I>
-where
-    D: AsRef<[u8]> + Sized + 'static,
-    I: IndexActorHandle + Clone + Send + Sync + 'static,
-{
-    pub fn new(
-        update_db_size: usize,
-        inbox: mpsc::Receiver<UpdateMsg<D>>,
-        path: impl AsRef<Path>,
-        index_handle: I,
-    ) -> anyhow::Result<Self> {
-        let path = path.as_ref().join("updates");
-
-        std::fs::create_dir_all(&path)?;
-
-        let mut options = heed::EnvOpenOptions::new();
-        options.map_size(update_db_size);
-
-        let must_exit = Arc::new(AtomicBool::new(false));
-
-        let store = UpdateStore::open(options, &path, index_handle.clone(), must_exit.clone())?;
-        std::fs::create_dir_all(path.join("update_files"))?;
-        let inbox = Some(inbox);
-        Ok(Self {
-            path,
-            store,
-            inbox,
-            index_handle,
-            must_exit,
-        })
-    }
-
-    pub async fn run(mut self) {
-        use UpdateMsg::*;
-
-        trace!("Started update actor.");
-
-        let mut inbox = self
-            .inbox
-            .take()
-            .expect("A receiver should be present by now.");
-
-        let must_exit = self.must_exit.clone();
-        let stream = stream! {
-            loop {
-                let msg = inbox.recv().await;
-
-                if must_exit.load(std::sync::atomic::Ordering::Relaxed) {
-                    break;
-                }
-
-                match msg {
-                    Some(msg) => yield msg,
-                    None => break,
-                }
-            }
-        };
-
-        stream
-            .for_each_concurrent(Some(10), |msg| async {
-                match msg {
-                    Update {
-                        uuid,
-                        meta,
-                        data,
-                        ret,
-                    } => {
-                        let _ = ret.send(self.handle_update(uuid, meta, data).await);
-                    }
-                    ListUpdates { uuid, ret } => {
-                        let _ = ret.send(self.handle_list_updates(uuid).await);
-                    }
-                    GetUpdate { uuid, ret, id } => {
-                        let _ = ret.send(self.handle_get_update(uuid, id).await);
-                    }
-                    Delete { uuid, ret } => {
-                        let _ = ret.send(self.handle_delete(uuid).await);
-                    }
-                    Snapshot { uuids, path, ret } => {
-                        let _ = ret.send(self.handle_snapshot(uuids, path).await);
-                    }
-                    GetInfo { ret } => {
-                        let _ = ret.send(self.handle_get_info().await);
-                    }
-                    Dump { uuids, path, ret } => {
-                        let _ = ret.send(self.handle_dump(uuids, path).await);
-                    }
-                }
-            })
-            .await;
-    }
-
-    async fn handle_update(
-        &self,
-        uuid: Uuid,
-        meta: UpdateMeta,
-        payload: mpsc::Receiver<PayloadData<D>>,
-    ) -> Result<UpdateStatus> {
-        let file_path = match meta {
-            UpdateMeta::DocumentsAddition { .. } => {
-                let update_file_id = uuid::Uuid::new_v4();
-                let path = self
-                    .path
-                    .join(format!("update_files/update_{}", update_file_id));
-                let mut file = fs::OpenOptions::new()
-                    .read(true)
-                    .write(true)
-                    .create(true)
-                    .open(&path)
-                    .await?;
-
-                async fn write_to_file<D>(
-                    file: &mut fs::File,
-                    mut payload: mpsc::Receiver<PayloadData<D>>,
-                ) -> Result<usize>
-                where
-                    D: AsRef<[u8]> + Sized + 'static,
-                {
-                    let mut file_len = 0;
-
-                    while let Some(bytes) = payload.recv().await {
-                        let bytes = bytes?;
-                        file_len += bytes.as_ref().len();
-                        file.write_all(bytes.as_ref()).await?;
-                    }
-
-                    file.flush().await?;
-
-                    Ok(file_len)
-                }
-
-                let file_len = write_to_file(&mut file, payload).await;
-
-                match file_len {
-                    Ok(len) if len > 0 => {
-                        let file = file.into_std().await;
-                        Some((file, update_file_id))
-                    }
-                    Err(e) => {
-                        fs::remove_file(&path).await?;
-                        return Err(e);
-                    }
-                    _ => {
-                        fs::remove_file(&path).await?;
-                        None
-                    }
-                }
-            }
-            _ => None,
-        };
-
-        let update_store = self.store.clone();
-
-        tokio::task::spawn_blocking(move || {
-            use std::io::{BufReader, Seek};
-
-            // If the payload is empty, ignore the check.
-            let update_uuid = if let Some((mut file, uuid)) = file_path {
-                // set the file back to the beginning
-                file.seek(SeekFrom::Start(0))?;
-                // Check that the json payload is valid:
-                let reader = BufReader::new(&mut file);
-                // Validate that the payload is in the correct format.
-                let _: Seq<Map<Str, Any>> = serde_json::from_reader(reader)
-                    .map_err(|e| UpdateActorError::InvalidPayload(Box::new(e)))?;
-
-                Some(uuid)
-            } else {
-                None
-            };
-
-            // The payload is valid, we can register it to the update store.
-            let status = update_store
-                .register_update(meta, update_uuid, uuid)
-                .map(UpdateStatus::Enqueued)?;
-            Ok(status)
-        })
-        .await?
-    }
-
-    async fn handle_list_updates(&self, uuid: Uuid) -> Result<Vec<UpdateStatus>> {
-        let update_store = self.store.clone();
-        tokio::task::spawn_blocking(move || {
-            let result = update_store.list(uuid)?;
-            Ok(result)
-        })
-        .await?
-    }
-
-    async fn handle_get_update(&self, uuid: Uuid, id: u64) -> Result<UpdateStatus> {
-        let store = self.store.clone();
-        tokio::task::spawn_blocking(move || {
-            let result = store
-                .meta(uuid, id)?
-                .ok_or(UpdateActorError::UnexistingUpdate(id))?;
-            Ok(result)
-        })
-        .await?
-    }
-
-    async fn handle_delete(&self, uuid: Uuid) -> Result<()> {
-        let store = self.store.clone();
-
-        tokio::task::spawn_blocking(move || store.delete_all(uuid)).await??;
-
-        Ok(())
-    }
-
-    async fn handle_snapshot(&self, uuids: HashSet<Uuid>, path: PathBuf) -> Result<()> {
-        let index_handle = self.index_handle.clone();
-        let update_store = self.store.clone();
-
-        tokio::task::spawn_blocking(move || update_store.snapshot(&uuids, &path, index_handle))
-            .await??;
-
-        Ok(())
-    }
-
-    async fn handle_dump(&self, uuids: HashSet<Uuid>, path: PathBuf) -> Result<()> {
-        let index_handle = self.index_handle.clone();
-        let update_store = self.store.clone();
-
-        tokio::task::spawn_blocking(move || -> Result<()> {
-            update_store.dump(&uuids, path.to_path_buf(), index_handle)?;
-            Ok(())
-        })
-        .await??;
-
-        Ok(())
-    }
-
-    async fn handle_get_info(&self) -> Result<UpdateStoreInfo> {
-        let update_store = self.store.clone();
-        let info = tokio::task::spawn_blocking(move || -> Result<UpdateStoreInfo> {
-            let info = update_store.get_info()?;
-            Ok(info)
-        })
-        .await??;
-
-        Ok(info)
-    }
-}

meilisearch-http/src/index_controller/update_actor/error.rs

@@ -1,61 +0,0 @@
-use std::error::Error;
-
-use meilisearch_error::{Code, ErrorCode};
-
-use crate::index_controller::index_actor::error::IndexActorError;
-
-pub type Result<T> = std::result::Result<T, UpdateActorError>;
-
-#[derive(Debug, thiserror::Error)]
-#[allow(clippy::large_enum_variant)]
-pub enum UpdateActorError {
-    #[error("Update {0} not found.")]
-    UnexistingUpdate(u64),
-    #[error("Internal error: {0}")]
-    Internal(Box<dyn Error + Send + Sync + 'static>),
-    #[error("{0}")]
-    IndexActor(#[from] IndexActorError),
-    #[error(
-        "update store was shut down due to a fatal error, please check your logs for more info."
-    )]
-    FatalUpdateStoreError,
-    #[error("{0}")]
-    InvalidPayload(Box<dyn Error + Send + Sync + 'static>),
-    #[error("{0}")]
-    PayloadError(#[from] actix_web::error::PayloadError),
-}
-
-impl<T> From<tokio::sync::mpsc::error::SendError<T>> for UpdateActorError {
-    fn from(_: tokio::sync::mpsc::error::SendError<T>) -> Self {
-        Self::FatalUpdateStoreError
-    }
-}
-
-impl From<tokio::sync::oneshot::error::RecvError> for UpdateActorError {
-    fn from(_: tokio::sync::oneshot::error::RecvError) -> Self {
-        Self::FatalUpdateStoreError
-    }
-}
-
-internal_error!(
-    UpdateActorError: heed::Error,
-    std::io::Error,
-    serde_json::Error,
-    tokio::task::JoinError
-);
-
-impl ErrorCode for UpdateActorError {
-    fn error_code(&self) -> Code {
-        match self {
-            UpdateActorError::UnexistingUpdate(_) => Code::NotFound,
-            UpdateActorError::Internal(_) => Code::Internal,
-            UpdateActorError::IndexActor(e) => e.error_code(),
-            UpdateActorError::FatalUpdateStoreError => Code::Internal,
-            UpdateActorError::InvalidPayload(_) => Code::BadRequest,
-            UpdateActorError::PayloadError(error) => match error {
-                actix_http::error::PayloadError::Overflow => Code::PayloadTooLarge,
-                _ => Code::Internal,
-            },
-        }
-    }
-}

meilisearch-http/src/index_controller/update_actor/handle_impl.rs

@@ -1,103 +0,0 @@
-use std::collections::HashSet;
-use std::path::{Path, PathBuf};
-
-use tokio::sync::{mpsc, oneshot};
-use uuid::Uuid;
-
-use crate::index_controller::{IndexActorHandle, UpdateStatus};
-
-use super::error::Result;
-use super::{PayloadData, UpdateActor, UpdateActorHandle, UpdateMeta, UpdateMsg, UpdateStoreInfo};
-
-#[derive(Clone)]
-pub struct UpdateActorHandleImpl<D> {
-    sender: mpsc::Sender<UpdateMsg<D>>,
-}
-
-impl<D> UpdateActorHandleImpl<D>
-where
-    D: AsRef<[u8]> + Sized + 'static + Sync + Send,
-{
-    pub fn new<I>(
-        index_handle: I,
-        path: impl AsRef<Path>,
-        update_store_size: usize,
-    ) -> anyhow::Result<Self>
-    where
-        I: IndexActorHandle + Clone + Send + Sync + 'static,
-    {
-        let path = path.as_ref().to_owned();
-        let (sender, receiver) = mpsc::channel(100);
-        let actor = UpdateActor::new(update_store_size, receiver, path, index_handle)?;
-
-        tokio::task::spawn(actor.run());
-
-        Ok(Self { sender })
-    }
-}
-
-#[async_trait::async_trait]
-impl<D> UpdateActorHandle for UpdateActorHandleImpl<D>
-where
-    D: AsRef<[u8]> + Sized + 'static + Sync + Send,
-{
-    type Data = D;
-
-    async fn get_all_updates_status(&self, uuid: Uuid) -> Result<Vec<UpdateStatus>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::ListUpdates { uuid, ret };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-    async fn update_status(&self, uuid: Uuid, id: u64) -> Result<UpdateStatus> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::GetUpdate { uuid, id, ret };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-
-    async fn delete(&self, uuid: Uuid) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::Delete { uuid, ret };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-
-    async fn snapshot(&self, uuids: HashSet<Uuid>, path: PathBuf) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::Snapshot { uuids, path, ret };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-
-    async fn dump(&self, uuids: HashSet<Uuid>, path: PathBuf) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::Dump { uuids, path, ret };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-
-    async fn get_info(&self) -> Result<UpdateStoreInfo> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::GetInfo { ret };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-
-    async fn update(
-        &self,
-        meta: UpdateMeta,
-        data: mpsc::Receiver<PayloadData<Self::Data>>,
-        uuid: Uuid,
-    ) -> Result<UpdateStatus> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UpdateMsg::Update {
-            uuid,
-            data,
-            meta,
-            ret,
-        };
-        self.sender.send(msg).await?;
-        receiver.await?
-    }
-}

meilisearch-http/src/index_controller/update_actor/message.rs

@@ -1,43 +0,0 @@
-use std::collections::HashSet;
-use std::path::PathBuf;
-
-use tokio::sync::{mpsc, oneshot};
-use uuid::Uuid;
-
-use super::error::Result;
-use super::{PayloadData, UpdateMeta, UpdateStatus, UpdateStoreInfo};
-
-pub enum UpdateMsg<D> {
-    Update {
-        uuid: Uuid,
-        meta: UpdateMeta,
-        data: mpsc::Receiver<PayloadData<D>>,
-        ret: oneshot::Sender<Result<UpdateStatus>>,
-    },
-    ListUpdates {
-        uuid: Uuid,
-        ret: oneshot::Sender<Result<Vec<UpdateStatus>>>,
-    },
-    GetUpdate {
-        uuid: Uuid,
-        ret: oneshot::Sender<Result<UpdateStatus>>,
-        id: u64,
-    },
-    Delete {
-        uuid: Uuid,
-        ret: oneshot::Sender<Result<()>>,
-    },
-    Snapshot {
-        uuids: HashSet<Uuid>,
-        path: PathBuf,
-        ret: oneshot::Sender<Result<()>>,
-    },
-    Dump {
-        uuids: HashSet<Uuid>,
-        path: PathBuf,
-        ret: oneshot::Sender<Result<()>>,
-    },
-    GetInfo {
-        ret: oneshot::Sender<Result<UpdateStoreInfo>>,
-    },
-}

meilisearch-http/src/index_controller/update_actor/mod.rs

@@ -1,44 +0,0 @@
-use std::{collections::HashSet, path::PathBuf};
-
-use actix_http::error::PayloadError;
-use tokio::sync::mpsc;
-use uuid::Uuid;
-
-use crate::index_controller::{UpdateMeta, UpdateStatus};
-
-use actor::UpdateActor;
-use error::Result;
-use message::UpdateMsg;
-
-pub use handle_impl::UpdateActorHandleImpl;
-pub use store::{UpdateStore, UpdateStoreInfo};
-
-mod actor;
-pub mod error;
-mod handle_impl;
-mod message;
-pub mod store;
-
-type PayloadData<D> = std::result::Result<D, PayloadError>;
-
-#[cfg(test)]
-use mockall::automock;
-
-#[async_trait::async_trait]
-#[cfg_attr(test, automock(type Data=Vec<u8>;))]
-pub trait UpdateActorHandle {
-    type Data: AsRef<[u8]> + Sized + 'static + Sync + Send;
-
-    async fn get_all_updates_status(&self, uuid: Uuid) -> Result<Vec<UpdateStatus>>;
-    async fn update_status(&self, uuid: Uuid, id: u64) -> Result<UpdateStatus>;
-    async fn delete(&self, uuid: Uuid) -> Result<()>;
-    async fn snapshot(&self, uuid: HashSet<Uuid>, path: PathBuf) -> Result<()>;
-    async fn dump(&self, uuids: HashSet<Uuid>, path: PathBuf) -> Result<()>;
-    async fn get_info(&self) -> Result<UpdateStoreInfo>;
-    async fn update(
-        &self,
-        meta: UpdateMeta,
-        data: mpsc::Receiver<PayloadData<Self::Data>>,
-        uuid: Uuid,
-    ) -> Result<UpdateStatus>;
-}

meilisearch-http/src/index_controller/update_actor/store/codec.rs

@@ -1,86 +0,0 @@
-use std::{borrow::Cow, convert::TryInto, mem::size_of};
-
-use heed::{BytesDecode, BytesEncode};
-use uuid::Uuid;
-
-pub struct NextIdCodec;
-
-pub enum NextIdKey {
-    Global,
-    Index(Uuid),
-}
-
-impl<'a> BytesEncode<'a> for NextIdCodec {
-    type EItem = NextIdKey;
-
-    fn bytes_encode(item: &'a Self::EItem) -> Option<Cow<'a, [u8]>> {
-        match item {
-            NextIdKey::Global => Some(Cow::Borrowed(b"__global__")),
-            NextIdKey::Index(ref uuid) => Some(Cow::Borrowed(uuid.as_bytes())),
-        }
-    }
-}
-
-pub struct PendingKeyCodec;
-
-impl<'a> BytesEncode<'a> for PendingKeyCodec {
-    type EItem = (u64, Uuid, u64);
-
-    fn bytes_encode((global_id, uuid, update_id): &'a Self::EItem) -> Option<Cow<'a, [u8]>> {
-        let mut bytes = Vec::with_capacity(size_of::<Self::EItem>());
-        bytes.extend_from_slice(&global_id.to_be_bytes());
-        bytes.extend_from_slice(uuid.as_bytes());
-        bytes.extend_from_slice(&update_id.to_be_bytes());
-        Some(Cow::Owned(bytes))
-    }
-}
-
-impl<'a> BytesDecode<'a> for PendingKeyCodec {
-    type DItem = (u64, Uuid, u64);
-
-    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
-        let global_id_bytes = bytes.get(0..size_of::<u64>())?.try_into().ok()?;
-        let global_id = u64::from_be_bytes(global_id_bytes);
-
-        let uuid_bytes = bytes
-            .get(size_of::<u64>()..(size_of::<u64>() + size_of::<Uuid>()))?
-            .try_into()
-            .ok()?;
-        let uuid = Uuid::from_bytes(uuid_bytes);
-
-        let update_id_bytes = bytes
-            .get((size_of::<u64>() + size_of::<Uuid>())..)?
-            .try_into()
-            .ok()?;
-        let update_id = u64::from_be_bytes(update_id_bytes);
-
-        Some((global_id, uuid, update_id))
-    }
-}
-
-pub struct UpdateKeyCodec;
-
-impl<'a> BytesEncode<'a> for UpdateKeyCodec {
-    type EItem = (Uuid, u64);
-
-    fn bytes_encode((uuid, update_id): &'a Self::EItem) -> Option<Cow<'a, [u8]>> {
-        let mut bytes = Vec::with_capacity(size_of::<Self::EItem>());
-        bytes.extend_from_slice(uuid.as_bytes());
-        bytes.extend_from_slice(&update_id.to_be_bytes());
-        Some(Cow::Owned(bytes))
-    }
-}
-
-impl<'a> BytesDecode<'a> for UpdateKeyCodec {
-    type DItem = (Uuid, u64);
-
-    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
-        let uuid_bytes = bytes.get(0..size_of::<Uuid>())?.try_into().ok()?;
-        let uuid = Uuid::from_bytes(uuid_bytes);
-
-        let update_id_bytes = bytes.get(size_of::<Uuid>()..)?.try_into().ok()?;
-        let update_id = u64::from_be_bytes(update_id_bytes);
-
-        Some((uuid, update_id))
-    }
-}

meilisearch-http/src/index_controller/update_actor/store/dump.rs

@@ -1,184 +0,0 @@
-use std::{
-    collections::HashSet,
-    fs::{create_dir_all, File},
-    io::{BufRead, BufReader, Write},
-    path::{Path, PathBuf},
-};
-
-use heed::{EnvOpenOptions, RoTxn};
-use serde::{Deserialize, Serialize};
-use uuid::Uuid;
-
-use super::{Result, State, UpdateStore};
-use crate::index_controller::{
-    index_actor::IndexActorHandle, update_actor::store::update_uuid_to_file_path, Enqueued,
-    UpdateStatus,
-};
-
-#[derive(Serialize, Deserialize)]
-struct UpdateEntry {
-    uuid: Uuid,
-    update: UpdateStatus,
-}
-
-impl UpdateStore {
-    pub fn dump(
-        &self,
-        uuids: &HashSet<Uuid>,
-        path: PathBuf,
-        handle: impl IndexActorHandle,
-    ) -> Result<()> {
-        let state_lock = self.state.write();
-        state_lock.swap(State::Dumping);
-
-        // txn must *always* be acquired after state lock, or it will dead lock.
-        let txn = self.env.write_txn()?;
-
-        let dump_path = path.join("updates");
-        create_dir_all(&dump_path)?;
-
-        self.dump_updates(&txn, uuids, &dump_path)?;
-
-        let fut = dump_indexes(uuids, handle, &path);
-        tokio::runtime::Handle::current().block_on(fut)?;
-
-        state_lock.swap(State::Idle);
-
-        Ok(())
-    }
-
-    fn dump_updates(
-        &self,
-        txn: &RoTxn,
-        uuids: &HashSet<Uuid>,
-        path: impl AsRef<Path>,
-    ) -> Result<()> {
-        let dump_data_path = path.as_ref().join("data.jsonl");
-        let mut dump_data_file = File::create(dump_data_path)?;
-
-        let update_files_path = path.as_ref().join(super::UPDATE_DIR);
-        create_dir_all(&update_files_path)?;
-
-        self.dump_pending(txn, uuids, &mut dump_data_file, &path)?;
-        self.dump_completed(txn, uuids, &mut dump_data_file)?;
-
-        Ok(())
-    }
-
-    fn dump_pending(
-        &self,
-        txn: &RoTxn,
-        uuids: &HashSet<Uuid>,
-        mut file: &mut File,
-        dst_path: impl AsRef<Path>,
-    ) -> Result<()> {
-        let pendings = self.pending_queue.iter(txn)?.lazily_decode_data();
-
-        for pending in pendings {
-            let ((_, uuid, _), data) = pending?;
-            if uuids.contains(&uuid) {
-                let update = data.decode()?;
-
-                if let Some(ref update_uuid) = update.content {
-                    let src = super::update_uuid_to_file_path(&self.path, *update_uuid);
-                    let dst = super::update_uuid_to_file_path(&dst_path, *update_uuid);
-                    std::fs::copy(src, dst)?;
-                }
-
-                let update_json = UpdateEntry {
-                    uuid,
-                    update: update.into(),
-                };
-
-                serde_json::to_writer(&mut file, &update_json)?;
-                file.write_all(b"\n")?;
-            }
-        }
-
-        Ok(())
-    }
-
-    fn dump_completed(
-        &self,
-        txn: &RoTxn,
-        uuids: &HashSet<Uuid>,
-        mut file: &mut File,
-    ) -> Result<()> {
-        let updates = self.updates.iter(txn)?.lazily_decode_data();
-
-        for update in updates {
-            let ((uuid, _), data) = update?;
-            if uuids.contains(&uuid) {
-                let update = data.decode()?;
-
-                let update_json = UpdateEntry { uuid, update };
-
-                serde_json::to_writer(&mut file, &update_json)?;
-                file.write_all(b"\n")?;
-            }
-        }
-
-        Ok(())
-    }
-
-    pub fn load_dump(
-        src: impl AsRef<Path>,
-        dst: impl AsRef<Path>,
-        db_size: usize,
-    ) -> anyhow::Result<()> {
-        let dst_update_path = dst.as_ref().join("updates/");
-        create_dir_all(&dst_update_path)?;
-
-        let mut options = EnvOpenOptions::new();
-        options.map_size(db_size as usize);
-        let (store, _) = UpdateStore::new(options, &dst_update_path)?;
-
-        let src_update_path = src.as_ref().join("updates");
-        let update_data = File::open(&src_update_path.join("data.jsonl"))?;
-        let mut update_data = BufReader::new(update_data);
-
-        std::fs::create_dir_all(dst_update_path.join("update_files/"))?;
-
-        let mut wtxn = store.env.write_txn()?;
-        let mut line = String::new();
-        loop {
-            match update_data.read_line(&mut line) {
-                Ok(0) => break,
-                Ok(_) => {
-                    let UpdateEntry { uuid, update } = serde_json::from_str(&line)?;
-                    store.register_raw_updates(&mut wtxn, &update, uuid)?;
-
-                    // Copy ascociated update path if it exists
-                    if let UpdateStatus::Enqueued(Enqueued {
-                        content: Some(uuid),
-                        ..
-                    }) = update
-                    {
-                        let src = update_uuid_to_file_path(&src_update_path, uuid);
-                        let dst = update_uuid_to_file_path(&dst_update_path, uuid);
-                        std::fs::copy(src, dst)?;
-                    }
-                }
-                _ => break,
-            }
-
-            line.clear();
-        }
-
-        wtxn.commit()?;
-
-        Ok(())
-    }
-}
-
-async fn dump_indexes(
-    uuids: &HashSet<Uuid>,
-    handle: impl IndexActorHandle,
-    path: impl AsRef<Path>,
-) -> Result<()> {
-    for uuid in uuids {
-        handle.dump(*uuid, path.as_ref().to_owned()).await?;
-    }
-
-    Ok(())
-}

meilisearch-http/src/index_controller/update_actor/store/mod.rs

@@ -1,729 +0,0 @@
-mod codec;
-pub mod dump;
-
-use std::fs::{copy, create_dir_all, remove_file, File};
-use std::path::Path;
-use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::Arc;
-use std::{
-    collections::{BTreeMap, HashSet},
-    path::PathBuf,
-    time::Duration,
-};
-
-use arc_swap::ArcSwap;
-use futures::StreamExt;
-use heed::types::{ByteSlice, OwnedType, SerdeJson};
-use heed::zerocopy::U64;
-use heed::{CompactionOption, Database, Env, EnvOpenOptions};
-use log::error;
-use parking_lot::{Mutex, MutexGuard};
-use tokio::runtime::Handle;
-use tokio::sync::mpsc;
-use tokio::sync::mpsc::error::TrySendError;
-use tokio::time::timeout;
-use uuid::Uuid;
-
-use codec::*;
-
-use super::error::Result;
-use super::UpdateMeta;
-use crate::helpers::EnvSizer;
-use crate::index_controller::{index_actor::CONCURRENT_INDEX_MSG, updates::*, IndexActorHandle};
-
-#[allow(clippy::upper_case_acronyms)]
-type BEU64 = U64<heed::byteorder::BE>;
-
-const UPDATE_DIR: &str = "update_files";
-
-pub struct UpdateStoreInfo {
-    /// Size of the update store in bytes.
-    pub size: u64,
-    /// Uuid of the currently processing update if it exists
-    pub processing: Option<Uuid>,
-}
-
-/// A data structure that allows concurrent reads AND exactly one writer.
-pub struct StateLock {
-    lock: Mutex<()>,
-    data: ArcSwap<State>,
-}
-
-pub struct StateLockGuard<'a> {
-    _lock: MutexGuard<'a, ()>,
-    state: &'a StateLock,
-}
-
-impl StateLockGuard<'_> {
-    pub fn swap(&self, state: State) -> Arc<State> {
-        self.state.data.swap(Arc::new(state))
-    }
-}
-
-impl StateLock {
-    fn from_state(state: State) -> Self {
-        let lock = Mutex::new(());
-        let data = ArcSwap::from(Arc::new(state));
-        Self { lock, data }
-    }
-
-    pub fn read(&self) -> Arc<State> {
-        self.data.load().clone()
-    }
-
-    pub fn write(&self) -> StateLockGuard {
-        let _lock = self.lock.lock();
-        let state = &self;
-        StateLockGuard { _lock, state }
-    }
-}
-
-#[allow(clippy::large_enum_variant)]
-pub enum State {
-    Idle,
-    Processing(Uuid, Processing),
-    Snapshoting,
-    Dumping,
-}
-
-#[derive(Clone)]
-pub struct UpdateStore {
-    pub env: Env,
-    /// A queue containing the updates to process, ordered by arrival.
-    /// The key are built as follow:
-    /// | global_update_id | index_uuid | update_id |
-    /// |     8-bytes      |  16-bytes  |  8-bytes  |
-    pending_queue: Database<PendingKeyCodec, SerdeJson<Enqueued>>,
-    /// Map indexes to the next available update id. If NextIdKey::Global is queried, then the next
-    /// global update id is returned
-    next_update_id: Database<NextIdCodec, OwnedType<BEU64>>,
-    /// Contains all the performed updates meta, be they failed, aborted, or processed.
-    /// The keys are built as follow:
-    /// |    Uuid  |   id    |
-    /// | 16-bytes | 8-bytes |
-    updates: Database<UpdateKeyCodec, SerdeJson<UpdateStatus>>,
-    /// Indicates the current state of the update store,
-    state: Arc<StateLock>,
-    /// Wake up the loop when a new event occurs.
-    notification_sender: mpsc::Sender<()>,
-    path: PathBuf,
-}
-
-impl UpdateStore {
-    fn new(
-        mut options: EnvOpenOptions,
-        path: impl AsRef<Path>,
-    ) -> anyhow::Result<(Self, mpsc::Receiver<()>)> {
-        options.max_dbs(5);
-
-        let env = options.open(&path)?;
-        let pending_queue = env.create_database(Some("pending-queue"))?;
-        let next_update_id = env.create_database(Some("next-update-id"))?;
-        let updates = env.create_database(Some("updates"))?;
-
-        let state = Arc::new(StateLock::from_state(State::Idle));
-
-        let (notification_sender, notification_receiver) = mpsc::channel(1);
-
-        Ok((
-            Self {
-                env,
-                pending_queue,
-                next_update_id,
-                updates,
-                state,
-                notification_sender,
-                path: path.as_ref().to_owned(),
-            },
-            notification_receiver,
-        ))
-    }
-
-    pub fn open(
-        options: EnvOpenOptions,
-        path: impl AsRef<Path>,
-        index_handle: impl IndexActorHandle + Clone + Sync + Send + 'static,
-        must_exit: Arc<AtomicBool>,
-    ) -> anyhow::Result<Arc<Self>> {
-        let (update_store, mut notification_receiver) = Self::new(options, path)?;
-        let update_store = Arc::new(update_store);
-
-        // Send a first notification to trigger the process.
-        if let Err(TrySendError::Closed(())) = update_store.notification_sender.try_send(()) {
-            panic!("Failed to init update store");
-        }
-
-        // We need a weak reference so we can take ownership on the arc later when we
-        // want to close the index.
-        let duration = Duration::from_secs(10 * 60); // 10 minutes
-        let update_store_weak = Arc::downgrade(&update_store);
-        tokio::task::spawn(async move {
-            // Block and wait for something to process with a timeout. The timeout
-            // function returns a Result and we must just unlock the loop on Result.
-            'outer: while timeout(duration, notification_receiver.recv())
-                .await
-                .map_or(true, |o| o.is_some())
-            {
-                loop {
-                    match update_store_weak.upgrade() {
-                        Some(update_store) => {
-                            let handler = index_handle.clone();
-                            let res = tokio::task::spawn_blocking(move || {
-                                update_store.process_pending_update(handler)
-                            })
-                            .await
-                            .expect("Fatal error processing update.");
-                            match res {
-                                Ok(Some(_)) => (),
-                                Ok(None) => break,
-                                Err(e) => {
-                                    error!("Fatal error while processing an update that requires the update store to shutdown: {}", e);
-                                    must_exit.store(true, Ordering::SeqCst);
-                                    break 'outer;
-                                }
-                            }
-                        }
-                        // the ownership on the arc has been taken, we need to exit.
-                        None => break 'outer,
-                    }
-                }
-            }
-
-            error!("Update store loop exited.");
-        });
-
-        Ok(update_store)
-    }
-
-    /// Returns the next global update id and the next update id for a given `index_uuid`.
-    fn next_update_id(&self, txn: &mut heed::RwTxn, index_uuid: Uuid) -> heed::Result<(u64, u64)> {
-        let global_id = self
-            .next_update_id
-            .get(txn, &NextIdKey::Global)?
-            .map(U64::get)
-            .unwrap_or_default();
-
-        self.next_update_id
-            .put(txn, &NextIdKey::Global, &BEU64::new(global_id + 1))?;
-
-        let update_id = self.next_update_id_raw(txn, index_uuid)?;
-
-        Ok((global_id, update_id))
-    }
-
-    /// Returns the next next update id for a given `index_uuid` without
-    /// incrementing the global update id. This is useful for the dumps.
-    fn next_update_id_raw(&self, txn: &mut heed::RwTxn, index_uuid: Uuid) -> heed::Result<u64> {
-        let update_id = self
-            .next_update_id
-            .get(txn, &NextIdKey::Index(index_uuid))?
-            .map(U64::get)
-            .unwrap_or_default();
-
-        self.next_update_id.put(
-            txn,
-            &NextIdKey::Index(index_uuid),
-            &BEU64::new(update_id + 1),
-        )?;
-
-        Ok(update_id)
-    }
-
-    /// Registers the update content in the pending store and the meta
-    /// into the pending-meta store. Returns the new unique update id.
-    pub fn register_update(
-        &self,
-        meta: UpdateMeta,
-        content: Option<Uuid>,
-        index_uuid: Uuid,
-    ) -> heed::Result<Enqueued> {
-        let mut txn = self.env.write_txn()?;
-
-        let (global_id, update_id) = self.next_update_id(&mut txn, index_uuid)?;
-        let meta = Enqueued::new(meta, update_id, content);
-
-        self.pending_queue
-            .put(&mut txn, &(global_id, index_uuid, update_id), &meta)?;
-
-        txn.commit()?;
-
-        if let Err(TrySendError::Closed(())) = self.notification_sender.try_send(()) {
-            panic!("Update store loop exited");
-        }
-
-        Ok(meta)
-    }
-
-    /// Push already processed update in the UpdateStore without triggering the notification
-    /// process. This is useful for the dumps.
-    pub fn register_raw_updates(
-        &self,
-        wtxn: &mut heed::RwTxn,
-        update: &UpdateStatus,
-        index_uuid: Uuid,
-    ) -> heed::Result<()> {
-        match update {
-            UpdateStatus::Enqueued(enqueued) => {
-                let (global_id, _update_id) = self.next_update_id(wtxn, index_uuid)?;
-                self.pending_queue.remap_key_type::<PendingKeyCodec>().put(
-                    wtxn,
-                    &(global_id, index_uuid, enqueued.id()),
-                    enqueued,
-                )?;
-            }
-            _ => {
-                let _update_id = self.next_update_id_raw(wtxn, index_uuid)?;
-                self.updates.put(wtxn, &(index_uuid, update.id()), update)?;
-            }
-        }
-        Ok(())
-    }
-
-    /// Executes the user provided function on the next pending update (the one with the lowest id).
-    /// This is asynchronous as it let the user process the update with a read-only txn and
-    /// only writing the result meta to the processed-meta store *after* it has been processed.
-    fn process_pending_update(&self, index_handle: impl IndexActorHandle) -> Result<Option<()>> {
-        // Create a read transaction to be able to retrieve the pending update in order.
-        let rtxn = self.env.read_txn()?;
-        let first_meta = self.pending_queue.first(&rtxn)?;
-        drop(rtxn);
-
-        // If there is a pending update we process and only keep
-        // a reader while processing it, not a writer.
-        match first_meta {
-            Some(((global_id, index_uuid, _), mut pending)) => {
-                let content = pending.content.take();
-                let processing = pending.processing();
-                // Acquire the state lock and set the current state to processing.
-                // txn must *always* be acquired after state lock, or it will dead lock.
-                let state = self.state.write();
-                state.swap(State::Processing(index_uuid, processing.clone()));
-
-                let result =
-                    self.perform_update(content, processing, index_handle, index_uuid, global_id);
-
-                state.swap(State::Idle);
-
-                result
-            }
-            None => Ok(None),
-        }
-    }
-
-    fn perform_update(
-        &self,
-        content: Option<Uuid>,
-        processing: Processing,
-        index_handle: impl IndexActorHandle,
-        index_uuid: Uuid,
-        global_id: u64,
-    ) -> Result<Option<()>> {
-        let content_path = content.map(|uuid| update_uuid_to_file_path(&self.path, uuid));
-        let update_id = processing.id();
-
-        let file = match content_path {
-            Some(ref path) => {
-                let file = File::open(path)?;
-                Some(file)
-            }
-            None => None,
-        };
-
-        // Process the pending update using the provided user function.
-        let handle = Handle::current();
-        let result =
-            match handle.block_on(index_handle.update(index_uuid, processing.clone(), file)) {
-                Ok(result) => result,
-                Err(e) => Err(processing.fail(e.into())),
-            };
-
-        // Once the pending update have been successfully processed
-        // we must remove the content from the pending and processing stores and
-        // write the *new* meta to the processed-meta store and commit.
-        let mut wtxn = self.env.write_txn()?;
-        self.pending_queue
-            .delete(&mut wtxn, &(global_id, index_uuid, update_id))?;
-
-        let result = match result {
-            Ok(res) => res.into(),
-            Err(res) => res.into(),
-        };
-
-        self.updates
-            .put(&mut wtxn, &(index_uuid, update_id), &result)?;
-
-        wtxn.commit()?;
-
-        if let Some(ref path) = content_path {
-            remove_file(&path)?;
-        }
-
-        Ok(Some(()))
-    }
-
-    /// List the updates for `index_uuid`.
-    pub fn list(&self, index_uuid: Uuid) -> Result<Vec<UpdateStatus>> {
-        let mut update_list = BTreeMap::<u64, UpdateStatus>::new();
-
-        let txn = self.env.read_txn()?;
-
-        let pendings = self.pending_queue.iter(&txn)?.lazily_decode_data();
-        for entry in pendings {
-            let ((_, uuid, id), pending) = entry?;
-            if uuid == index_uuid {
-                update_list.insert(id, pending.decode()?.into());
-            }
-        }
-
-        let updates = self
-            .updates
-            .remap_key_type::<ByteSlice>()
-            .prefix_iter(&txn, index_uuid.as_bytes())?;
-
-        for entry in updates {
-            let (_, update) = entry?;
-            update_list.insert(update.id(), update);
-        }
-
-        // If the currently processing update is from this index, replace the corresponding pending update with this one.
-        match *self.state.read() {
-            State::Processing(uuid, ref processing) if uuid == index_uuid => {
-                update_list.insert(processing.id(), processing.clone().into());
-            }
-            _ => (),
-        }
-
-        Ok(update_list.into_iter().map(|(_, v)| v).collect())
-    }
-
-    /// Returns the update associated meta or `None` if the update doesn't exist.
-    pub fn meta(&self, index_uuid: Uuid, update_id: u64) -> heed::Result<Option<UpdateStatus>> {
-        // Check if the update is the one currently processing
-        match *self.state.read() {
-            State::Processing(uuid, ref processing)
-                if uuid == index_uuid && processing.id() == update_id =>
-            {
-                return Ok(Some(processing.clone().into()));
-            }
-            _ => (),
-        }
-
-        let txn = self.env.read_txn()?;
-        // Else, check if it is in the updates database:
-        let update = self.updates.get(&txn, &(index_uuid, update_id))?;
-
-        if let Some(update) = update {
-            return Ok(Some(update));
-        }
-
-        // If nothing was found yet, we resolve to iterate over the pending queue.
-        let pendings = self.pending_queue.iter(&txn)?.lazily_decode_data();
-
-        for entry in pendings {
-            let ((_, uuid, id), pending) = entry?;
-            if uuid == index_uuid && id == update_id {
-                return Ok(Some(pending.decode()?.into()));
-            }
-        }
-
-        // No update was found.
-        Ok(None)
-    }
-
-    /// Delete all updates for an index from the update store. If the currently processing update
-    /// is for `index_uuid`, the call will block until the update is terminated.
-    pub fn delete_all(&self, index_uuid: Uuid) -> Result<()> {
-        let mut txn = self.env.write_txn()?;
-        // Contains all the content file paths that we need to be removed if the deletion was successful.
-        let mut uuids_to_remove = Vec::new();
-
-        let mut pendings = self.pending_queue.iter_mut(&mut txn)?.lazily_decode_data();
-
-        while let Some(Ok(((_, uuid, _), pending))) = pendings.next() {
-            if uuid == index_uuid {
-                let mut pending = pending.decode()?;
-                if let Some(update_uuid) = pending.content.take() {
-                    uuids_to_remove.push(update_uuid);
-                }
-
-                // Invariant check: we can only delete the current entry when we don't hold
-                // references to it anymore. This must be done after we have retrieved its content.
-                unsafe {
-                    pendings.del_current()?;
-                }
-            }
-        }
-
-        drop(pendings);
-
-        let mut updates = self
-            .updates
-            .remap_key_type::<ByteSlice>()
-            .prefix_iter_mut(&mut txn, index_uuid.as_bytes())?
-            .lazily_decode_data();
-
-        while let Some(_) = updates.next() {
-            unsafe {
-                updates.del_current()?;
-            }
-        }
-
-        drop(updates);
-
-        txn.commit()?;
-
-        // If the currently processing update is from our index, we wait until it is
-        // finished before returning. This ensure that no write to the index occurs after we delete it.
-        if let State::Processing(uuid, _) = *self.state.read() {
-            if uuid == index_uuid {
-                // wait for a write lock, do nothing with it.
-                self.state.write();
-            }
-        }
-
-        // Finally, remove any outstanding update files. This must be done after waiting for the
-        // last update to ensure that the update files are not deleted before the update needs
-        // them.
-        uuids_to_remove
-            .iter()
-            .map(|uuid| update_uuid_to_file_path(&self.path, *uuid))
-            .for_each(|path| {
-                let _ = remove_file(path);
-            });
-
-        Ok(())
-    }
-
-    pub fn snapshot(
-        &self,
-        uuids: &HashSet<Uuid>,
-        path: impl AsRef<Path>,
-        handle: impl IndexActorHandle + Clone,
-    ) -> Result<()> {
-        let state_lock = self.state.write();
-        state_lock.swap(State::Snapshoting);
-
-        let txn = self.env.write_txn()?;
-
-        let update_path = path.as_ref().join("updates");
-        create_dir_all(&update_path)?;
-
-        // acquire write lock to prevent further writes during snapshot
-        create_dir_all(&update_path)?;
-        let db_path = update_path.join("data.mdb");
-
-        // create db snapshot
-        self.env.copy_to_path(&db_path, CompactionOption::Enabled)?;
-
-        let update_files_path = update_path.join(UPDATE_DIR);
-        create_dir_all(&update_files_path)?;
-
-        let pendings = self.pending_queue.iter(&txn)?.lazily_decode_data();
-
-        for entry in pendings {
-            let ((_, uuid, _), pending) = entry?;
-            if uuids.contains(&uuid) {
-                if let Enqueued {
-                    content: Some(uuid),
-                    ..
-                } = pending.decode()?
-                {
-                    let path = update_uuid_to_file_path(&self.path, uuid);
-                    copy(path, &update_files_path)?;
-                }
-            }
-        }
-
-        let path = &path.as_ref().to_path_buf();
-        let handle = &handle;
-        // Perform the snapshot of each index concurently. Only a third of the capabilities of
-        // the index actor at a time not to put too much pressure on the index actor
-        let mut stream = futures::stream::iter(uuids.iter())
-            .map(move |uuid| handle.snapshot(*uuid, path.clone()))
-            .buffer_unordered(CONCURRENT_INDEX_MSG / 3);
-
-        Handle::current().block_on(async {
-            while let Some(res) = stream.next().await {
-                res?;
-            }
-            Ok(()) as Result<()>
-        })?;
-
-        Ok(())
-    }
-
-    pub fn get_info(&self) -> Result<UpdateStoreInfo> {
-        let mut size = self.env.size();
-        let txn = self.env.read_txn()?;
-        for entry in self.pending_queue.iter(&txn)? {
-            let (_, pending) = entry?;
-            if let Enqueued {
-                content: Some(uuid),
-                ..
-            } = pending
-            {
-                let path = update_uuid_to_file_path(&self.path, uuid);
-                size += File::open(path)?.metadata()?.len();
-            }
-        }
-        let processing = match *self.state.read() {
-            State::Processing(uuid, _) => Some(uuid),
-            _ => None,
-        };
-
-        Ok(UpdateStoreInfo { size, processing })
-    }
-}
-
-fn update_uuid_to_file_path(root: impl AsRef<Path>, uuid: Uuid) -> PathBuf {
-    root.as_ref()
-        .join(UPDATE_DIR)
-        .join(format!("update_{}", uuid))
-}
-
-#[cfg(test)]
-mod test {
-    use super::*;
-    use crate::index_controller::{
-        index_actor::{error::IndexActorError, MockIndexActorHandle},
-        UpdateResult,
-    };
-
-    use futures::future::ok;
-
-    #[actix_rt::test]
-    async fn test_next_id() {
-        let dir = tempfile::tempdir_in(".").unwrap();
-        let mut options = EnvOpenOptions::new();
-        let handle = Arc::new(MockIndexActorHandle::new());
-        options.map_size(4096 * 100);
-        let update_store = UpdateStore::open(
-            options,
-            dir.path(),
-            handle,
-            Arc::new(AtomicBool::new(false)),
-        )
-        .unwrap();
-
-        let index1_uuid = Uuid::new_v4();
-        let index2_uuid = Uuid::new_v4();
-
-        let mut txn = update_store.env.write_txn().unwrap();
-        let ids = update_store.next_update_id(&mut txn, index1_uuid).unwrap();
-        txn.commit().unwrap();
-        assert_eq!((0, 0), ids);
-
-        let mut txn = update_store.env.write_txn().unwrap();
-        let ids = update_store.next_update_id(&mut txn, index2_uuid).unwrap();
-        txn.commit().unwrap();
-        assert_eq!((1, 0), ids);
-
-        let mut txn = update_store.env.write_txn().unwrap();
-        let ids = update_store.next_update_id(&mut txn, index1_uuid).unwrap();
-        txn.commit().unwrap();
-        assert_eq!((2, 1), ids);
-    }
-
-    #[actix_rt::test]
-    async fn test_register_update() {
-        let dir = tempfile::tempdir_in(".").unwrap();
-        let mut options = EnvOpenOptions::new();
-        let handle = Arc::new(MockIndexActorHandle::new());
-        options.map_size(4096 * 100);
-        let update_store = UpdateStore::open(
-            options,
-            dir.path(),
-            handle,
-            Arc::new(AtomicBool::new(false)),
-        )
-        .unwrap();
-        let meta = UpdateMeta::ClearDocuments;
-        let uuid = Uuid::new_v4();
-        let store_clone = update_store.clone();
-        tokio::task::spawn_blocking(move || {
-            store_clone.register_update(meta, None, uuid).unwrap();
-        })
-        .await
-        .unwrap();
-
-        let txn = update_store.env.read_txn().unwrap();
-        assert!(update_store
-            .pending_queue
-            .get(&txn, &(0, uuid, 0))
-            .unwrap()
-            .is_some());
-    }
-
-    #[actix_rt::test]
-    async fn test_process_update() {
-        let dir = tempfile::tempdir_in(".").unwrap();
-        let mut handle = MockIndexActorHandle::new();
-
-        handle
-            .expect_update()
-            .times(2)
-            .returning(|_index_uuid, processing, _file| {
-                if processing.id() == 0 {
-                    Box::pin(ok(Ok(processing.process(UpdateResult::Other))))
-                } else {
-                    Box::pin(ok(Err(
-                        processing.fail(IndexActorError::ExistingPrimaryKey.into())
-                    )))
-                }
-            });
-
-        let handle = Arc::new(handle);
-
-        let mut options = EnvOpenOptions::new();
-        options.map_size(4096 * 100);
-        let store = UpdateStore::open(
-            options,
-            dir.path(),
-            handle.clone(),
-            Arc::new(AtomicBool::new(false)),
-        )
-        .unwrap();
-
-        // wait a bit for the event loop exit.
-        tokio::time::sleep(std::time::Duration::from_millis(50)).await;
-
-        let mut txn = store.env.write_txn().unwrap();
-
-        let update = Enqueued::new(UpdateMeta::ClearDocuments, 0, None);
-        let uuid = Uuid::new_v4();
-
-        store
-            .pending_queue
-            .put(&mut txn, &(0, uuid, 0), &update)
-            .unwrap();
-
-        let update = Enqueued::new(UpdateMeta::ClearDocuments, 1, None);
-
-        store
-            .pending_queue
-            .put(&mut txn, &(1, uuid, 1), &update)
-            .unwrap();
-
-        txn.commit().unwrap();
-
-        // Process the pending, and check that it has been moved to the update databases, and
-        // removed from the pending database.
-        let store_clone = store.clone();
-        tokio::task::spawn_blocking(move || {
-            store_clone.process_pending_update(handle.clone()).unwrap();
-            store_clone.process_pending_update(handle).unwrap();
-        })
-        .await
-        .unwrap();
-
-        let txn = store.env.read_txn().unwrap();
-
-        assert!(store.pending_queue.first(&txn).unwrap().is_none());
-        let update = store.updates.get(&txn, &(uuid, 0)).unwrap().unwrap();
-
-        assert!(matches!(update, UpdateStatus::Processed(_)));
-        let update = store.updates.get(&txn, &(uuid, 1)).unwrap().unwrap();
-
-        assert!(matches!(update, UpdateStatus::Failed(_)));
-    }
-}

meilisearch-http/src/index_controller/updates.rs

@@ -1,233 +0,0 @@
-use chrono::{DateTime, Utc};
-use milli::update::{DocumentAdditionResult, IndexDocumentsMethod, UpdateFormat};
-use serde::{Deserialize, Serialize};
-use uuid::Uuid;
-
-use crate::{
-    error::ResponseError,
-    index::{Settings, Unchecked},
-};
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub enum UpdateResult {
-    DocumentsAddition(DocumentAdditionResult),
-    DocumentDeletion { deleted: u64 },
-    Other,
-}
-
-#[allow(clippy::large_enum_variant)]
-#[derive(Debug, Clone, Serialize, Deserialize)]
-#[serde(tag = "type")]
-pub enum UpdateMeta {
-    DocumentsAddition {
-        method: IndexDocumentsMethod,
-        format: UpdateFormat,
-        primary_key: Option<String>,
-    },
-    ClearDocuments,
-    DeleteDocuments {
-        ids: Vec<String>,
-    },
-    Settings(Settings<Unchecked>),
-}
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct Enqueued {
-    pub update_id: u64,
-    pub meta: UpdateMeta,
-    pub enqueued_at: DateTime<Utc>,
-    pub content: Option<Uuid>,
-}
-
-impl Enqueued {
-    pub fn new(meta: UpdateMeta, update_id: u64, content: Option<Uuid>) -> Self {
-        Self {
-            enqueued_at: Utc::now(),
-            meta,
-            update_id,
-            content,
-        }
-    }
-
-    pub fn processing(self) -> Processing {
-        Processing {
-            from: self,
-            started_processing_at: Utc::now(),
-        }
-    }
-
-    pub fn abort(self) -> Aborted {
-        Aborted {
-            from: self,
-            aborted_at: Utc::now(),
-        }
-    }
-
-    pub fn meta(&self) -> &UpdateMeta {
-        &self.meta
-    }
-
-    pub fn id(&self) -> u64 {
-        self.update_id
-    }
-}
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct Processed {
-    pub success: UpdateResult,
-    pub processed_at: DateTime<Utc>,
-    #[serde(flatten)]
-    pub from: Processing,
-}
-
-impl Processed {
-    pub fn id(&self) -> u64 {
-        self.from.id()
-    }
-
-    pub fn meta(&self) -> &UpdateMeta {
-        self.from.meta()
-    }
-}
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct Processing {
-    #[serde(flatten)]
-    pub from: Enqueued,
-    pub started_processing_at: DateTime<Utc>,
-}
-
-impl Processing {
-    pub fn id(&self) -> u64 {
-        self.from.id()
-    }
-
-    pub fn meta(&self) -> &UpdateMeta {
-        self.from.meta()
-    }
-
-    pub fn process(self, success: UpdateResult) -> Processed {
-        Processed {
-            success,
-            from: self,
-            processed_at: Utc::now(),
-        }
-    }
-
-    pub fn fail(self, error: ResponseError) -> Failed {
-        Failed {
-            from: self,
-            error,
-            failed_at: Utc::now(),
-        }
-    }
-}
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct Aborted {
-    #[serde(flatten)]
-    from: Enqueued,
-    aborted_at: DateTime<Utc>,
-}
-
-impl Aborted {
-    pub fn id(&self) -> u64 {
-        self.from.id()
-    }
-
-    pub fn meta(&self) -> &UpdateMeta {
-        self.from.meta()
-    }
-}
-
-#[derive(Debug, Serialize, Deserialize)]
-#[serde(rename_all = "camelCase")]
-pub struct Failed {
-    #[serde(flatten)]
-    pub from: Processing,
-    pub error: ResponseError,
-    pub failed_at: DateTime<Utc>,
-}
-
-impl Failed {
-    pub fn id(&self) -> u64 {
-        self.from.id()
-    }
-
-    pub fn meta(&self) -> &UpdateMeta {
-        self.from.meta()
-    }
-}
-
-#[derive(Debug, Serialize, Deserialize)]
-#[serde(tag = "status", rename_all = "camelCase")]
-pub enum UpdateStatus {
-    Processing(Processing),
-    Enqueued(Enqueued),
-    Processed(Processed),
-    Aborted(Aborted),
-    Failed(Failed),
-}
-
-impl UpdateStatus {
-    pub fn id(&self) -> u64 {
-        match self {
-            UpdateStatus::Processing(u) => u.id(),
-            UpdateStatus::Enqueued(u) => u.id(),
-            UpdateStatus::Processed(u) => u.id(),
-            UpdateStatus::Aborted(u) => u.id(),
-            UpdateStatus::Failed(u) => u.id(),
-        }
-    }
-
-    pub fn meta(&self) -> &UpdateMeta {
-        match self {
-            UpdateStatus::Processing(u) => u.meta(),
-            UpdateStatus::Enqueued(u) => u.meta(),
-            UpdateStatus::Processed(u) => u.meta(),
-            UpdateStatus::Aborted(u) => u.meta(),
-            UpdateStatus::Failed(u) => u.meta(),
-        }
-    }
-
-    pub fn processed(&self) -> Option<&Processed> {
-        match self {
-            UpdateStatus::Processed(p) => Some(p),
-            _ => None,
-        }
-    }
-}
-
-impl From<Enqueued> for UpdateStatus {
-    fn from(other: Enqueued) -> Self {
-        Self::Enqueued(other)
-    }
-}
-
-impl From<Aborted> for UpdateStatus {
-    fn from(other: Aborted) -> Self {
-        Self::Aborted(other)
-    }
-}
-
-impl From<Processed> for UpdateStatus {
-    fn from(other: Processed) -> Self {
-        Self::Processed(other)
-    }
-}
-
-impl From<Processing> for UpdateStatus {
-    fn from(other: Processing) -> Self {
-        Self::Processing(other)
-    }
-}
-
-impl From<Failed> for UpdateStatus {
-    fn from(other: Failed) -> Self {
-        Self::Failed(other)
-    }
-}

meilisearch-http/src/index_controller/uuid_resolver/actor.rs

@@ -1,98 +0,0 @@
-use std::{collections::HashSet, path::PathBuf};
-
-use log::{trace, warn};
-use tokio::sync::mpsc;
-use uuid::Uuid;
-
-use super::{error::UuidResolverError, Result, UuidResolveMsg, UuidStore};
-
-pub struct UuidResolverActor<S> {
-    inbox: mpsc::Receiver<UuidResolveMsg>,
-    store: S,
-}
-
-impl<S: UuidStore> UuidResolverActor<S> {
-    pub fn new(inbox: mpsc::Receiver<UuidResolveMsg>, store: S) -> Self {
-        Self { inbox, store }
-    }
-
-    pub async fn run(mut self) {
-        use UuidResolveMsg::*;
-
-        trace!("uuid resolver started");
-
-        loop {
-            match self.inbox.recv().await {
-                Some(Get { uid: name, ret }) => {
-                    let _ = ret.send(self.handle_get(name).await);
-                }
-                Some(Delete { uid: name, ret }) => {
-                    let _ = ret.send(self.handle_delete(name).await);
-                }
-                Some(List { ret }) => {
-                    let _ = ret.send(self.handle_list().await);
-                }
-                Some(Insert { ret, uuid, name }) => {
-                    let _ = ret.send(self.handle_insert(name, uuid).await);
-                }
-                Some(SnapshotRequest { path, ret }) => {
-                    let _ = ret.send(self.handle_snapshot(path).await);
-                }
-                Some(GetSize { ret }) => {
-                    let _ = ret.send(self.handle_get_size().await);
-                }
-                Some(DumpRequest { path, ret }) => {
-                    let _ = ret.send(self.handle_dump(path).await);
-                }
-                // all senders have been dropped, need to quit.
-                None => break,
-            }
-        }
-
-        warn!("exiting uuid resolver loop");
-    }
-
-    async fn handle_get(&self, uid: String) -> Result<Uuid> {
-        self.store
-            .get_uuid(uid.clone())
-            .await?
-            .ok_or(UuidResolverError::UnexistingIndex(uid))
-    }
-
-    async fn handle_delete(&self, uid: String) -> Result<Uuid> {
-        self.store
-            .delete(uid.clone())
-            .await?
-            .ok_or(UuidResolverError::UnexistingIndex(uid))
-    }
-
-    async fn handle_list(&self) -> Result<Vec<(String, Uuid)>> {
-        let result = self.store.list().await?;
-        Ok(result)
-    }
-
-    async fn handle_snapshot(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        self.store.snapshot(path).await
-    }
-
-    async fn handle_dump(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        self.store.dump(path).await
-    }
-
-    async fn handle_insert(&self, uid: String, uuid: Uuid) -> Result<()> {
-        if !is_index_uid_valid(&uid) {
-            return Err(UuidResolverError::BadlyFormatted(uid));
-        }
-        self.store.insert(uid, uuid).await?;
-        Ok(())
-    }
-
-    async fn handle_get_size(&self) -> Result<u64> {
-        self.store.get_size().await
-    }
-}
-
-fn is_index_uid_valid(uid: &str) -> bool {
-    uid.chars()
-        .all(|x| x.is_ascii_alphanumeric() || x == '-' || x == '_')
-}

meilisearch-http/src/index_controller/uuid_resolver/error.rs

@@ -1,34 +0,0 @@
-use meilisearch_error::{Code, ErrorCode};
-
-pub type Result<T> = std::result::Result<T, UuidResolverError>;
-
-#[derive(Debug, thiserror::Error)]
-pub enum UuidResolverError {
-    #[error("Index already exists.")]
-    NameAlreadyExist,
-    #[error("Index \"{0}\" not found.")]
-    UnexistingIndex(String),
-    #[error("Index must have a valid uid; Index uid can be of type integer or string only composed of alphanumeric characters, hyphens (-) and underscores (_).")]
-    BadlyFormatted(String),
-    #[error("Internal error: {0}")]
-    Internal(Box<dyn std::error::Error + Sync + Send + 'static>),
-}
-
-internal_error!(
-    UuidResolverError: heed::Error,
-    uuid::Error,
-    std::io::Error,
-    tokio::task::JoinError,
-    serde_json::Error
-);
-
-impl ErrorCode for UuidResolverError {
-    fn error_code(&self) -> Code {
-        match self {
-            UuidResolverError::NameAlreadyExist => Code::IndexAlreadyExists,
-            UuidResolverError::UnexistingIndex(_) => Code::IndexNotFound,
-            UuidResolverError::BadlyFormatted(_) => Code::InvalidIndexUid,
-            UuidResolverError::Internal(_) => Code::Internal,
-        }
-    }
-}

meilisearch-http/src/index_controller/uuid_resolver/handle_impl.rs

@@ -1,87 +0,0 @@
-use std::collections::HashSet;
-use std::path::{Path, PathBuf};
-
-use tokio::sync::{mpsc, oneshot};
-use uuid::Uuid;
-
-use super::{HeedUuidStore, Result, UuidResolveMsg, UuidResolverActor, UuidResolverHandle};
-
-#[derive(Clone)]
-pub struct UuidResolverHandleImpl {
-    sender: mpsc::Sender<UuidResolveMsg>,
-}
-
-impl UuidResolverHandleImpl {
-    pub fn new(path: impl AsRef<Path>) -> Result<Self> {
-        let (sender, reveiver) = mpsc::channel(100);
-        let store = HeedUuidStore::new(path)?;
-        let actor = UuidResolverActor::new(reveiver, store);
-        tokio::spawn(actor.run());
-        Ok(Self { sender })
-    }
-}
-
-#[async_trait::async_trait]
-impl UuidResolverHandle for UuidResolverHandleImpl {
-    async fn get(&self, name: String) -> Result<Uuid> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::Get { uid: name, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-
-    async fn delete(&self, name: String) -> Result<Uuid> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::Delete { uid: name, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-
-    async fn list(&self) -> Result<Vec<(String, Uuid)>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::List { ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-
-    async fn insert(&self, name: String, uuid: Uuid) -> Result<()> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::Insert { ret, name, uuid };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-
-    async fn snapshot(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::SnapshotRequest { path, ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-
-    async fn get_size(&self) -> Result<u64> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::GetSize { ret };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-    async fn dump(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        let (ret, receiver) = oneshot::channel();
-        let msg = UuidResolveMsg::DumpRequest { ret, path };
-        let _ = self.sender.send(msg).await;
-        Ok(receiver
-            .await
-            .expect("Uuid resolver actor has been killed")?)
-    }
-}

meilisearch-http/src/index_controller/uuid_resolver/mod.rs

@@ -1,35 +0,0 @@
-mod actor;
-pub mod error;
-mod handle_impl;
-mod message;
-pub mod store;
-
-use std::collections::HashSet;
-use std::path::PathBuf;
-
-use uuid::Uuid;
-
-use actor::UuidResolverActor;
-use error::Result;
-use message::UuidResolveMsg;
-use store::UuidStore;
-
-#[cfg(test)]
-use mockall::automock;
-
-pub use handle_impl::UuidResolverHandleImpl;
-pub use store::HeedUuidStore;
-
-const UUID_STORE_SIZE: usize = 1_073_741_824; //1GiB
-
-#[async_trait::async_trait]
-#[cfg_attr(test, automock)]
-pub trait UuidResolverHandle {
-    async fn get(&self, name: String) -> Result<Uuid>;
-    async fn insert(&self, name: String, uuid: Uuid) -> Result<()>;
-    async fn delete(&self, name: String) -> Result<Uuid>;
-    async fn list(&self) -> Result<Vec<(String, Uuid)>>;
-    async fn snapshot(&self, path: PathBuf) -> Result<HashSet<Uuid>>;
-    async fn get_size(&self) -> Result<u64>;
-    async fn dump(&self, path: PathBuf) -> Result<HashSet<Uuid>>;
-}

meilisearch-http/src/index_controller/uuid_resolver/store.rs

@@ -1,224 +0,0 @@
-use std::collections::HashSet;
-use std::fs::{create_dir_all, File};
-use std::io::{BufRead, BufReader, Write};
-use std::path::{Path, PathBuf};
-
-use heed::types::{ByteSlice, Str};
-use heed::{CompactionOption, Database, Env, EnvOpenOptions};
-use serde::{Deserialize, Serialize};
-use uuid::Uuid;
-
-use super::{error::UuidResolverError, Result, UUID_STORE_SIZE};
-use crate::helpers::EnvSizer;
-
-#[derive(Serialize, Deserialize)]
-struct DumpEntry {
-    uuid: Uuid,
-    uid: String,
-}
-
-const UUIDS_DB_PATH: &str = "index_uuids";
-
-#[async_trait::async_trait]
-pub trait UuidStore: Sized {
-    // Create a new entry for `name`. Return an error if `err` and the entry already exists, return
-    // the uuid otherwise.
-    async fn get_uuid(&self, uid: String) -> Result<Option<Uuid>>;
-    async fn delete(&self, uid: String) -> Result<Option<Uuid>>;
-    async fn list(&self) -> Result<Vec<(String, Uuid)>>;
-    async fn insert(&self, name: String, uuid: Uuid) -> Result<()>;
-    async fn snapshot(&self, path: PathBuf) -> Result<HashSet<Uuid>>;
-    async fn get_size(&self) -> Result<u64>;
-    async fn dump(&self, path: PathBuf) -> Result<HashSet<Uuid>>;
-}
-
-#[derive(Clone)]
-pub struct HeedUuidStore {
-    env: Env,
-    db: Database<Str, ByteSlice>,
-}
-
-impl HeedUuidStore {
-    pub fn new(path: impl AsRef<Path>) -> Result<Self> {
-        let path = path.as_ref().join(UUIDS_DB_PATH);
-        create_dir_all(&path)?;
-        let mut options = EnvOpenOptions::new();
-        options.map_size(UUID_STORE_SIZE); // 1GB
-        let env = options.open(path)?;
-        let db = env.create_database(None)?;
-        Ok(Self { env, db })
-    }
-
-    pub fn get_uuid(&self, name: String) -> Result<Option<Uuid>> {
-        let env = self.env.clone();
-        let db = self.db;
-        let txn = env.read_txn()?;
-        match db.get(&txn, &name)? {
-            Some(uuid) => {
-                let uuid = Uuid::from_slice(uuid)?;
-                Ok(Some(uuid))
-            }
-            None => Ok(None),
-        }
-    }
-
-    pub fn delete(&self, uid: String) -> Result<Option<Uuid>> {
-        let env = self.env.clone();
-        let db = self.db;
-        let mut txn = env.write_txn()?;
-        match db.get(&txn, &uid)? {
-            Some(uuid) => {
-                let uuid = Uuid::from_slice(uuid)?;
-                db.delete(&mut txn, &uid)?;
-                txn.commit()?;
-                Ok(Some(uuid))
-            }
-            None => Ok(None),
-        }
-    }
-
-    pub fn list(&self) -> Result<Vec<(String, Uuid)>> {
-        let env = self.env.clone();
-        let db = self.db;
-        let txn = env.read_txn()?;
-        let mut entries = Vec::new();
-        for entry in db.iter(&txn)? {
-            let (name, uuid) = entry?;
-            let uuid = Uuid::from_slice(uuid)?;
-            entries.push((name.to_owned(), uuid))
-        }
-        Ok(entries)
-    }
-
-    pub fn insert(&self, name: String, uuid: Uuid) -> Result<()> {
-        let env = self.env.clone();
-        let db = self.db;
-        let mut txn = env.write_txn()?;
-
-        if db.get(&txn, &name)?.is_some() {
-            return Err(UuidResolverError::NameAlreadyExist);
-        }
-
-        db.put(&mut txn, &name, uuid.as_bytes())?;
-        txn.commit()?;
-        Ok(())
-    }
-
-    pub fn snapshot(&self, mut path: PathBuf) -> Result<HashSet<Uuid>> {
-        let env = self.env.clone();
-        let db = self.db;
-        // Write transaction to acquire a lock on the database.
-        let txn = env.write_txn()?;
-        let mut entries = HashSet::new();
-        for entry in db.iter(&txn)? {
-            let (_, uuid) = entry?;
-            let uuid = Uuid::from_slice(uuid)?;
-            entries.insert(uuid);
-        }
-
-        // only perform snapshot if there are indexes
-        if !entries.is_empty() {
-            path.push(UUIDS_DB_PATH);
-            create_dir_all(&path).unwrap();
-            path.push("data.mdb");
-            env.copy_to_path(path, CompactionOption::Enabled)?;
-        }
-        Ok(entries)
-    }
-
-    pub fn get_size(&self) -> Result<u64> {
-        Ok(self.env.size())
-    }
-
-    pub fn dump(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        let dump_path = path.join(UUIDS_DB_PATH);
-        create_dir_all(&dump_path)?;
-        let dump_file_path = dump_path.join("data.jsonl");
-        let mut dump_file = File::create(&dump_file_path)?;
-        let mut uuids = HashSet::new();
-
-        let txn = self.env.read_txn()?;
-        for entry in self.db.iter(&txn)? {
-            let (uid, uuid) = entry?;
-            let uid = uid.to_string();
-            let uuid = Uuid::from_slice(uuid)?;
-
-            let entry = DumpEntry { uuid, uid };
-            serde_json::to_writer(&mut dump_file, &entry)?;
-            dump_file.write_all(b"\n").unwrap();
-
-            uuids.insert(uuid);
-        }
-
-        Ok(uuids)
-    }
-
-    pub fn load_dump(src: impl AsRef<Path>, dst: impl AsRef<Path>) -> Result<()> {
-        let uuid_resolver_path = dst.as_ref().join(UUIDS_DB_PATH);
-        std::fs::create_dir_all(&uuid_resolver_path)?;
-
-        let src_indexes = src.as_ref().join(UUIDS_DB_PATH).join("data.jsonl");
-        let indexes = File::open(&src_indexes)?;
-        let mut indexes = BufReader::new(indexes);
-        let mut line = String::new();
-
-        let db = Self::new(dst)?;
-        let mut txn = db.env.write_txn()?;
-
-        loop {
-            match indexes.read_line(&mut line) {
-                Ok(0) => break,
-                Ok(_) => {
-                    let DumpEntry { uuid, uid } = serde_json::from_str(&line)?;
-                    println!("importing {} {}", uid, uuid);
-                    db.db.put(&mut txn, &uid, uuid.as_bytes())?;
-                }
-                Err(e) => return Err(e.into()),
-            }
-
-            line.clear();
-        }
-        txn.commit()?;
-
-        db.env.prepare_for_closing().wait();
-
-        Ok(())
-    }
-}
-
-#[async_trait::async_trait]
-impl UuidStore for HeedUuidStore {
-    async fn get_uuid(&self, name: String) -> Result<Option<Uuid>> {
-        let this = self.clone();
-        tokio::task::spawn_blocking(move || this.get_uuid(name)).await?
-    }
-
-    async fn delete(&self, uid: String) -> Result<Option<Uuid>> {
-        let this = self.clone();
-        tokio::task::spawn_blocking(move || this.delete(uid)).await?
-    }
-
-    async fn list(&self) -> Result<Vec<(String, Uuid)>> {
-        let this = self.clone();
-        tokio::task::spawn_blocking(move || this.list()).await?
-    }
-
-    async fn insert(&self, name: String, uuid: Uuid) -> Result<()> {
-        let this = self.clone();
-        tokio::task::spawn_blocking(move || this.insert(name, uuid)).await?
-    }
-
-    async fn snapshot(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        let this = self.clone();
-        tokio::task::spawn_blocking(move || this.snapshot(path)).await?
-    }
-
-    async fn get_size(&self) -> Result<u64> {
-        self.get_size()
-    }
-
-    async fn dump(&self, path: PathBuf) -> Result<HashSet<Uuid>> {
-        let this = self.clone();
-        tokio::task::spawn_blocking(move || this.dump(path)).await?
-    }
-}

meilisearch-http/src/lib.rs

@@ -1,105 +1,92 @@
-//! # MeiliSearch
-//! Hello there, future contributors. If you are here and see this code, it's probably because you want to add a super new fancy feature in MeiliSearch or fix a bug and first of all, thank you for that!
-//!
-//! To help you in this task, we'll try to do a little overview of the project.
-//! ## Milli
-//! [Milli](https://github.com/meilisearch/milli) is the core library of MeiliSearch. It's where we actually index documents and perform searches. Its purpose is to do these two tasks as fast as possible. You can give an update to milli, and it'll uses as many cores as provided to perform it as fast as possible. Nothing more. You can perform searches at the same time (search only uses one core).
-//! As you can see, we're missing quite a lot of features here; milli does not handle multiples indexes, it can't queue updates, it doesn't provide any web / API frontend, it doesn't implement dumps or snapshots, etc...
-//!
-//! ## `Index` module
-//! The [index] module is what encapsulates one milli index. It abstracts over its transaction and isolates a task that can be run into a thread. This is the unit of interaction with milli.
-//! If you add a feature to milli, you'll probably need to add it in this module too before exposing it to the rest of meilisearch.
-//!
-//! ## `IndexController` module
-//! To handle multiple indexes, we created an [index_controller]. It's in charge of creating new indexes, keeping references to all its indexes, forward asynchronous updates to its indexes, and provide an API to search in its indexes synchronously.
-//! To achieves this goal, we use an [actor model](https://en.wikipedia.org/wiki/Actor_model).
-//!
-//! ### The actor model
-//! Every actor is composed of at least three files:
-//! - `mod.rs` declare and import all the files used by the actor. We also describe the interface (= all the methods) used to interact with the actor. If you are not modifying anything inside of an actor, this is usually all you need to see.
-//! - `handle_impl.rs` implements the interface described in the `mod.rs`; in reality, there is no code logic in this file. Every method is only wrapping its parameters in a structure that is sent to the actor. This is useful for test and futureproofing.
-//! - `message.rs` contains an enum that describes all the interactions you can have with the actor.
-//! - `actor.rs` is used to create and execute the actor. It's where we'll write the loop looking for new messages and actually perform the tasks.
-//!
-//! MeiliSearch currently uses four actors:
-//! - [`uuid_resolver`](index_controller/uuid_resolver/index.html) hold the association between the user-provided indexes name and the internal [`uuid`](https://en.wikipedia.org/wiki/Universally_unique_identifier) representation we use.
-//! - [`index_actor`](index_controller::index_actor) is our representation of multiples indexes. Any request made to MeiliSearch that needs to talk to milli will pass through this actor.
-//! - [`update_actor`](index_controller/update_actor/index.html) is in charge of indexes updates. Since updates can take a long time to receive and  process, we need to:
-//!   1. Store them as fast as possible so we can continue to receive other updates even if nothing has been processed
-//!   2. Feed the `index_actor` with a new update every time it finished its current job.
-//! - [`dump_actor`](index_controller/dump_actor/index.html) this actor handle the  [dumps](https://docs.meilisearch.com/reference/api/dump.html). It needs to contact all the others actors and create a dump of everything that was currently happening.
-//!
-//! ## Data module
-//! The [data] module provide a unified interface to communicate with the index controller and other services (snapshot, dumps, ...), initialize the MeiliSearch instance
-//!
-//! ## HTTP server
-//! To handle the web and API part, we are using [actix-web](https://docs.rs/actix-web/); you can find all routes in the [routes] module.
-//! Currently, the configuration of actix-web is made in the [lib.rs](crate).
-//! Most of the routes use [extractors] to handle the authentication.
-
 #![allow(rustdoc::private_intra_doc_links)]
-pub mod data;
 #[macro_use]
 pub mod error;
+pub mod analytics;
+mod task;
 #[macro_use]
 pub mod extractors;
 pub mod helpers;
-mod index;
-mod index_controller;
 pub mod option;
 pub mod routes;
 
-#[cfg(all(not(debug_assertions), feature = "analytics"))]
-pub mod analytics;
+use std::sync::Arc;
+use std::time::Duration;
 
-use crate::extractors::authentication::AuthConfig;
-
-pub use self::data::Data;
+use crate::error::MeilisearchHttpError;
+use actix_web::error::JsonPayloadError;
+use analytics::Analytics;
+use error::PayloadError;
+use http::header::CONTENT_TYPE;
 pub use option::Opt;
 
-use actix_web::web;
+use actix_web::{web, HttpRequest};
 
-use extractors::authentication::policies::*;
 use extractors::payload::PayloadConfig;
+use meilisearch_auth::AuthController;
+use meilisearch_lib::MeiliSearch;
 
-pub fn configure_data(config: &mut web::ServiceConfig, data: Data) {
-    let http_payload_size_limit = data.http_payload_size_limit();
+pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<MeiliSearch> {
+    let mut meilisearch = MeiliSearch::builder();
+    meilisearch
+        .set_max_index_size(opt.max_index_size.get_bytes() as usize)
+        .set_max_task_store_size(opt.max_task_db_size.get_bytes() as usize)
+        .set_ignore_missing_snapshot(opt.ignore_missing_snapshot)
+        .set_ignore_snapshot_if_db_exists(opt.ignore_snapshot_if_db_exists)
+        .set_dump_dst(opt.dumps_dir.clone())
+        .set_snapshot_interval(Duration::from_secs(opt.snapshot_interval_sec))
+        .set_snapshot_dir(opt.snapshot_dir.clone());
+
+    if let Some(ref path) = opt.import_snapshot {
+        meilisearch.set_import_snapshot(path.clone());
+    }
+
+    if let Some(ref path) = opt.import_dump {
+        meilisearch.set_dump_src(path.clone());
+    }
+
+    if opt.schedule_snapshot {
+        meilisearch.set_schedule_snapshot();
+    }
+
+    meilisearch.build(opt.db_path.clone(), opt.indexer_options.clone())
+}
+
+pub fn configure_data(
+    config: &mut web::ServiceConfig,
+    data: MeiliSearch,
+    auth: AuthController,
+    opt: &Opt,
+    analytics: Arc<dyn Analytics>,
+) {
+    let http_payload_size_limit = opt.http_payload_size_limit.get_bytes() as usize;
     config
-        .data(data.clone())
         .app_data(data)
+        .app_data(auth)
+        .app_data(web::Data::from(analytics))
         .app_data(
             web::JsonConfig::default()
-                .limit(http_payload_size_limit)
-                .content_type(|_mime| true) // Accept all mime types
-                .error_handler(|err, _req| error::payload_error_handler(err).into()),
+                .content_type(|mime| mime == mime::APPLICATION_JSON)
+                .error_handler(|err, req: &HttpRequest| match err {
+                    JsonPayloadError::ContentType => match req.headers().get(CONTENT_TYPE) {
+                        Some(content_type) => MeilisearchHttpError::InvalidContentType(
+                            content_type.to_str().unwrap_or("unknown").to_string(),
+                            vec![mime::APPLICATION_JSON.to_string()],
+                        )
+                        .into(),
+                        None => MeilisearchHttpError::MissingContentType(vec![
+                            mime::APPLICATION_JSON.to_string(),
+                        ])
+                        .into(),
+                    },
+                    err => PayloadError::from(err).into(),
+                }),
         )
         .app_data(PayloadConfig::new(http_payload_size_limit))
         .app_data(
-            web::QueryConfig::default()
-                .error_handler(|err, _req| error::payload_error_handler(err).into()),
+            web::QueryConfig::default().error_handler(|err, _req| PayloadError::from(err).into()),
         );
 }
 
-pub fn configure_auth(config: &mut web::ServiceConfig, data: &Data) {
-    let keys = data.api_keys();
-    let auth_config = if let Some(ref master_key) = keys.master {
-        let private_key = keys.private.as_ref().unwrap();
-        let public_key = keys.public.as_ref().unwrap();
-        let mut policies = init_policies!(Public, Private, Admin);
-        create_users!(
-            policies,
-            master_key.as_bytes() => { Admin, Private, Public },
-            private_key.as_bytes() => { Private, Public },
-            public_key.as_bytes() => { Public }
-        );
-        AuthConfig::Auth(policies)
-    } else {
-        AuthConfig::NoAuth
-    };
-
-    config.app_data(auth_config);
-}
-
 #[cfg(feature = "mini-dashboard")]
 pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
     use actix_web::HttpResponse;
@@ -111,7 +98,6 @@ pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
 
     if enable_frontend {
         let generated = generated::generate();
-        let mut scope = web::scope("/");
         // Generate routes for mini-dashboard assets
         for (path, resource) in generated.into_iter() {
             let Resource {
@@ -123,12 +109,11 @@ pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
                     web::get().to(move || HttpResponse::Ok().content_type(mime_type).body(data)),
                 ));
             } else {
-                scope = scope.service(web::resource(path).route(
+                config.service(web::resource(path).route(
                     web::get().to(move || HttpResponse::Ok().content_type(mime_type).body(data)),
                 ));
             }
         }
-        config.service(scope);
     } else {
         config.service(web::resource("/").route(web::get().to(routes::running)));
     }
@@ -141,23 +126,24 @@ pub fn dashboard(config: &mut web::ServiceConfig, _enable_frontend: bool) {
 
 #[macro_export]
 macro_rules! create_app {
-    ($data:expr, $enable_frontend:expr) => {{
+    ($data:expr, $auth:expr, $enable_frontend:expr, $opt:expr, $analytics:expr) => {{
         use actix_cors::Cors;
         use actix_web::middleware::TrailingSlash;
         use actix_web::App;
         use actix_web::{middleware, web};
+        use meilisearch_error::ResponseError;
+        use meilisearch_http::error::MeilisearchHttpError;
         use meilisearch_http::routes;
-        use meilisearch_http::{configure_auth, configure_data, dashboard};
+        use meilisearch_http::{configure_data, dashboard};
 
         App::new()
-            .configure(|s| configure_data(s, $data.clone()))
-            .configure(|s| configure_auth(s, &$data))
+            .configure(|s| configure_data(s, $data.clone(), $auth.clone(), &$opt, $analytics))
             .configure(routes::configure)
             .configure(|s| dashboard(s, $enable_frontend))
             .wrap(
                 Cors::default()
                     .send_wildcard()
-                    .allowed_headers(vec!["content-type", "x-meili-api-key"])
+                    .allow_any_header()
                     .allow_any_origin()
                     .allow_any_method()
                     .max_age(86_400), // 24h

meilisearch-http/src/main.rs

@@ -1,21 +1,20 @@
 use std::env;
+use std::sync::Arc;
 
 use actix_web::HttpServer;
-use main_error::MainError;
-use meilisearch_http::{create_app, Data, Opt};
-use structopt::StructOpt;
-
-#[cfg(all(not(debug_assertions), feature = "analytics"))]
+use meilisearch_auth::AuthController;
 use meilisearch_http::analytics;
+use meilisearch_http::analytics::Analytics;
+use meilisearch_http::{create_app, setup_meilisearch, Opt};
+use meilisearch_lib::MeiliSearch;
+use structopt::StructOpt;
 
 #[cfg(target_os = "linux")]
 #[global_allocator]
-static ALLOC: jemallocator::Jemalloc = jemallocator::Jemalloc;
-
-#[actix_web::main]
-async fn main() -> Result<(), MainError> {
-    let opt = Opt::from_args();
+static ALLOC: tikv_jemallocator::Jemalloc = tikv_jemallocator::Jemalloc;
 
+/// does all the setup before meilisearch is launched
+fn setup(opt: &Opt) -> anyhow::Result<()> {
     let mut log_builder = env_logger::Builder::new();
     log_builder.parse_filters(&opt.log_level);
     if opt.log_level == "info" {
@@ -25,40 +24,66 @@ async fn main() -> Result<(), MainError> {
 
     log_builder.init();
 
+    Ok(())
+}
+
+#[actix_web::main]
+async fn main() -> anyhow::Result<()> {
+    let opt = Opt::from_args();
+
+    setup(&opt)?;
+
     match opt.env.as_ref() {
         "production" => {
             if opt.master_key.is_none() {
-                return Err(
+                anyhow::bail!(
                     "In production mode, the environment variable MEILI_MASTER_KEY is mandatory"
-                        .into(),
-                );
+                )
             }
         }
         "development" => (),
         _ => unreachable!(),
     }
 
-    let data = Data::new(opt.clone())?;
+    let meilisearch = setup_meilisearch(&opt)?;
+
+    let auth_controller = AuthController::new(&opt.db_path, &opt.master_key)?;
 
     #[cfg(all(not(debug_assertions), feature = "analytics"))]
-    if !opt.no_analytics {
-        let analytics_data = data.clone();
-        let analytics_opt = opt.clone();
-        tokio::task::spawn(analytics::analytics_sender(analytics_data, analytics_opt));
-    }
+    let (analytics, user) = if opt.analytics() {
+        analytics::SegmentAnalytics::new(&opt, &meilisearch).await
+    } else {
+        analytics::MockAnalytics::new(&opt)
+    };
+    #[cfg(any(debug_assertions, not(feature = "analytics")))]
+    let (analytics, user) = analytics::MockAnalytics::new(&opt);
 
-    print_launch_resume(&opt, &data);
+    print_launch_resume(&opt, &user);
 
-    run_http(data, opt).await?;
+    run_http(meilisearch, auth_controller, opt, analytics).await?;
 
     Ok(())
 }
 
-async fn run_http(data: Data, opt: Opt) -> Result<(), Box<dyn std::error::Error>> {
+async fn run_http(
+    data: MeiliSearch,
+    auth_controller: AuthController,
+    opt: Opt,
+    analytics: Arc<dyn Analytics>,
+) -> anyhow::Result<()> {
     let _enable_dashboard = &opt.env == "development";
-    let http_server = HttpServer::new(move || create_app!(data, _enable_dashboard))
-        // Disable signals allows the server to terminate immediately when a user enter CTRL-C
-        .disable_signals();
+    let opt_clone = opt.clone();
+    let http_server = HttpServer::new(move || {
+        create_app!(
+            data,
+            auth_controller,
+            _enable_dashboard,
+            opt_clone,
+            analytics.clone()
+        )
+    })
+    // Disable signals allows the server to terminate immediately when a user enter CTRL-C
+    .disable_signals();
 
     if let Some(config) = opt.get_ssl_config()? {
         http_server
@@ -66,12 +91,12 @@ async fn run_http(data: Data, opt: Opt) -> Result<(), Box<dyn std::error::Error>
             .run()
             .await?;
     } else {
-        http_server.bind(opt.http_addr)?.run().await?;
+        http_server.bind(&opt.http_addr)?.run().await?;
     }
     Ok(())
 }
 
-pub fn print_launch_resume(opt: &Opt, data: &Data) {
+pub fn print_launch_resume(opt: &Opt, user: &str) {
     let commit_sha = option_env!("VERGEN_GIT_SHA").unwrap_or("unknown");
     let commit_date = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP").unwrap_or("unknown");
 
@@ -100,23 +125,27 @@ pub fn print_launch_resume(opt: &Opt, data: &Data) {
 
     #[cfg(all(not(debug_assertions), feature = "analytics"))]
     {
-        if opt.no_analytics {
-            eprintln!("Anonymous telemetry:\t\"Disabled\"");
-        } else {
+        if opt.analytics() {
             eprintln!(
                 "
 Thank you for using MeiliSearch!
 
 We collect anonymized analytics to improve our product and your experience. To learn more, including how to turn off analytics, visit our dedicated documentation page: https://docs.meilisearch.com/learn/what_is_meilisearch/telemetry.html
 
-Anonymous telemetry:   \"Enabled\""
+Anonymous telemetry:\t\"Enabled\""
             );
+        } else {
+            eprintln!("Anonymous telemetry:\t\"Disabled\"");
         }
     }
 
+    if !user.is_empty() {
+        eprintln!("Instance UID:\t\t\"{}\"", user);
+    }
+
     eprintln!();
 
-    if data.api_keys().master.is_some() {
+    if opt.master_key.is_some() {
         eprintln!("A Master Key has been set. Requests to MeiliSearch won't be authorized unless you provide an authentication key.");
     } else {
         eprintln!("No master key found; The server will accept unidentified requests. \
@@ -126,6 +155,6 @@ Anonymous telemetry:   \"Enabled\""
     eprintln!();
     eprintln!("Documentation:\t\thttps://docs.meilisearch.com");
     eprintln!("Source code:\t\thttps://github.com/meilisearch/meilisearch");
-    eprintln!("Contact:\t\thttps://docs.meilisearch.com/resources/contact.html or bonjour@meilisearch.com");
+    eprintln!("Contact:\t\thttps://docs.meilisearch.com/resources/contact.html");
     eprintln!();
 }

meilisearch-http/src/option.rs

@@ -1,71 +1,16 @@
-use byte_unit::ByteError;
-use std::fmt;
+use std::fs;
 use std::io::{BufReader, Read};
-use std::ops::Deref;
 use std::path::PathBuf;
-use std::str::FromStr;
 use std::sync::Arc;
-use std::{error, fs};
 
 use byte_unit::Byte;
-use milli::CompressionType;
+use meilisearch_lib::options::IndexerOpts;
 use rustls::internal::pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
 use rustls::{
     AllowAnyAnonymousOrAuthenticatedClient, AllowAnyAuthenticatedClient, NoClientAuth,
     RootCertStore,
 };
 use structopt::StructOpt;
-use sysinfo::{RefreshKind, System, SystemExt};
-
-#[derive(Debug, Clone, StructOpt)]
-pub struct IndexerOpts {
-    /// The amount of documents to skip before printing
-    /// a log regarding the indexing advancement.
-    #[structopt(long, default_value = "100000")] // 100k
-    pub log_every_n: usize,
-
-    /// Grenad max number of chunks in bytes.
-    #[structopt(long)]
-    pub max_nb_chunks: Option<usize>,
-
-    /// The maximum amount of memory the indexer will use. It defaults to 2/3
-    /// of the available memory. It is recommended to use something like 80%-90%
-    /// of the available memory, no more.
-    ///
-    /// In case the engine is unable to retrieve the available memory the engine will
-    /// try to use the memory it needs but without real limit, this can lead to
-    /// Out-Of-Memory issues and it is recommended to specify the amount of memory to use.
-    #[structopt(long, default_value)]
-    pub max_memory: MaxMemory,
-
-    /// The name of the compression algorithm to use when compressing intermediate
-    /// Grenad chunks while indexing documents.
-    ///
-    /// Choosing a fast algorithm will make the indexing faster but may consume more memory.
-    #[structopt(long, default_value = "snappy", possible_values = &["snappy", "zlib", "lz4", "lz4hc", "zstd"])]
-    pub chunk_compression_type: CompressionType,
-
-    /// The level of compression of the chosen algorithm.
-    #[structopt(long, requires = "chunk-compression-type")]
-    pub chunk_compression_level: Option<u32>,
-
-    /// Number of parallel jobs for indexing, defaults to # of CPUs.
-    #[structopt(long)]
-    pub indexing_jobs: Option<usize>,
-}
-
-impl Default for IndexerOpts {
-    fn default() -> Self {
-        Self {
-            log_every_n: 100_000,
-            max_nb_chunks: None,
-            max_memory: MaxMemory::default(),
-            chunk_compression_type: CompressionType::None,
-            chunk_compression_level: None,
-            indexing_jobs: None,
-        }
-    }
-}
 
 const POSSIBLE_ENV: [&str; 2] = ["development", "production"];
 
@@ -93,15 +38,15 @@ pub struct Opt {
     /// Do not send analytics to Meili.
     #[cfg(all(not(debug_assertions), feature = "analytics"))]
     #[structopt(long, env = "MEILI_NO_ANALYTICS")]
-    pub no_analytics: bool,
+    pub no_analytics: Option<Option<bool>>,
 
     /// The maximum size, in bytes, of the main lmdb database directory
     #[structopt(long, env = "MEILI_MAX_INDEX_SIZE", default_value = "100 GiB")]
     pub max_index_size: Byte,
 
     /// The maximum size, in bytes, of the update lmdb database directory
-    #[structopt(long, env = "MEILI_MAX_UDB_SIZE", default_value = "100 GiB")]
-    pub max_udb_size: Byte,
+    #[structopt(long, env = "MEILI_MAX_TASK_DB_SIZE", default_value = "100 GiB")]
+    pub max_task_db_size: Byte,
 
     /// The maximum size, in bytes, of accepted JSON payloads
     #[structopt(long, env = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT", default_value = "100 MB")]
@@ -184,7 +129,17 @@ pub struct Opt {
 }
 
 impl Opt {
-    pub fn get_ssl_config(&self) -> Result<Option<rustls::ServerConfig>, Box<dyn error::Error>> {
+    /// Wether analytics should be enabled or not.
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
+    pub fn analytics(&self) -> bool {
+        match self.no_analytics {
+            None => true,
+            Some(None) => false,
+            Some(Some(disabled)) => !disabled,
+        }
+    }
+
+    pub fn get_ssl_config(&self) -> anyhow::Result<Option<rustls::ServerConfig>> {
         if let (Some(cert_path), Some(key_path)) = (&self.ssl_cert_path, &self.ssl_key_path) {
             let client_auth = match &self.ssl_auth_path {
                 Some(auth_path) => {
@@ -210,7 +165,7 @@ impl Opt {
             let ocsp = load_ocsp(&self.ssl_ocsp_path)?;
             config
                 .set_single_cert_with_ocsp_and_sct(certs, privkey, ocsp, vec![])
-                .map_err(|_| "bad certificates/private key")?;
+                .map_err(|_| anyhow::anyhow!("bad certificates/private key"))?;
 
             if self.ssl_resumption {
                 config.set_persistence(rustls::ServerSessionMemoryCache::new(256));
@@ -227,82 +182,31 @@ impl Opt {
     }
 }
 
-/// A type used to detect the max memory available and use 2/3 of it.
-#[derive(Debug, Clone, Copy)]
-pub struct MaxMemory(Option<Byte>);
-
-impl FromStr for MaxMemory {
-    type Err = ByteError;
-
-    fn from_str(s: &str) -> Result<MaxMemory, ByteError> {
-        Byte::from_str(s).map(Some).map(MaxMemory)
-    }
-}
-
-impl Default for MaxMemory {
-    fn default() -> MaxMemory {
-        MaxMemory(
-            total_memory_bytes()
-                .map(|bytes| bytes * 2 / 3)
-                .map(Byte::from_bytes),
-        )
-    }
-}
-
-impl fmt::Display for MaxMemory {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        match self.0 {
-            Some(memory) => write!(f, "{}", memory.get_appropriate_unit(true)),
-            None => f.write_str("unknown"),
-        }
-    }
-}
-
-impl Deref for MaxMemory {
-    type Target = Option<Byte>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl MaxMemory {
-    pub fn unlimited() -> Self {
-        Self(None)
-    }
-}
-
-/// Returns the total amount of bytes available or `None` if this system isn't supported.
-fn total_memory_bytes() -> Option<u64> {
-    if System::IS_SUPPORTED {
-        let memory_kind = RefreshKind::new().with_memory();
-        let mut system = System::new_with_specifics(memory_kind);
-        system.refresh_memory();
-        Some(system.total_memory() * 1024) // KiB into bytes
-    } else {
-        None
-    }
-}
-
-fn load_certs(filename: PathBuf) -> Result<Vec<rustls::Certificate>, Box<dyn error::Error>> {
-    let certfile = fs::File::open(filename).map_err(|_| "cannot open certificate file")?;
+fn load_certs(filename: PathBuf) -> anyhow::Result<Vec<rustls::Certificate>> {
+    let certfile =
+        fs::File::open(filename).map_err(|_| anyhow::anyhow!("cannot open certificate file"))?;
     let mut reader = BufReader::new(certfile);
-    Ok(certs(&mut reader).map_err(|_| "cannot read certificate file")?)
+    certs(&mut reader).map_err(|_| anyhow::anyhow!("cannot read certificate file"))
 }
 
-fn load_private_key(filename: PathBuf) -> Result<rustls::PrivateKey, Box<dyn error::Error>> {
+fn load_private_key(filename: PathBuf) -> anyhow::Result<rustls::PrivateKey> {
     let rsa_keys = {
-        let keyfile =
-            fs::File::open(filename.clone()).map_err(|_| "cannot open private key file")?;
+        let keyfile = fs::File::open(filename.clone())
+            .map_err(|_| anyhow::anyhow!("cannot open private key file"))?;
         let mut reader = BufReader::new(keyfile);
-        rsa_private_keys(&mut reader).map_err(|_| "file contains invalid rsa private key")?
+        rsa_private_keys(&mut reader)
+            .map_err(|_| anyhow::anyhow!("file contains invalid rsa private key"))?
     };
 
     let pkcs8_keys = {
-        let keyfile = fs::File::open(filename).map_err(|_| "cannot open private key file")?;
+        let keyfile = fs::File::open(filename)
+            .map_err(|_| anyhow::anyhow!("cannot open private key file"))?;
         let mut reader = BufReader::new(keyfile);
-        pkcs8_private_keys(&mut reader)
-            .map_err(|_| "file contains invalid pkcs8 private key (encrypted keys not supported)")?
+        pkcs8_private_keys(&mut reader).map_err(|_| {
+            anyhow::anyhow!(
+                "file contains invalid pkcs8 private key (encrypted keys not supported)"
+            )
+        })?
     };
 
     // prefer to load pkcs8 keys
@@ -314,14 +218,14 @@ fn load_private_key(filename: PathBuf) -> Result<rustls::PrivateKey, Box<dyn err
     }
 }
 
-fn load_ocsp(filename: &Option<PathBuf>) -> Result<Vec<u8>, Box<dyn error::Error>> {
+fn load_ocsp(filename: &Option<PathBuf>) -> anyhow::Result<Vec<u8>> {
     let mut ret = Vec::new();
 
     if let Some(ref name) = filename {
         fs::File::open(name)
-            .map_err(|_| "cannot open ocsp file")?
+            .map_err(|_| anyhow::anyhow!("cannot open ocsp file"))?
             .read_to_end(&mut ret)
-            .map_err(|_| "cannot read oscp file")?;
+            .map_err(|_| anyhow::anyhow!("cannot read oscp file"))?;
     }
 
     Ok(ret)

meilisearch-http/src/routes/api_key.rs

@@ -0,0 +1,134 @@
+use std::str;
+
+use actix_web::{web, HttpRequest, HttpResponse};
+use chrono::SecondsFormat;
+
+use meilisearch_auth::{generate_key, Action, AuthController, Key};
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+use crate::extractors::authentication::{policies::*, GuardedData};
+use meilisearch_error::ResponseError;
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(
+        web::resource("")
+            .route(web::post().to(create_api_key))
+            .route(web::get().to(list_api_keys)),
+    )
+    .service(
+        web::resource("/{api_key}")
+            .route(web::get().to(get_api_key))
+            .route(web::patch().to(patch_api_key))
+            .route(web::delete().to(delete_api_key)),
+    );
+}
+
+pub async fn create_api_key(
+    auth_controller: GuardedData<MasterPolicy, AuthController>,
+    body: web::Json<Value>,
+    _req: HttpRequest,
+) -> Result<HttpResponse, ResponseError> {
+    let key = auth_controller.create_key(body.into_inner()).await?;
+    let res = KeyView::from_key(key, auth_controller.get_master_key());
+
+    Ok(HttpResponse::Created().json(res))
+}
+
+pub async fn list_api_keys(
+    auth_controller: GuardedData<MasterPolicy, AuthController>,
+    _req: HttpRequest,
+) -> Result<HttpResponse, ResponseError> {
+    let keys = auth_controller.list_keys().await?;
+    let res: Vec<_> = keys
+        .into_iter()
+        .map(|k| KeyView::from_key(k, auth_controller.get_master_key()))
+        .collect();
+
+    Ok(HttpResponse::Ok().json(KeyListView::from(res)))
+}
+
+pub async fn get_api_key(
+    auth_controller: GuardedData<MasterPolicy, AuthController>,
+    path: web::Path<AuthParam>,
+) -> Result<HttpResponse, ResponseError> {
+    // keep 8 first characters that are the ID of the API key.
+    let key = auth_controller.get_key(&path.api_key).await?;
+    let res = KeyView::from_key(key, auth_controller.get_master_key());
+
+    Ok(HttpResponse::Ok().json(res))
+}
+
+pub async fn patch_api_key(
+    auth_controller: GuardedData<MasterPolicy, AuthController>,
+    body: web::Json<Value>,
+    path: web::Path<AuthParam>,
+) -> Result<HttpResponse, ResponseError> {
+    let key = auth_controller
+        // keep 8 first characters that are the ID of the API key.
+        .update_key(&path.api_key, body.into_inner())
+        .await?;
+    let res = KeyView::from_key(key, auth_controller.get_master_key());
+
+    Ok(HttpResponse::Ok().json(res))
+}
+
+pub async fn delete_api_key(
+    auth_controller: GuardedData<MasterPolicy, AuthController>,
+    path: web::Path<AuthParam>,
+) -> Result<HttpResponse, ResponseError> {
+    // keep 8 first characters that are the ID of the API key.
+    auth_controller.delete_key(&path.api_key).await?;
+
+    Ok(HttpResponse::NoContent().finish())
+}
+
+#[derive(Deserialize)]
+pub struct AuthParam {
+    api_key: String,
+}
+
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct KeyView {
+    description: Option<String>,
+    key: String,
+    actions: Vec<Action>,
+    indexes: Vec<String>,
+    expires_at: Option<String>,
+    created_at: String,
+    updated_at: String,
+}
+
+impl KeyView {
+    fn from_key(key: Key, master_key: Option<&String>) -> Self {
+        let key_id = str::from_utf8(&key.id).unwrap();
+        let generated_key = match master_key {
+            Some(master_key) => generate_key(master_key.as_bytes(), key_id),
+            None => generate_key(&[], key_id),
+        };
+
+        KeyView {
+            description: key.description,
+            key: generated_key,
+            actions: key.actions,
+            indexes: key.indexes,
+            expires_at: key
+                .expires_at
+                .map(|dt| dt.to_rfc3339_opts(SecondsFormat::Secs, true)),
+            created_at: key.created_at.to_rfc3339_opts(SecondsFormat::Secs, true),
+            updated_at: key.updated_at.to_rfc3339_opts(SecondsFormat::Secs, true),
+        }
+    }
+}
+
+#[derive(Debug, Serialize)]
+struct KeyListView {
+    results: Vec<KeyView>,
+}
+
+impl From<Vec<KeyView>> for KeyListView {
+    fn from(results: Vec<KeyView>) -> Self {
+        Self { results }
+    }
+}

meilisearch-http/src/routes/dump.rs

@@ -1,18 +1,26 @@
-use actix_web::{web, HttpResponse};
+use actix_web::{web, HttpRequest, HttpResponse};
 use log::debug;
+use meilisearch_error::ResponseError;
+use meilisearch_lib::MeiliSearch;
 use serde::{Deserialize, Serialize};
+use serde_json::json;
 
-use crate::error::ResponseError;
+use crate::analytics::Analytics;
 use crate::extractors::authentication::{policies::*, GuardedData};
-use crate::Data;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(create_dump)))
         .service(web::resource("/{dump_uid}/status").route(web::get().to(get_dump_status)));
 }
 
-pub async fn create_dump(data: GuardedData<Private, Data>) -> Result<HttpResponse, ResponseError> {
-    let res = data.create_dump().await?;
+pub async fn create_dump(
+    meilisearch: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, MeiliSearch>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    analytics.publish("Dump Created".to_string(), json!({}), Some(&req));
+
+    let res = meilisearch.create_dump().await?;
 
     debug!("returns: {:?}", res);
     Ok(HttpResponse::Accepted().json(res))
@@ -30,10 +38,10 @@ struct DumpParam {
 }
 
 async fn get_dump_status(
-    data: GuardedData<Private, Data>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DUMPS_GET }>, MeiliSearch>,
     path: web::Path<DumpParam>,
 ) -> Result<HttpResponse, ResponseError> {
-    let res = data.dump_status(path.dump_uid.clone()).await?;
+    let res = meilisearch.dump_info(path.dump_uid.clone()).await?;
 
     debug!("returns: {:?}", res);
     Ok(HttpResponse::Ok().json(res))

meilisearch-http/src/routes/indexes/documents.rs

@@ -1,50 +1,64 @@
-use actix_web::{web, HttpResponse};
+use actix_web::error::PayloadError;
+use actix_web::http::header::CONTENT_TYPE;
+use actix_web::web::Bytes;
+use actix_web::HttpMessage;
+use actix_web::{web, HttpRequest, HttpResponse};
+use bstr::ByteSlice;
+use futures::{Stream, StreamExt};
 use log::debug;
-use milli::update::{IndexDocumentsMethod, UpdateFormat};
+use meilisearch_error::ResponseError;
+use meilisearch_lib::index_controller::{DocumentAdditionFormat, Update};
+use meilisearch_lib::milli::update::IndexDocumentsMethod;
+use meilisearch_lib::MeiliSearch;
+use mime::Mime;
+use once_cell::sync::Lazy;
 use serde::Deserialize;
 use serde_json::Value;
+use tokio::sync::mpsc;
 
-use crate::error::ResponseError;
+use crate::analytics::Analytics;
+use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::{policies::*, GuardedData};
 use crate::extractors::payload::Payload;
-use crate::routes::IndexParam;
-use crate::Data;
+use crate::task::SummarizedTaskView;
 
 const DEFAULT_RETRIEVE_DOCUMENTS_OFFSET: usize = 0;
 const DEFAULT_RETRIEVE_DOCUMENTS_LIMIT: usize = 20;
 
-/*
-macro_rules! guard_content_type {
-    ($fn_name:ident, $guard_value:literal) => {
-        fn $fn_name(head: &actix_web::dev::RequestHead) -> bool {
-            if let Some(content_type) = head.headers.get("Content-Type") {
-                content_type
-                    .to_str()
-                    .map(|v| v.contains($guard_value))
-                    .unwrap_or(false)
-            } else {
-                false
-            }
+static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
+    vec![
+        "application/json".to_string(),
+        "application/x-ndjson".to_string(),
+        "text/csv".to_string(),
+    ]
+});
+
+/// This is required because Payload is not Sync nor Send
+fn payload_to_stream(mut payload: Payload) -> impl Stream<Item = Result<Bytes, PayloadError>> {
+    let (snd, recv) = mpsc::channel(1);
+    tokio::task::spawn_local(async move {
+        while let Some(data) = payload.next().await {
+            let _ = snd.send(data).await;
         }
-    };
+    });
+    tokio_stream::wrappers::ReceiverStream::new(recv)
 }
 
-guard_content_type!(guard_json, "application/json");
-*/
-
-fn guard_json(head: &actix_web::dev::RequestHead) -> bool {
-    if let Some(_content_type) = head.headers.get("Content-Type") {
-        // CURRENTLY AND FOR THIS RELEASE ONLY WE DECIDED TO INTERPRET ALL CONTENT-TYPES AS JSON
-        true
-        /*
-        content_type
-            .to_str()
-            .map(|v| v.contains("application/json"))
-            .unwrap_or(false)
-        */
-    } else {
-        // if no content-type is specified we still accept the data as json!
-        true
+/// Extracts the mime type from the content type and return
+/// a meilisearch error if anyhthing bad happen.
+fn extract_mime_type(req: &HttpRequest) -> Result<Option<Mime>, MeilisearchHttpError> {
+    match req.mime_type() {
+        Ok(Some(mime)) => Ok(Some(mime)),
+        Ok(None) => Ok(None),
+        Err(_) => match req.headers().get(CONTENT_TYPE) {
+            Some(content_type) => Err(MeilisearchHttpError::InvalidContentType(
+                content_type.as_bytes().as_bstr().to_string(),
+                ACCEPTED_CONTENT_TYPE.clone(),
+            )),
+            None => Err(MeilisearchHttpError::MissingContentType(
+                ACCEPTED_CONTENT_TYPE.clone(),
+            )),
+        },
     }
 }
 
@@ -58,8 +72,8 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
         web::resource("")
             .route(web::get().to(get_all_documents))
-            .route(web::post().guard(guard_json).to(add_documents))
-            .route(web::put().guard(guard_json).to(update_documents))
+            .route(web::post().to(add_documents))
+            .route(web::put().to(update_documents))
             .route(web::delete().to(clear_all_documents)),
     )
     // this route needs to be before the /documents/{document_id} to match properly
@@ -72,27 +86,30 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
 }
 
 pub async fn get_document(
-    data: GuardedData<Public, Data>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, MeiliSearch>,
     path: web::Path<DocumentParam>,
 ) -> Result<HttpResponse, ResponseError> {
     let index = path.index_uid.clone();
     let id = path.document_id.clone();
-    let document = data
-        .retrieve_document(index, id, None as Option<Vec<String>>)
+    let document = meilisearch
+        .document(index, id, None as Option<Vec<String>>)
         .await?;
     debug!("returns: {:?}", document);
     Ok(HttpResponse::Ok().json(document))
 }
 
 pub async fn delete_document(
-    data: GuardedData<Private, Data>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, MeiliSearch>,
     path: web::Path<DocumentParam>,
 ) -> Result<HttpResponse, ResponseError> {
-    let update_status = data
-        .delete_documents(path.index_uid.clone(), vec![path.document_id.clone()])
-        .await?;
-    debug!("returns: {:?}", update_status);
-    Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update_status.id() })))
+    let DocumentParam {
+        document_id,
+        index_uid,
+    } = path.into_inner();
+    let update = Update::DeleteDocuments(vec![document_id]);
+    let task: SummarizedTaskView = meilisearch.register_update(index_uid, update).await?.into();
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Accepted().json(task))
 }
 
 #[derive(Deserialize, Debug)]
@@ -104,8 +121,8 @@ pub struct BrowseQuery {
 }
 
 pub async fn get_all_documents(
-    data: GuardedData<Public, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, MeiliSearch>,
+    path: web::Path<String>,
     params: web::Query<BrowseQuery>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", params);
@@ -120,9 +137,9 @@ pub async fn get_all_documents(
         Some(names)
     });
 
-    let documents = data
-        .retrieve_documents(
-            path.index_uid.clone(),
+    let documents = meilisearch
+        .documents(
+            path.into_inner(),
             params.offset.unwrap_or(DEFAULT_RETRIEVE_DOCUMENTS_OFFSET),
             params.limit.unwrap_or(DEFAULT_RETRIEVE_DOCUMENTS_LIMIT),
             attributes_to_retrieve,
@@ -135,58 +152,121 @@ pub async fn get_all_documents(
 #[derive(Deserialize, Debug)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct UpdateDocumentsQuery {
-    primary_key: Option<String>,
+    pub primary_key: Option<String>,
 }
 
-/// Route used when the payload type is "application/json"
-/// Used to add or replace documents
 pub async fn add_documents(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ADD }>, MeiliSearch>,
+    path: web::Path<String>,
     params: web::Query<UpdateDocumentsQuery>,
     body: Payload,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", params);
-    let update_status = data
-        .add_documents(
-            path.into_inner().index_uid,
-            IndexDocumentsMethod::ReplaceDocuments,
-            UpdateFormat::Json,
-            body,
-            params.primary_key.clone(),
-        )
-        .await?;
+    let params = params.into_inner();
+    let index_uid = path.into_inner();
 
-    debug!("returns: {:?}", update_status);
-    Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update_status.id() })))
+    analytics.add_documents(
+        &params,
+        meilisearch.get_index(index_uid.clone()).await.is_err(),
+        &req,
+    );
+
+    let allow_index_creation = meilisearch.filters().allow_index_creation;
+    let task = document_addition(
+        extract_mime_type(&req)?,
+        meilisearch,
+        index_uid,
+        params.primary_key,
+        body,
+        IndexDocumentsMethod::ReplaceDocuments,
+        allow_index_creation,
+    )
+    .await?;
+
+    Ok(HttpResponse::Accepted().json(task))
 }
 
-/// Route used when the payload type is "application/json"
-/// Used to add or replace documents
 pub async fn update_documents(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ADD }>, MeiliSearch>,
+    path: web::Path<String>,
     params: web::Query<UpdateDocumentsQuery>,
     body: Payload,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", params);
-    let update = data
-        .add_documents(
-            path.into_inner().index_uid,
-            IndexDocumentsMethod::UpdateDocuments,
-            UpdateFormat::Json,
-            body,
-            params.primary_key.clone(),
-        )
-        .await?;
+    let index_uid = path.into_inner();
 
-    debug!("returns: {:?}", update);
-    Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update.id() })))
+    analytics.update_documents(
+        &params,
+        meilisearch.get_index(index_uid.clone()).await.is_err(),
+        &req,
+    );
+
+    let allow_index_creation = meilisearch.filters().allow_index_creation;
+    let task = document_addition(
+        extract_mime_type(&req)?,
+        meilisearch,
+        index_uid,
+        params.into_inner().primary_key,
+        body,
+        IndexDocumentsMethod::UpdateDocuments,
+        allow_index_creation,
+    )
+    .await?;
+
+    Ok(HttpResponse::Accepted().json(task))
+}
+
+async fn document_addition(
+    mime_type: Option<Mime>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ADD }>, MeiliSearch>,
+    index_uid: String,
+    primary_key: Option<String>,
+    body: Payload,
+    method: IndexDocumentsMethod,
+    allow_index_creation: bool,
+) -> Result<SummarizedTaskView, ResponseError> {
+    let format = match mime_type
+        .as_ref()
+        .map(|m| (m.type_().as_str(), m.subtype().as_str()))
+    {
+        Some(("application", "json")) => DocumentAdditionFormat::Json,
+        Some(("application", "x-ndjson")) => DocumentAdditionFormat::Ndjson,
+        Some(("text", "csv")) => DocumentAdditionFormat::Csv,
+        Some((type_, subtype)) => {
+            return Err(MeilisearchHttpError::InvalidContentType(
+                format!("{}/{}", type_, subtype),
+                ACCEPTED_CONTENT_TYPE.clone(),
+            )
+            .into())
+        }
+        None => {
+            return Err(
+                MeilisearchHttpError::MissingContentType(ACCEPTED_CONTENT_TYPE.clone()).into(),
+            )
+        }
+    };
+
+    let update = Update::DocumentAddition {
+        payload: Box::new(payload_to_stream(body)),
+        primary_key,
+        method,
+        format,
+        allow_index_creation,
+    };
+
+    let task = meilisearch.register_update(index_uid, update).await?.into();
+
+    debug!("returns: {:?}", task);
+    Ok(task)
 }
 
 pub async fn delete_documents(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, MeiliSearch>,
+    path: web::Path<String>,
     body: web::Json<Vec<Value>>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", body);
@@ -199,16 +279,26 @@ pub async fn delete_documents(
         })
         .collect();
 
-    let update_status = data.delete_documents(path.index_uid.clone(), ids).await?;
-    debug!("returns: {:?}", update_status);
-    Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update_status.id() })))
+    let update = Update::DeleteDocuments(ids);
+    let task: SummarizedTaskView = meilisearch
+        .register_update(path.into_inner(), update)
+        .await?
+        .into();
+
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Accepted().json(task))
 }
 
 pub async fn clear_all_documents(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, MeiliSearch>,
+    path: web::Path<String>,
 ) -> Result<HttpResponse, ResponseError> {
-    let update_status = data.clear_documents(path.index_uid.clone()).await?;
-    debug!("returns: {:?}", update_status);
-    Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update_status.id() })))
+    let update = Update::ClearDocuments;
+    let task: SummarizedTaskView = meilisearch
+        .register_update(path.into_inner(), update)
+        .await?
+        .into();
+
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Accepted().json(task))
 }

meilisearch-http/src/routes/indexes/mod.rs

@@ -1,17 +1,20 @@
-use actix_web::{web, HttpResponse};
+use actix_web::{web, HttpRequest, HttpResponse};
 use chrono::{DateTime, Utc};
 use log::debug;
+use meilisearch_error::ResponseError;
+use meilisearch_lib::index_controller::Update;
+use meilisearch_lib::MeiliSearch;
 use serde::{Deserialize, Serialize};
+use serde_json::json;
 
-use crate::error::ResponseError;
+use crate::analytics::Analytics;
 use crate::extractors::authentication::{policies::*, GuardedData};
-use crate::routes::IndexParam;
-use crate::Data;
+use crate::task::SummarizedTaskView;
 
 pub mod documents;
 pub mod search;
 pub mod settings;
-pub mod updates;
+pub mod tasks;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -30,13 +33,23 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::resource("/stats").route(web::get().to(get_index_stats)))
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
-            .service(web::scope("/updates").configure(updates::configure))
+            .service(web::scope("/tasks").configure(tasks::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }
 
-pub async fn list_indexes(data: GuardedData<Private, Data>) -> Result<HttpResponse, ResponseError> {
-    let indexes = data.list_indexes().await?;
+pub async fn list_indexes(
+    data: GuardedData<ActionPolicy<{ actions::INDEXES_GET }>, MeiliSearch>,
+) -> Result<HttpResponse, ResponseError> {
+    let filters = data.filters();
+    let mut indexes = data.list_indexes().await?;
+    if let Some(indexes_filter) = filters.indexes.as_ref() {
+        indexes = indexes
+            .into_iter()
+            .filter(|i| indexes_filter.contains(&i.uid))
+            .collect();
+    }
+
     debug!("returns: {:?}", indexes);
     Ok(HttpResponse::Ok().json(indexes))
 }
@@ -49,16 +62,30 @@ pub struct IndexCreateRequest {
 }
 
 pub async fn create_index(
-    data: GuardedData<Private, Data>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::INDEXES_CREATE }>, MeiliSearch>,
     body: web::Json<IndexCreateRequest>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let body = body.into_inner();
-    let meta = data.create_index(body.uid, body.primary_key).await?;
-    Ok(HttpResponse::Created().json(meta))
+    let IndexCreateRequest {
+        primary_key, uid, ..
+    } = body.into_inner();
+
+    analytics.publish(
+        "Index Created".to_string(),
+        json!({ "primary_key": primary_key }),
+        Some(&req),
+    );
+
+    let update = Update::CreateIndex { primary_key };
+    let task: SummarizedTaskView = meilisearch.register_update(uid, update).await?.into();
+
+    Ok(HttpResponse::Accepted().json(task))
 }
 
 #[derive(Debug, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
+#[allow(dead_code)]
 pub struct UpdateIndexRequest {
     uid: Option<String>,
     primary_key: Option<String>,
@@ -75,41 +102,58 @@ pub struct UpdateIndexResponse {
 }
 
 pub async fn get_index(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::INDEXES_GET }>, MeiliSearch>,
+    path: web::Path<String>,
 ) -> Result<HttpResponse, ResponseError> {
-    let meta = data.index(path.index_uid.clone()).await?;
+    let meta = meilisearch.get_index(path.into_inner()).await?;
     debug!("returns: {:?}", meta);
     Ok(HttpResponse::Ok().json(meta))
 }
 
 pub async fn update_index(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::INDEXES_UPDATE }>, MeiliSearch>,
+    path: web::Path<String>,
     body: web::Json<UpdateIndexRequest>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", body);
     let body = body.into_inner();
-    let meta = data
-        .update_index(path.into_inner().index_uid, body.primary_key, body.uid)
-        .await?;
-    debug!("returns: {:?}", meta);
-    Ok(HttpResponse::Ok().json(meta))
+    analytics.publish(
+        "Index Updated".to_string(),
+        json!({ "primary_key": body.primary_key}),
+        Some(&req),
+    );
+
+    let update = Update::UpdateIndex {
+        primary_key: body.primary_key,
+    };
+
+    let task: SummarizedTaskView = meilisearch
+        .register_update(path.into_inner(), update)
+        .await?
+        .into();
+
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Accepted().json(task))
 }
 
 pub async fn delete_index(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::INDEXES_DELETE }>, MeiliSearch>,
+    path: web::Path<String>,
 ) -> Result<HttpResponse, ResponseError> {
-    data.delete_index(path.index_uid.clone()).await?;
-    Ok(HttpResponse::NoContent().finish())
+    let uid = path.into_inner();
+    let update = Update::DeleteIndex;
+    let task: SummarizedTaskView = meilisearch.register_update(uid, update).await?.into();
+
+    Ok(HttpResponse::Accepted().json(task))
 }
 
 pub async fn get_index_stats(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::STATS_GET }>, MeiliSearch>,
+    path: web::Path<String>,
 ) -> Result<HttpResponse, ResponseError> {
-    let response = data.get_index_stats(path.index_uid.clone()).await?;
+    let response = meilisearch.get_index_stats(path.into_inner()).await?;
 
     debug!("returns: {:?}", response);
     Ok(HttpResponse::Ok().json(response))

meilisearch-http/src/routes/indexes/search.rs

@@ -1,13 +1,13 @@
-use actix_web::{web, HttpResponse};
+use actix_web::{web, HttpRequest, HttpResponse};
 use log::debug;
+use meilisearch_error::ResponseError;
+use meilisearch_lib::index::{default_crop_length, SearchQuery, DEFAULT_SEARCH_LIMIT};
+use meilisearch_lib::MeiliSearch;
 use serde::Deserialize;
 use serde_json::Value;
 
-use crate::error::ResponseError;
+use crate::analytics::{Analytics, SearchAggregator};
 use crate::extractors::authentication::{policies::*, GuardedData};
-use crate::index::{default_crop_length, SearchQuery, DEFAULT_SEARCH_LIMIT};
-use crate::routes::IndexParam;
-use crate::Data;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -61,9 +61,7 @@ impl From<SearchQueryGet> for SearchQuery {
             None => None,
         };
 
-        let sort = other
-            .sort
-            .map(|attrs| attrs.split(',').map(String::from).collect());
+        let sort = other.sort.map(|attr| fix_sort_query_parameters(&attr));
 
         Self {
             q: other.q,
@@ -81,14 +79,51 @@ impl From<SearchQueryGet> for SearchQuery {
     }
 }
 
+// TODO: TAMO: split on :asc, and :desc, instead of doing some weird things
+
+/// Transform the sort query parameter into something that matches the post expected format.
+fn fix_sort_query_parameters(sort_query: &str) -> Vec<String> {
+    let mut sort_parameters = Vec::new();
+    let mut merge = false;
+    for current_sort in sort_query.trim_matches('"').split(',').map(|s| s.trim()) {
+        if current_sort.starts_with("_geoPoint(") {
+            sort_parameters.push(current_sort.to_string());
+            merge = true;
+        } else if merge && !sort_parameters.is_empty() {
+            sort_parameters
+                .last_mut()
+                .unwrap()
+                .push_str(&format!(",{}", current_sort));
+            if current_sort.ends_with("):desc") || current_sort.ends_with("):asc") {
+                merge = false;
+            }
+        } else {
+            sort_parameters.push(current_sort.to_string());
+            merge = false;
+        }
+    }
+    sort_parameters
+}
+
 pub async fn search_with_url_query(
-    data: GuardedData<Public, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::SEARCH }>, MeiliSearch>,
+    path: web::Path<String>,
     params: web::Query<SearchQueryGet>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", params);
-    let query = params.into_inner().into();
-    let search_result = data.search(path.into_inner().index_uid, query).await?;
+    let query: SearchQuery = params.into_inner().into();
+
+    let mut aggregate = SearchAggregator::from_query(&query, &req);
+
+    let search_result = meilisearch.search(path.into_inner(), query).await;
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.get_search(aggregate);
+
+    let search_result = search_result?;
 
     // Tests that the nb_hits is always set to false
     #[cfg(test)]
@@ -99,14 +134,24 @@ pub async fn search_with_url_query(
 }
 
 pub async fn search_with_post(
-    data: GuardedData<Public, Data>,
-    path: web::Path<IndexParam>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::SEARCH }>, MeiliSearch>,
+    path: web::Path<String>,
     params: web::Json<SearchQuery>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!("search called with params: {:?}", params);
-    let search_result = data
-        .search(path.into_inner().index_uid, params.into_inner())
-        .await?;
+    let query = params.into_inner();
+    debug!("search called with params: {:?}", query);
+
+    let mut aggregate = SearchAggregator::from_query(&query, &req);
+
+    let search_result = meilisearch.search(path.into_inner(), query).await;
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.post_search(aggregate);
+
+    let search_result = search_result?;
 
     // Tests that the nb_hits is always set to false
     #[cfg(test)]
@@ -115,3 +160,42 @@ pub async fn search_with_post(
     debug!("returns: {:?}", search_result);
     Ok(HttpResponse::Ok().json(search_result))
 }
+
+#[cfg(test)]
+mod test {
+    use super::*;
+
+    #[test]
+    fn test_fix_sort_query_parameters() {
+        let sort = fix_sort_query_parameters("_geoPoint(12, 13):asc");
+        assert_eq!(sort, vec!["_geoPoint(12,13):asc".to_string()]);
+        let sort = fix_sort_query_parameters("doggo:asc,_geoPoint(12.45,13.56):desc");
+        assert_eq!(
+            sort,
+            vec![
+                "doggo:asc".to_string(),
+                "_geoPoint(12.45,13.56):desc".to_string(),
+            ]
+        );
+        let sort = fix_sort_query_parameters(
+            "doggo:asc , _geoPoint(12.45, 13.56, 2590352):desc , catto:desc",
+        );
+        assert_eq!(
+            sort,
+            vec![
+                "doggo:asc".to_string(),
+                "_geoPoint(12.45,13.56,2590352):desc".to_string(),
+                "catto:desc".to_string(),
+            ]
+        );
+        let sort = fix_sort_query_parameters("doggo:asc , _geoPoint(1, 2), catto:desc");
+        // This is ugly but eh, I don't want to write a full parser just for this unused route
+        assert_eq!(
+            sort,
+            vec![
+                "doggo:asc".to_string(),
+                "_geoPoint(1,2),catto:desc".to_string(),
+            ]
+        );
+    }
+}

meilisearch-http/src/routes/indexes/settings.rs

@@ -1,65 +1,98 @@
-use actix_web::{web, HttpResponse};
 use log::debug;
 
+use actix_web::{web, HttpRequest, HttpResponse};
+use meilisearch_error::ResponseError;
+use meilisearch_lib::index::{Settings, Unchecked};
+use meilisearch_lib::index_controller::Update;
+use meilisearch_lib::MeiliSearch;
+use serde_json::json;
+
+use crate::analytics::Analytics;
 use crate::extractors::authentication::{policies::*, GuardedData};
-use crate::index::Settings;
-use crate::Data;
-use crate::{error::ResponseError, index::Unchecked};
+use crate::task::SummarizedTaskView;
 
 #[macro_export]
 macro_rules! make_setting_route {
-    ($route:literal, $type:ty, $attr:ident, $camelcase_attr:literal) => {
+    ($route:literal, $type:ty, $attr:ident, $camelcase_attr:literal, $analytics_var:ident, $analytics:expr) => {
         pub mod $attr {
+            use actix_web::{web, HttpRequest, HttpResponse, Resource};
             use log::debug;
-            use actix_web::{web, HttpResponse, Resource};
 
-            use milli::update::Setting;
+            use meilisearch_lib::milli::update::Setting;
+            use meilisearch_lib::{index::Settings, index_controller::Update, MeiliSearch};
 
-            use crate::data;
-            use crate::error::ResponseError;
-            use crate::index::Settings;
-            use crate::extractors::authentication::{GuardedData, policies::*};
+            use crate::analytics::Analytics;
+            use crate::extractors::authentication::{policies::*, GuardedData};
+            use crate::task::SummarizedTaskView;
+            use meilisearch_error::ResponseError;
 
             pub async fn delete(
-                data: GuardedData<Private, data::Data>,
+                meilisearch: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, MeiliSearch>,
                 index_uid: web::Path<String>,
             ) -> Result<HttpResponse, ResponseError> {
-                use crate::index::Settings;
                 let settings = Settings {
                     $attr: Setting::Reset,
                     ..Default::default()
                 };
-                let update_status = data.update_settings(index_uid.into_inner(), settings, false).await?;
-                debug!("returns: {:?}", update_status);
-                Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update_status.id() })))
+
+                let allow_index_creation = meilisearch.filters().allow_index_creation;
+                let update = Update::Settings {
+                    settings,
+                    is_deletion: true,
+                    allow_index_creation,
+                };
+                let task: SummarizedTaskView = meilisearch
+                    .register_update(index_uid.into_inner(), update)
+                    .await?
+                    .into();
+
+                debug!("returns: {:?}", task);
+                Ok(HttpResponse::Accepted().json(task))
             }
 
             pub async fn update(
-                data: GuardedData<Private, data::Data>,
+                meilisearch: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, MeiliSearch>,
                 index_uid: actix_web::web::Path<String>,
                 body: actix_web::web::Json<Option<$type>>,
+                req: HttpRequest,
+                $analytics_var: web::Data<dyn Analytics>,
             ) -> std::result::Result<HttpResponse, ResponseError> {
+                let body = body.into_inner();
+
+                $analytics(&body, &req);
+
                 let settings = Settings {
-                    $attr: match body.into_inner() {
+                    $attr: match body {
                         Some(inner_body) => Setting::Set(inner_body),
-                        None => Setting::Reset
+                        None => Setting::Reset,
                     },
                     ..Default::default()
                 };
 
-                let update_status = data.update_settings(index_uid.into_inner(), settings, true).await?;
-                debug!("returns: {:?}", update_status);
-                Ok(HttpResponse::Accepted().json(serde_json::json!({ "updateId": update_status.id() })))
+                let allow_index_creation = meilisearch.filters().allow_index_creation;
+                let update = Update::Settings {
+                    settings,
+                    is_deletion: false,
+                    allow_index_creation,
+                };
+                let task: SummarizedTaskView = meilisearch
+                    .register_update(index_uid.into_inner(), update)
+                    .await?
+                    .into();
+
+                debug!("returns: {:?}", task);
+                Ok(HttpResponse::Accepted().json(task))
             }
 
             pub async fn get(
-                data: GuardedData<Private, data::Data>,
+                meilisearch: GuardedData<ActionPolicy<{ actions::SETTINGS_GET }>, MeiliSearch>,
                 index_uid: actix_web::web::Path<String>,
             ) -> std::result::Result<HttpResponse, ResponseError> {
-                let settings = data.settings(index_uid.into_inner()).await?;
+                let settings = meilisearch.settings(index_uid.into_inner()).await?;
                 debug!("returns: {:?}", settings);
                 let mut json = serde_json::json!(&settings);
                 let val = json[$camelcase_attr].take();
+
                 Ok(HttpResponse::Ok().json(val))
             }
 
@@ -71,20 +104,53 @@ macro_rules! make_setting_route {
             }
         }
     };
+    ($route:literal, $type:ty, $attr:ident, $camelcase_attr:literal) => {
+        make_setting_route!($route, $type, $attr, $camelcase_attr, _analytics, |_, _| {});
+    };
 }
 
 make_setting_route!(
     "/filterable-attributes",
     std::collections::BTreeSet<String>,
     filterable_attributes,
-    "filterableAttributes"
+    "filterableAttributes",
+    analytics,
+    |setting: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
+        use serde_json::json;
+
+        analytics.publish(
+            "FilterableAttributes Updated".to_string(),
+            json!({
+                "filterable_attributes": {
+                    "total": setting.as_ref().map(|filter| filter.len()).unwrap_or(0),
+                    "has_geo": setting.as_ref().map(|filter| filter.contains("_geo")).unwrap_or(false),
+                }
+            }),
+            Some(req),
+        );
+    }
 );
 
 make_setting_route!(
     "/sortable-attributes",
     std::collections::BTreeSet<String>,
     sortable_attributes,
-    "sortableAttributes"
+    "sortableAttributes",
+    analytics,
+    |setting: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
+        use serde_json::json;
+
+        analytics.publish(
+            "SortableAttributes Updated".to_string(),
+            json!({
+                "sortable_attributes": {
+                    "total": setting.as_ref().map(|sort| sort.len()).unwrap_or(0),
+                    "has_geo": setting.as_ref().map(|sort| sort.contains("_geo")).unwrap_or(false),
+                },
+            }),
+            Some(req),
+        );
+    }
 );
 
 make_setting_route!(
@@ -98,7 +164,21 @@ make_setting_route!(
     "/searchable-attributes",
     Vec<String>,
     searchable_attributes,
-    "searchableAttributes"
+    "searchableAttributes",
+    analytics,
+    |setting: &Option<Vec<String>>, req: &HttpRequest| {
+        use serde_json::json;
+
+        analytics.publish(
+            "SearchableAttributes Updated".to_string(),
+            json!({
+                "searchable_attributes": {
+                    "total": setting.as_ref().map(|searchable| searchable.len()).unwrap_or(0),
+                },
+            }),
+            Some(req),
+        );
+    }
 );
 
 make_setting_route!(
@@ -122,7 +202,26 @@ make_setting_route!(
     "distinctAttribute"
 );
 
-make_setting_route!("/ranking-rules", Vec<String>, ranking_rules, "rankingRules");
+make_setting_route!(
+    "/ranking-rules",
+    Vec<String>,
+    ranking_rules,
+    "rankingRules",
+    analytics,
+    |setting: &Option<Vec<String>>, req: &HttpRequest| {
+        use serde_json::json;
+
+        analytics.publish(
+            "RankingRules Updated".to_string(),
+            json!({
+                "ranking_rules": {
+                    "sort_position": setting.as_ref().map(|sort| sort.iter().position(|s| s == "sort")),
+                }
+            }),
+            Some(req),
+        );
+    }
+);
 
 macro_rules! generate_configure {
     ($($mod:ident),*) => {
@@ -149,21 +248,52 @@ generate_configure!(
 );
 
 pub async fn update_all(
-    data: GuardedData<Private, Data>,
+    meilisearch: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, MeiliSearch>,
     index_uid: web::Path<String>,
     body: web::Json<Settings<Unchecked>>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let settings = body.into_inner().check();
-    let update_result = data
-        .update_settings(index_uid.into_inner(), settings, true)
-        .await?;
-    let json = serde_json::json!({ "updateId": update_result.id() });
-    debug!("returns: {:?}", json);
-    Ok(HttpResponse::Accepted().json(json))
+    let settings = body.into_inner();
+
+    analytics.publish(
+        "Settings Updated".to_string(),
+        json!({
+           "ranking_rules": {
+                "sort_position": settings.ranking_rules.as_ref().set().map(|sort| sort.iter().position(|s| s == "sort")),
+            },
+            "searchable_attributes": {
+                "total": settings.searchable_attributes.as_ref().set().map(|searchable| searchable.len()).unwrap_or(0),
+            },
+           "sortable_attributes": {
+                "total": settings.sortable_attributes.as_ref().set().map(|sort| sort.len()).unwrap_or(0),
+                "has_geo": settings.sortable_attributes.as_ref().set().map(|sort| sort.iter().any(|s| s == "_geo")).unwrap_or(false),
+            },
+           "filterable_attributes": {
+                "total": settings.filterable_attributes.as_ref().set().map(|filter| filter.len()).unwrap_or(0),
+                "has_geo": settings.filterable_attributes.as_ref().set().map(|filter| filter.iter().any(|s| s == "_geo")).unwrap_or(false),
+            },
+        }),
+        Some(&req),
+    );
+
+    let allow_index_creation = meilisearch.filters().allow_index_creation;
+    let update = Update::Settings {
+        settings,
+        is_deletion: false,
+        allow_index_creation,
+    };
+    let task: SummarizedTaskView = meilisearch
+        .register_update(index_uid.into_inner(), update)
+        .await?
+        .into();
+
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Accepted().json(task))
 }
 
 pub async fn get_all(
-    data: GuardedData<Private, Data>,
+    data: GuardedData<ActionPolicy<{ actions::SETTINGS_GET }>, MeiliSearch>,
     index_uid: web::Path<String>,
 ) -> Result<HttpResponse, ResponseError> {
     let settings = data.settings(index_uid.into_inner()).await?;
@@ -172,14 +302,22 @@ pub async fn get_all(
 }
 
 pub async fn delete_all(
-    data: GuardedData<Private, Data>,
+    data: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, MeiliSearch>,
     index_uid: web::Path<String>,
 ) -> Result<HttpResponse, ResponseError> {
-    let settings = Settings::cleared();
-    let update_result = data
-        .update_settings(index_uid.into_inner(), settings, false)
-        .await?;
-    let json = serde_json::json!({ "updateId": update_result.id() });
-    debug!("returns: {:?}", json);
-    Ok(HttpResponse::Accepted().json(json))
+    let settings = Settings::cleared().into_unchecked();
+
+    let allow_index_creation = data.filters().allow_index_creation;
+    let update = Update::Settings {
+        settings,
+        is_deletion: true,
+        allow_index_creation,
+    };
+    let task: SummarizedTaskView = data
+        .register_update(index_uid.into_inner(), update)
+        .await?
+        .into();
+
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Accepted().json(task))
 }

meilisearch-http/src/routes/indexes/tasks.rs

@@ -0,0 +1,76 @@
+use actix_web::{web, HttpRequest, HttpResponse};
+use chrono::{DateTime, Utc};
+use log::debug;
+use meilisearch_error::ResponseError;
+use meilisearch_lib::MeiliSearch;
+use serde::{Deserialize, Serialize};
+use serde_json::json;
+
+use crate::analytics::Analytics;
+use crate::extractors::authentication::{policies::*, GuardedData};
+use crate::task::{TaskListView, TaskView};
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(web::resource("").route(web::get().to(get_all_tasks_status)))
+        .service(web::resource("{task_id}").route(web::get().to(get_task_status)));
+}
+
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UpdateIndexResponse {
+    name: String,
+    uid: String,
+    created_at: DateTime<Utc>,
+    updated_at: DateTime<Utc>,
+    primary_key: Option<String>,
+}
+
+#[derive(Deserialize)]
+pub struct UpdateParam {
+    index_uid: String,
+    task_id: u64,
+}
+
+pub async fn get_task_status(
+    meilisearch: GuardedData<ActionPolicy<{ actions::TASKS_GET }>, MeiliSearch>,
+    index_uid: web::Path<UpdateParam>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    analytics.publish(
+        "Index Tasks Seen".to_string(),
+        json!({ "per_task_uid": true }),
+        Some(&req),
+    );
+
+    let UpdateParam { index_uid, task_id } = index_uid.into_inner();
+
+    let task: TaskView = meilisearch.get_index_task(index_uid, task_id).await?.into();
+
+    debug!("returns: {:?}", task);
+    Ok(HttpResponse::Ok().json(task))
+}
+
+pub async fn get_all_tasks_status(
+    meilisearch: GuardedData<ActionPolicy<{ actions::TASKS_GET }>, MeiliSearch>,
+    index_uid: web::Path<String>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    analytics.publish(
+        "Index Tasks Seen".to_string(),
+        json!({ "per_task_uid": false }),
+        Some(&req),
+    );
+
+    let tasks: TaskListView = meilisearch
+        .list_index_task(index_uid.into_inner(), None, None)
+        .await?
+        .into_iter()
+        .map(TaskView::from)
+        .collect::<Vec<_>>()
+        .into();
+
+    debug!("returns: {:?}", tasks);
+    Ok(HttpResponse::Ok().json(tasks))
+}

meilisearch-http/src/routes/indexes/updates.rs

@@ -1,64 +0,0 @@
-use actix_web::{web, HttpResponse};
-use chrono::{DateTime, Utc};
-use log::debug;
-use serde::{Deserialize, Serialize};
-
-use crate::error::ResponseError;
-use crate::extractors::authentication::{policies::*, GuardedData};
-use crate::routes::{IndexParam, UpdateStatusResponse};
-use crate::Data;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::get().to(get_all_updates_status)))
-        .service(web::resource("{update_id}").route(web::get().to(get_update_status)));
-}
-
-#[derive(Debug, Deserialize)]
-#[serde(rename_all = "camelCase", deny_unknown_fields)]
-struct UpdateIndexRequest {
-    uid: Option<String>,
-    primary_key: Option<String>,
-}
-
-#[derive(Debug, Serialize)]
-#[serde(rename_all = "camelCase")]
-pub struct UpdateIndexResponse {
-    name: String,
-    uid: String,
-    created_at: DateTime<Utc>,
-    updated_at: DateTime<Utc>,
-    primary_key: Option<String>,
-}
-
-#[derive(Deserialize)]
-pub struct UpdateParam {
-    index_uid: String,
-    update_id: u64,
-}
-
-pub async fn get_update_status(
-    data: GuardedData<Private, Data>,
-    path: web::Path<UpdateParam>,
-) -> Result<HttpResponse, ResponseError> {
-    let params = path.into_inner();
-    let meta = data
-        .get_update_status(params.index_uid, params.update_id)
-        .await?;
-    let meta = UpdateStatusResponse::from(meta);
-    debug!("returns: {:?}", meta);
-    Ok(HttpResponse::Ok().json(meta))
-}
-
-pub async fn get_all_updates_status(
-    data: GuardedData<Private, Data>,
-    path: web::Path<IndexParam>,
-) -> Result<HttpResponse, ResponseError> {
-    let metas = data.get_updates_status(path.into_inner().index_uid).await?;
-    let metas = metas
-        .into_iter()
-        .map(UpdateStatusResponse::from)
-        .collect::<Vec<_>>();
-
-    debug!("returns: {:?}", metas);
-    Ok(HttpResponse::Ok().json(metas))
-}

meilisearch-http/src/routes/mod.rs

@@ -1,23 +1,24 @@
-use std::time::Duration;
-
 use actix_web::{web, HttpResponse};
 use chrono::{DateTime, Utc};
 use log::debug;
 use serde::{Deserialize, Serialize};
 
-use crate::error::ResponseError;
-use crate::extractors::authentication::{policies::*, GuardedData};
-use crate::index::{Settings, Unchecked};
-use crate::index_controller::{UpdateMeta, UpdateResult, UpdateStatus};
-use crate::Data;
+use meilisearch_error::ResponseError;
+use meilisearch_lib::index::{Settings, Unchecked};
+use meilisearch_lib::MeiliSearch;
 
+use crate::extractors::authentication::{policies::*, GuardedData};
+
+mod api_key;
 mod dump;
-mod indexes;
+pub mod indexes;
+mod tasks;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("/health").route(web::get().to(get_health)))
+    cfg.service(web::scope("/tasks").configure(tasks::configure))
+        .service(web::resource("/health").route(web::get().to(get_health)))
+        .service(web::scope("/keys").configure(api_key::configure))
         .service(web::scope("/dumps").configure(dump::configure))
-        .service(web::resource("/keys").route(web::get().to(list_keys)))
         .service(web::resource("/stats").route(web::get().to(get_stats)))
         .service(web::resource("/version").route(web::get().to(get_version)))
         .service(web::scope("/indexes").configure(indexes::configure));
@@ -46,38 +47,6 @@ pub enum UpdateType {
     },
 }
 
-impl From<&UpdateStatus> for UpdateType {
-    fn from(other: &UpdateStatus) -> Self {
-        use milli::update::IndexDocumentsMethod::*;
-        match other.meta() {
-            UpdateMeta::DocumentsAddition { method, .. } => {
-                let number = match other {
-                    UpdateStatus::Processed(processed) => match processed.success {
-                        UpdateResult::DocumentsAddition(ref addition) => {
-                            Some(addition.nb_documents)
-                        }
-                        _ => None,
-                    },
-                    _ => None,
-                };
-
-                match method {
-                    ReplaceDocuments => UpdateType::DocumentsAddition { number },
-                    UpdateDocuments => UpdateType::DocumentsPartial { number },
-                    _ => unreachable!(),
-                }
-            }
-            UpdateMeta::ClearDocuments => UpdateType::ClearAll,
-            UpdateMeta::DeleteDocuments { ids } => UpdateType::DocumentsDeletion {
-                number: Some(ids.len()),
-            },
-            UpdateMeta::Settings(settings) => UpdateType::Settings {
-                settings: settings.clone(),
-            },
-        }
-    }
-}
-
 #[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(rename_all = "camelCase")]
 pub struct ProcessedUpdateResult {
@@ -95,8 +64,7 @@ pub struct FailedUpdateResult {
     pub update_id: u64,
     #[serde(rename = "type")]
     pub update_type: UpdateType,
-    #[serde(flatten)]
-    pub response: ResponseError,
+    pub error: ResponseError,
     pub duration: f64, // in seconds
     pub enqueued_at: DateTime<Utc>,
     pub processed_at: DateTime<Utc>,
@@ -134,79 +102,6 @@ pub enum UpdateStatusResponse {
     },
 }
 
-impl From<UpdateStatus> for UpdateStatusResponse {
-    fn from(other: UpdateStatus) -> Self {
-        let update_type = UpdateType::from(&other);
-
-        match other {
-            UpdateStatus::Processing(processing) => {
-                let content = EnqueuedUpdateResult {
-                    update_id: processing.id(),
-                    update_type,
-                    enqueued_at: processing.from.enqueued_at,
-                    started_processing_at: Some(processing.started_processing_at),
-                };
-                UpdateStatusResponse::Processing { content }
-            }
-            UpdateStatus::Enqueued(enqueued) => {
-                let content = EnqueuedUpdateResult {
-                    update_id: enqueued.id(),
-                    update_type,
-                    enqueued_at: enqueued.enqueued_at,
-                    started_processing_at: None,
-                };
-                UpdateStatusResponse::Enqueued { content }
-            }
-            UpdateStatus::Processed(processed) => {
-                let duration = processed
-                    .processed_at
-                    .signed_duration_since(processed.from.started_processing_at)
-                    .num_milliseconds();
-
-                // necessary since chrono::duration don't expose a f64 secs method.
-                let duration = Duration::from_millis(duration as u64).as_secs_f64();
-
-                let content = ProcessedUpdateResult {
-                    update_id: processed.id(),
-                    update_type,
-                    duration,
-                    enqueued_at: processed.from.from.enqueued_at,
-                    processed_at: processed.processed_at,
-                };
-                UpdateStatusResponse::Processed { content }
-            }
-            UpdateStatus::Aborted(_) => unreachable!(),
-            UpdateStatus::Failed(failed) => {
-                let duration = failed
-                    .failed_at
-                    .signed_duration_since(failed.from.started_processing_at)
-                    .num_milliseconds();
-
-                // necessary since chrono::duration don't expose a f64 secs method.
-                let duration = Duration::from_millis(duration as u64).as_secs_f64();
-
-                let update_id = failed.id();
-                let response = failed.error;
-
-                let content = FailedUpdateResult {
-                    update_id,
-                    update_type,
-                    response,
-                    duration,
-                    enqueued_at: failed.from.from.enqueued_at,
-                    processed_at: failed.failed_at,
-                };
-                UpdateStatusResponse::Failed { content }
-            }
-        }
-    }
-}
-
-#[derive(Deserialize)]
-pub struct IndexParam {
-    index_uid: String,
-}
-
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct IndexUpdateResponse {
@@ -222,15 +117,19 @@ impl IndexUpdateResponse {
 /// Always return a 200 with:
 /// ```json
 /// {
-///     "status": "Meilisearch is running"
+///     "status": "MeiliSearch is running"
 /// }
 /// ```
 pub async fn running() -> HttpResponse {
     HttpResponse::Ok().json(serde_json::json!({ "status": "MeiliSearch is running" }))
 }
 
-async fn get_stats(data: GuardedData<Private, Data>) -> Result<HttpResponse, ResponseError> {
-    let response = data.get_all_stats().await?;
+async fn get_stats(
+    meilisearch: GuardedData<ActionPolicy<{ actions::STATS_GET }>, MeiliSearch>,
+) -> Result<HttpResponse, ResponseError> {
+    let filters = meilisearch.filters();
+
+    let response = meilisearch.get_all_stats(&filters.indexes).await?;
 
     debug!("returns: {:?}", response);
     Ok(HttpResponse::Ok().json(response))
@@ -244,7 +143,9 @@ struct VersionResponse {
     pkg_version: String,
 }
 
-async fn get_version(_data: GuardedData<Private, Data>) -> HttpResponse {
+async fn get_version(
+    _meilisearch: GuardedData<ActionPolicy<{ actions::VERSION }>, MeiliSearch>,
+) -> HttpResponse {
     let commit_sha = option_env!("VERGEN_GIT_SHA").unwrap_or("unknown");
     let commit_date = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP").unwrap_or("unknown");
 
@@ -261,108 +162,6 @@ struct KeysResponse {
     public: Option<String>,
 }
 
-pub async fn list_keys(data: GuardedData<Admin, Data>) -> HttpResponse {
-    let api_keys = data.api_keys.clone();
-    HttpResponse::Ok().json(&KeysResponse {
-        private: api_keys.private,
-        public: api_keys.public,
-    })
-}
-
 pub async fn get_health() -> Result<HttpResponse, ResponseError> {
     Ok(HttpResponse::Ok().json(serde_json::json!({ "status": "available" })))
 }
-
-#[cfg(test)]
-mod test {
-    use super::*;
-    use crate::data::Data;
-    use crate::extractors::authentication::GuardedData;
-
-    /// A type implemented for a route that uses a authentication policy `Policy`.
-    ///
-    /// This trait is used for regression testing of route authenticaton policies.
-    trait Is<Policy, T> {}
-
-    macro_rules! impl_is_policy {
-        ($($param:ident)*) => {
-            impl<Policy, Func, $($param,)* Res> Is<Policy, (($($param,)*), Res)> for Func
-                where Func: Fn(GuardedData<Policy, Data>, $($param,)*) -> Res {}
-
-        };
-    }
-
-    impl_is_policy! {}
-    impl_is_policy! {A}
-    impl_is_policy! {A B}
-    impl_is_policy! {A B C}
-    impl_is_policy! {A B C D}
-
-    /// Emits a compile error if a route doesn't have the correct authentication policy.
-    ///
-    /// This works by trying to cast the route function into a Is<Policy, _> type, where Policy it
-    /// the authentication policy defined for the route.
-    macro_rules! test_auth_routes {
-        ($($policy:ident => { $($route:expr,)*})*) => {
-            #[test]
-            fn test_auth() {
-                $($(let _: &dyn Is<$policy, _> = &$route;)*)*
-            }
-        };
-    }
-
-    test_auth_routes! {
-        Public => {
-            indexes::search::search_with_url_query,
-            indexes::search::search_with_post,
-
-            indexes::documents::get_document,
-            indexes::documents::get_all_documents,
-        }
-        Private => {
-            get_stats,
-            get_version,
-
-            indexes::create_index,
-            indexes::list_indexes,
-            indexes::get_index_stats,
-            indexes::delete_index,
-            indexes::update_index,
-            indexes::get_index,
-
-            dump::create_dump,
-
-            indexes::settings::filterable_attributes::get,
-            indexes::settings::displayed_attributes::get,
-            indexes::settings::searchable_attributes::get,
-            indexes::settings::stop_words::get,
-            indexes::settings::synonyms::get,
-            indexes::settings::distinct_attribute::get,
-            indexes::settings::filterable_attributes::update,
-            indexes::settings::displayed_attributes::update,
-            indexes::settings::searchable_attributes::update,
-            indexes::settings::stop_words::update,
-            indexes::settings::synonyms::update,
-            indexes::settings::distinct_attribute::update,
-            indexes::settings::filterable_attributes::delete,
-            indexes::settings::displayed_attributes::delete,
-            indexes::settings::searchable_attributes::delete,
-            indexes::settings::stop_words::delete,
-            indexes::settings::synonyms::delete,
-            indexes::settings::distinct_attribute::delete,
-            indexes::settings::delete_all,
-            indexes::settings::get_all,
-            indexes::settings::update_all,
-
-            indexes::documents::clear_all_documents,
-            indexes::documents::delete_documents,
-            indexes::documents::update_documents,
-            indexes::documents::add_documents,
-            indexes::documents::delete_document,
-
-            indexes::updates::get_all_updates_status,
-            indexes::updates::get_update_status,
-        }
-        Admin => { list_keys, }
-    }
-}

meilisearch-http/src/routes/tasks.rs

@@ -0,0 +1,73 @@
+use actix_web::{web, HttpRequest, HttpResponse};
+use meilisearch_error::ResponseError;
+use meilisearch_lib::tasks::task::TaskId;
+use meilisearch_lib::tasks::TaskFilter;
+use meilisearch_lib::MeiliSearch;
+use serde_json::json;
+
+use crate::analytics::Analytics;
+use crate::extractors::authentication::{policies::*, GuardedData};
+use crate::task::{TaskListView, TaskView};
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(web::resource("").route(web::get().to(get_tasks)))
+        .service(web::resource("/{task_id}").route(web::get().to(get_task)));
+}
+
+async fn get_tasks(
+    meilisearch: GuardedData<ActionPolicy<{ actions::TASKS_GET }>, MeiliSearch>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    analytics.publish(
+        "Tasks Seen".to_string(),
+        json!({ "per_task_uid": false }),
+        Some(&req),
+    );
+
+    let filters = meilisearch.filters().indexes.as_ref().map(|indexes| {
+        let mut filters = TaskFilter::default();
+        for index in indexes {
+            filters.filter_index(index.to_string());
+        }
+        filters
+    });
+
+    let tasks: TaskListView = meilisearch
+        .list_tasks(filters, None, None)
+        .await?
+        .into_iter()
+        .map(TaskView::from)
+        .collect::<Vec<_>>()
+        .into();
+
+    Ok(HttpResponse::Ok().json(tasks))
+}
+
+async fn get_task(
+    meilisearch: GuardedData<ActionPolicy<{ actions::TASKS_GET }>, MeiliSearch>,
+    task_id: web::Path<TaskId>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    analytics.publish(
+        "Tasks Seen".to_string(),
+        json!({ "per_task_uid": true }),
+        Some(&req),
+    );
+
+    let filters = meilisearch.filters().indexes.as_ref().map(|indexes| {
+        let mut filters = TaskFilter::default();
+        for index in indexes {
+            filters.filter_index(index.to_string());
+        }
+        filters
+    });
+
+    let task: TaskView = meilisearch
+        .get_task(task_id.into_inner(), filters)
+        .await?
+        .into();
+
+    Ok(HttpResponse::Ok().json(task))
+}

meilisearch-http/src/task.rs

@@ -0,0 +1,313 @@
+use chrono::{DateTime, Duration, Utc};
+use meilisearch_error::ResponseError;
+use meilisearch_lib::index::{Settings, Unchecked};
+use meilisearch_lib::milli::update::IndexDocumentsMethod;
+use meilisearch_lib::tasks::task::{
+    DocumentDeletion, Task, TaskContent, TaskEvent, TaskId, TaskResult,
+};
+use serde::{Serialize, Serializer};
+
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+enum TaskType {
+    IndexCreation,
+    IndexUpdate,
+    IndexDeletion,
+    DocumentAddition,
+    DocumentPartial,
+    DocumentDeletion,
+    SettingsUpdate,
+    ClearAll,
+}
+
+impl From<TaskContent> for TaskType {
+    fn from(other: TaskContent) -> Self {
+        match other {
+            TaskContent::DocumentAddition {
+                merge_strategy: IndexDocumentsMethod::ReplaceDocuments,
+                ..
+            } => TaskType::DocumentAddition,
+            TaskContent::DocumentAddition {
+                merge_strategy: IndexDocumentsMethod::UpdateDocuments,
+                ..
+            } => TaskType::DocumentPartial,
+            TaskContent::DocumentDeletion(DocumentDeletion::Clear) => TaskType::ClearAll,
+            TaskContent::DocumentDeletion(DocumentDeletion::Ids(_)) => TaskType::DocumentDeletion,
+            TaskContent::SettingsUpdate { .. } => TaskType::SettingsUpdate,
+            TaskContent::IndexDeletion => TaskType::IndexDeletion,
+            TaskContent::IndexCreation { .. } => TaskType::IndexCreation,
+            TaskContent::IndexUpdate { .. } => TaskType::IndexUpdate,
+            _ => unreachable!("unexpected task type"),
+        }
+    }
+}
+
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+enum TaskStatus {
+    Enqueued,
+    Processing,
+    Succeeded,
+    Failed,
+}
+
+#[derive(Debug, Serialize)]
+#[serde(untagged)]
+#[allow(clippy::large_enum_variant)]
+enum TaskDetails {
+    #[serde(rename_all = "camelCase")]
+    DocumentAddition {
+        received_documents: usize,
+        indexed_documents: Option<u64>,
+    },
+    #[serde(rename_all = "camelCase")]
+    Settings {
+        #[serde(flatten)]
+        settings: Settings<Unchecked>,
+    },
+    #[serde(rename_all = "camelCase")]
+    IndexInfo { primary_key: Option<String> },
+    #[serde(rename_all = "camelCase")]
+    DocumentDeletion {
+        received_document_ids: usize,
+        deleted_documents: Option<u64>,
+    },
+    #[serde(rename_all = "camelCase")]
+    ClearAll { deleted_documents: Option<u64> },
+}
+
+fn serialize_duration<S: Serializer>(
+    duration: &Option<Duration>,
+    serializer: S,
+) -> Result<S::Ok, S::Error> {
+    match duration {
+        Some(duration) => {
+            let duration_str = duration.to_string();
+            serializer.serialize_str(&duration_str)
+        }
+        None => serializer.serialize_none(),
+    }
+}
+
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TaskView {
+    uid: TaskId,
+    index_uid: String,
+    status: TaskStatus,
+    #[serde(rename = "type")]
+    task_type: TaskType,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    details: Option<TaskDetails>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    error: Option<ResponseError>,
+    #[serde(serialize_with = "serialize_duration")]
+    duration: Option<Duration>,
+    enqueued_at: DateTime<Utc>,
+    started_at: Option<DateTime<Utc>>,
+    finished_at: Option<DateTime<Utc>>,
+}
+
+impl From<Task> for TaskView {
+    fn from(task: Task) -> Self {
+        let Task {
+            id,
+            index_uid,
+            content,
+            events,
+        } = task;
+
+        let (task_type, mut details) = match content {
+            TaskContent::DocumentAddition {
+                merge_strategy,
+                documents_count,
+                ..
+            } => {
+                let details = TaskDetails::DocumentAddition {
+                    received_documents: documents_count,
+                    indexed_documents: None,
+                };
+
+                let task_type = match merge_strategy {
+                    IndexDocumentsMethod::UpdateDocuments => TaskType::DocumentPartial,
+                    IndexDocumentsMethod::ReplaceDocuments => TaskType::DocumentAddition,
+                    _ => unreachable!("Unexpected document merge strategy."),
+                };
+
+                (task_type, Some(details))
+            }
+            TaskContent::DocumentDeletion(DocumentDeletion::Ids(ids)) => (
+                TaskType::DocumentDeletion,
+                Some(TaskDetails::DocumentDeletion {
+                    received_document_ids: ids.len(),
+                    deleted_documents: None,
+                }),
+            ),
+            TaskContent::DocumentDeletion(DocumentDeletion::Clear) => (
+                TaskType::ClearAll,
+                Some(TaskDetails::ClearAll {
+                    deleted_documents: None,
+                }),
+            ),
+            TaskContent::IndexDeletion => (
+                TaskType::IndexDeletion,
+                Some(TaskDetails::ClearAll {
+                    deleted_documents: None,
+                }),
+            ),
+            TaskContent::SettingsUpdate { settings, .. } => (
+                TaskType::SettingsUpdate,
+                Some(TaskDetails::Settings { settings }),
+            ),
+            TaskContent::IndexCreation { primary_key } => (
+                TaskType::IndexCreation,
+                Some(TaskDetails::IndexInfo { primary_key }),
+            ),
+            TaskContent::IndexUpdate { primary_key } => (
+                TaskType::IndexUpdate,
+                Some(TaskDetails::IndexInfo { primary_key }),
+            ),
+        };
+
+        // An event always has at least one event: "Created"
+        let (status, error, finished_at) = match events.last().unwrap() {
+            TaskEvent::Created(_) => (TaskStatus::Enqueued, None, None),
+            TaskEvent::Batched { .. } => (TaskStatus::Enqueued, None, None),
+            TaskEvent::Processing(_) => (TaskStatus::Processing, None, None),
+            TaskEvent::Succeded { timestamp, result } => {
+                match (result, &mut details) {
+                    (
+                        TaskResult::DocumentAddition {
+                            indexed_documents: num,
+                            ..
+                        },
+                        Some(TaskDetails::DocumentAddition {
+                            ref mut indexed_documents,
+                            ..
+                        }),
+                    ) => {
+                        indexed_documents.replace(*num);
+                    }
+                    (
+                        TaskResult::DocumentDeletion {
+                            deleted_documents: docs,
+                            ..
+                        },
+                        Some(TaskDetails::DocumentDeletion {
+                            ref mut deleted_documents,
+                            ..
+                        }),
+                    ) => {
+                        deleted_documents.replace(*docs);
+                    }
+                    (
+                        TaskResult::ClearAll {
+                            deleted_documents: docs,
+                        },
+                        Some(TaskDetails::ClearAll {
+                            ref mut deleted_documents,
+                        }),
+                    ) => {
+                        deleted_documents.replace(*docs);
+                    }
+                    _ => (),
+                }
+                (TaskStatus::Succeeded, None, Some(*timestamp))
+            }
+            TaskEvent::Failed { timestamp, error } => {
+                match details {
+                    Some(TaskDetails::DocumentDeletion {
+                        ref mut deleted_documents,
+                        ..
+                    }) => {
+                        deleted_documents.replace(0);
+                    }
+                    Some(TaskDetails::ClearAll {
+                        ref mut deleted_documents,
+                        ..
+                    }) => {
+                        deleted_documents.replace(0);
+                    }
+                    Some(TaskDetails::DocumentAddition {
+                        ref mut indexed_documents,
+                        ..
+                    }) => {
+                        indexed_documents.replace(0);
+                    }
+                    _ => (),
+                }
+                (TaskStatus::Failed, Some(error.clone()), Some(*timestamp))
+            }
+        };
+
+        let enqueued_at = match events.first() {
+            Some(TaskEvent::Created(ts)) => *ts,
+            _ => unreachable!("A task must always have a creation event."),
+        };
+
+        let started_at = events.iter().find_map(|e| match e {
+            TaskEvent::Processing(ts) => Some(*ts),
+            _ => None,
+        });
+
+        let duration = finished_at.zip(started_at).map(|(tf, ts)| (tf - ts));
+
+        Self {
+            uid: id,
+            index_uid: index_uid.into_inner(),
+            status,
+            task_type,
+            details,
+            error,
+            duration,
+            enqueued_at,
+            started_at,
+            finished_at,
+        }
+    }
+}
+
+#[derive(Debug, Serialize)]
+pub struct TaskListView {
+    results: Vec<TaskView>,
+}
+
+impl From<Vec<TaskView>> for TaskListView {
+    fn from(results: Vec<TaskView>) -> Self {
+        Self { results }
+    }
+}
+
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct SummarizedTaskView {
+    uid: TaskId,
+    index_uid: String,
+    status: TaskStatus,
+    #[serde(rename = "type")]
+    task_type: TaskType,
+    enqueued_at: DateTime<Utc>,
+}
+
+impl From<Task> for SummarizedTaskView {
+    fn from(mut other: Task) -> Self {
+        let created_event = other
+            .events
+            .drain(..1)
+            .next()
+            .expect("Task must have an enqueued event.");
+
+        let enqueued_at = match created_event {
+            TaskEvent::Created(ts) => ts,
+            _ => unreachable!("The first event of a task must always be 'Created'"),
+        };
+
+        Self {
+            uid: other.id,
+            index_uid: other.index_uid.to_string(),
+            status: TaskStatus::Enqueued,
+            task_type: other.content.into(),
+            enqueued_at,
+        }
+    }
+}

meilisearch-http/tests/auth/authorization.rs

@@ -0,0 +1,630 @@
+use crate::common::Server;
+use chrono::{Duration, Utc};
+use maplit::hashmap;
+use once_cell::sync::Lazy;
+use serde_json::{json, Value};
+use std::collections::{HashMap, HashSet};
+
+static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), &'static str>> =
+    Lazy::new(|| {
+        hashmap! {
+            ("POST",    "/indexes/products/search") =>                         "search",
+            ("GET",     "/indexes/products/search") =>                         "search",
+            ("POST",    "/indexes/products/documents") =>                      "documents.add",
+            ("GET",     "/indexes/products/documents") =>                      "documents.get",
+            ("GET",     "/indexes/products/documents/0") =>                    "documents.get",
+            ("DELETE",  "/indexes/products/documents/0") =>                    "documents.delete",
+            ("GET",     "/tasks") =>                                           "tasks.get",
+            ("GET",     "/indexes/products/tasks") =>                          "tasks.get",
+            ("GET",     "/indexes/products/tasks/0") =>                        "tasks.get",
+            ("PUT",     "/indexes/products/") =>                               "indexes.update",
+            ("GET",     "/indexes/products/") =>                               "indexes.get",
+            ("DELETE",  "/indexes/products/") =>                               "indexes.delete",
+            ("POST",    "/indexes") =>                                         "indexes.create",
+            ("GET",     "/indexes") =>                                         "indexes.get",
+            ("GET",     "/indexes/products/settings") =>                       "settings.get",
+            ("GET",     "/indexes/products/settings/displayed-attributes") =>  "settings.get",
+            ("GET",     "/indexes/products/settings/distinct-attribute") =>    "settings.get",
+            ("GET",     "/indexes/products/settings/filterable-attributes") => "settings.get",
+            ("GET",     "/indexes/products/settings/ranking-rules") =>         "settings.get",
+            ("GET",     "/indexes/products/settings/searchable-attributes") => "settings.get",
+            ("GET",     "/indexes/products/settings/sortable-attributes") =>   "settings.get",
+            ("GET",     "/indexes/products/settings/stop-words") =>            "settings.get",
+            ("GET",     "/indexes/products/settings/synonyms") =>              "settings.get",
+            ("DELETE",  "/indexes/products/settings") =>                       "settings.update",
+            ("POST",    "/indexes/products/settings") =>                       "settings.update",
+            ("POST",    "/indexes/products/settings/displayed-attributes") =>  "settings.update",
+            ("POST",    "/indexes/products/settings/distinct-attribute") =>    "settings.update",
+            ("POST",    "/indexes/products/settings/filterable-attributes") => "settings.update",
+            ("POST",    "/indexes/products/settings/ranking-rules") =>         "settings.update",
+            ("POST",    "/indexes/products/settings/searchable-attributes") => "settings.update",
+            ("POST",    "/indexes/products/settings/sortable-attributes") =>   "settings.update",
+            ("POST",    "/indexes/products/settings/stop-words") =>            "settings.update",
+            ("POST",    "/indexes/products/settings/synonyms") =>              "settings.update",
+            ("GET",     "/indexes/products/stats") =>                          "stats.get",
+            ("GET",     "/stats") =>                                           "stats.get",
+            ("POST",    "/dumps") =>                                           "dumps.create",
+            ("GET",     "/dumps/0/status") =>                                  "dumps.get",
+            ("GET",     "/version") =>                                         "version",
+        }
+    });
+
+static ALL_ACTIONS: Lazy<HashSet<&'static str>> =
+    Lazy::new(|| AUTHORIZATIONS.values().cloned().collect());
+
+static INVALID_RESPONSE: Lazy<Value> = Lazy::new(|| {
+    json!({"message": "The provided API key is invalid.",
+        "code": "invalid_api_key",
+        "type": "auth",
+        "link": "https://docs.meilisearch.com/errors#invalid_api_key"
+    })
+});
+
+#[actix_rt::test]
+async fn error_access_expired_key() {
+    use std::{thread, time};
+
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    let content = json!({
+        "indexes": ["products"],
+        "actions": ALL_ACTIONS.clone(),
+        "expiresAt": (Utc::now() + Duration::seconds(1)),
+    });
+
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    // wait until the key is expired.
+    thread::sleep(time::Duration::new(1, 0));
+
+    for (method, route) in AUTHORIZATIONS.keys() {
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_eq!(response, INVALID_RESPONSE.clone());
+        assert_eq!(code, 403);
+    }
+}
+
+#[actix_rt::test]
+async fn error_access_unauthorized_index() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    let content = json!({
+        "indexes": ["sales"],
+        "actions": ALL_ACTIONS.clone(),
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    for (method, route) in AUTHORIZATIONS
+        .keys()
+        // filter `products` index routes
+        .filter(|(_, route)| route.starts_with("/indexes/products"))
+    {
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_eq!(response, INVALID_RESPONSE.clone());
+        assert_eq!(code, 403);
+    }
+}
+
+#[actix_rt::test]
+async fn error_access_unauthorized_action() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    let content = json!({
+        "indexes": ["products"],
+        "actions": [],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    for ((method, route), action) in AUTHORIZATIONS.iter() {
+        server.use_api_key("MASTER_KEY");
+
+        // Patch API key letting all rights but the needed one.
+        let content = json!({
+            "actions": ALL_ACTIONS.iter().cloned().filter(|a| a != action).collect::<Vec<_>>(),
+        });
+        let (_, code) = server.patch_api_key(&key, content).await;
+        assert_eq!(code, 200);
+
+        server.use_api_key(&key);
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_eq!(response, INVALID_RESPONSE.clone());
+        assert_eq!(code, 403);
+    }
+}
+
+#[actix_rt::test]
+async fn access_authorized_restricted_index() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    let content = json!({
+        "indexes": ["products"],
+        "actions": [],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    for ((method, route), action) in AUTHORIZATIONS.iter() {
+        // Patch API key letting only the needed action.
+        let content = json!({
+            "actions": [action],
+        });
+
+        server.use_api_key("MASTER_KEY");
+        let (_, code) = server.patch_api_key(&key, content).await;
+        assert_eq!(code, 200);
+
+        server.use_api_key(&key);
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_ne!(response, INVALID_RESPONSE.clone());
+        assert_ne!(code, 403);
+
+        // Patch API key using action all action.
+        let content = json!({
+            "actions": ["*"],
+        });
+
+        server.use_api_key("MASTER_KEY");
+        let (_, code) = server.patch_api_key(&key, content).await;
+        assert_eq!(code, 200);
+
+        server.use_api_key(&key);
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_ne!(response, INVALID_RESPONSE.clone());
+        assert_ne!(code, 403);
+    }
+}
+
+#[actix_rt::test]
+async fn access_authorized_no_index_restriction() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    let content = json!({
+        "indexes": ["*"],
+        "actions": [],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    for ((method, route), action) in AUTHORIZATIONS.iter() {
+        server.use_api_key("MASTER_KEY");
+
+        // Patch API key letting only the needed action.
+        let content = json!({
+            "actions": [action],
+        });
+        let (_, code) = server.patch_api_key(&key, content).await;
+        assert_eq!(code, 200);
+
+        server.use_api_key(&key);
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_ne!(response, INVALID_RESPONSE.clone());
+        assert_ne!(code, 403);
+
+        // Patch API key using action all action.
+        let content = json!({
+            "actions": ["*"],
+        });
+
+        server.use_api_key("MASTER_KEY");
+        let (_, code) = server.patch_api_key(&key, content).await;
+        assert_eq!(code, 200);
+
+        server.use_api_key(&key);
+        let (response, code) = server.dummy_request(method, route).await;
+
+        assert_ne!(response, INVALID_RESPONSE.clone());
+        assert_ne!(code, 403);
+    }
+}
+
+#[actix_rt::test]
+async fn access_authorized_stats_restricted_index() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create index `test`
+    let index = server.index("test");
+    let (_, code) = index.create(Some("id")).await;
+    assert_eq!(code, 202);
+    // create index `products`
+    let index = server.index("products");
+    let (_, code) = index.create(Some("product_id")).await;
+    assert_eq!(code, 202);
+    index.wait_task(0).await;
+
+    // create key with access on `products` index only.
+    let content = json!({
+        "indexes": ["products"],
+        "actions": ["stats.get"],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let (response, code) = server.stats().await;
+    assert_eq!(code, 200);
+
+    // key should have access on `products` index.
+    assert!(response["indexes"].get("products").is_some());
+
+    // key should not have access on `test` index.
+    assert!(response["indexes"].get("test").is_none());
+}
+
+#[actix_rt::test]
+async fn access_authorized_stats_no_index_restriction() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create index `test`
+    let index = server.index("test");
+    let (_, code) = index.create(Some("id")).await;
+    assert_eq!(code, 202);
+    // create index `products`
+    let index = server.index("products");
+    let (_, code) = index.create(Some("product_id")).await;
+    assert_eq!(code, 202);
+    index.wait_task(0).await;
+
+    // create key with access on all indexes.
+    let content = json!({
+        "indexes": ["*"],
+        "actions": ["stats.get"],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let (response, code) = server.stats().await;
+    assert_eq!(code, 200);
+
+    // key should have access on `products` index.
+    assert!(response["indexes"].get("products").is_some());
+
+    // key should have access on `test` index.
+    assert!(response["indexes"].get("test").is_some());
+}
+
+#[actix_rt::test]
+async fn list_authorized_indexes_restricted_index() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create index `test`
+    let index = server.index("test");
+    let (_, code) = index.create(Some("id")).await;
+    assert_eq!(code, 202);
+    // create index `products`
+    let index = server.index("products");
+    let (_, code) = index.create(Some("product_id")).await;
+    assert_eq!(code, 202);
+    index.wait_task(0).await;
+
+    // create key with access on `products` index only.
+    let content = json!({
+        "indexes": ["products"],
+        "actions": ["indexes.get"],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let (response, code) = server.list_indexes().await;
+    assert_eq!(code, 200);
+
+    let response = response.as_array().unwrap();
+    // key should have access on `products` index.
+    assert!(response.iter().any(|index| index["uid"] == "products"));
+
+    // key should not have access on `test` index.
+    assert!(!response.iter().any(|index| index["uid"] == "test"));
+}
+
+#[actix_rt::test]
+async fn list_authorized_indexes_no_index_restriction() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create index `test`
+    let index = server.index("test");
+    let (_, code) = index.create(Some("id")).await;
+    assert_eq!(code, 202);
+    // create index `products`
+    let index = server.index("products");
+    let (_, code) = index.create(Some("product_id")).await;
+    assert_eq!(code, 202);
+    index.wait_task(0).await;
+
+    // create key with access on all indexes.
+    let content = json!({
+        "indexes": ["*"],
+        "actions": ["indexes.get"],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let (response, code) = server.list_indexes().await;
+    assert_eq!(code, 200);
+
+    let response = response.as_array().unwrap();
+    // key should have access on `products` index.
+    assert!(response.iter().any(|index| index["uid"] == "products"));
+
+    // key should have access on `test` index.
+    assert!(response.iter().any(|index| index["uid"] == "test"));
+}
+
+#[actix_rt::test]
+async fn list_authorized_tasks_restricted_index() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create index `test`
+    let index = server.index("test");
+    let (_, code) = index.create(Some("id")).await;
+    assert_eq!(code, 202);
+    // create index `products`
+    let index = server.index("products");
+    let (_, code) = index.create(Some("product_id")).await;
+    assert_eq!(code, 202);
+    index.wait_task(0).await;
+
+    // create key with access on `products` index only.
+    let content = json!({
+        "indexes": ["products"],
+        "actions": ["tasks.get"],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let (response, code) = server.service.get("/tasks").await;
+    assert_eq!(code, 200);
+    println!("{}", response);
+    let response = response["results"].as_array().unwrap();
+    // key should have access on `products` index.
+    assert!(response.iter().any(|task| task["indexUid"] == "products"));
+
+    // key should not have access on `test` index.
+    assert!(!response.iter().any(|task| task["indexUid"] == "test"));
+}
+
+#[actix_rt::test]
+async fn list_authorized_tasks_no_index_restriction() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create index `test`
+    let index = server.index("test");
+    let (_, code) = index.create(Some("id")).await;
+    assert_eq!(code, 202);
+    // create index `products`
+    let index = server.index("products");
+    let (_, code) = index.create(Some("product_id")).await;
+    assert_eq!(code, 202);
+    index.wait_task(0).await;
+
+    // create key with access on all indexes.
+    let content = json!({
+        "indexes": ["*"],
+        "actions": ["tasks.get"],
+        "expiresAt": Utc::now() + Duration::hours(1),
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let (response, code) = server.service.get("/tasks").await;
+    assert_eq!(code, 200);
+
+    let response = response["results"].as_array().unwrap();
+    // key should have access on `products` index.
+    assert!(response.iter().any(|task| task["indexUid"] == "products"));
+
+    // key should have access on `test` index.
+    assert!(response.iter().any(|task| task["indexUid"] == "test"));
+}
+
+#[actix_rt::test]
+async fn error_creating_index_without_action() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create key with access on all indexes.
+    let content = json!({
+        "indexes": ["*"],
+        "actions": ALL_ACTIONS.iter().cloned().filter(|a| *a != "indexes.create").collect::<Vec<_>>(),
+        "expiresAt": "2050-11-13T00:00:00Z"
+    });
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    let expected_error = json!({
+        "message": "Index `test` not found.",
+        "code": "index_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#index_not_found"
+    });
+
+    // try to create a index via add documents route
+    let index = server.index("test");
+    let documents = json!([
+        {
+            "id": 1,
+            "content": "foo",
+        }
+    ]);
+
+    let (response, code) = index.add_documents(documents, None).await;
+    assert_eq!(code, 202, "{:?}", response);
+    let task_id = response["uid"].as_u64().unwrap();
+
+    let response = index.wait_task(task_id).await;
+    assert_eq!(response["status"], "failed");
+    assert_eq!(response["error"], expected_error.clone());
+
+    // try to create a index via add settings route
+    let settings = json!({ "distinctAttribute": "test"});
+
+    let (response, code) = index.update_settings(settings).await;
+    assert_eq!(code, 202);
+    let task_id = response["uid"].as_u64().unwrap();
+
+    let response = index.wait_task(task_id).await;
+
+    assert_eq!(response["status"], "failed");
+    assert_eq!(response["error"], expected_error.clone());
+
+    // try to create a index via add specialized settings route
+    let (response, code) = index.update_distinct_attribute(json!("test")).await;
+    assert_eq!(code, 202);
+    let task_id = response["uid"].as_u64().unwrap();
+
+    let response = index.wait_task(task_id).await;
+
+    assert_eq!(response["status"], "failed");
+    assert_eq!(response["error"], expected_error.clone());
+}
+
+#[actix_rt::test]
+async fn lazy_create_index() {
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+
+    // create key with access on all indexes.
+    let content = json!({
+        "indexes": ["*"],
+        "actions": ["*"],
+        "expiresAt": "2050-11-13T00:00:00Z"
+    });
+
+    let (response, code) = server.add_api_key(content).await;
+    assert_eq!(code, 201);
+    assert!(response["key"].is_string());
+
+    // use created key.
+    let key = response["key"].as_str().unwrap();
+    server.use_api_key(&key);
+
+    // try to create a index via add documents route
+    let index = server.index("test");
+    let documents = json!([
+        {
+            "id": 1,
+            "content": "foo",
+        }
+    ]);
+
+    let (response, code) = index.add_documents(documents, None).await;
+    assert_eq!(code, 202, "{:?}", response);
+    let task_id = response["uid"].as_u64().unwrap();
+
+    index.wait_task(task_id).await;
+
+    let (response, code) = index.get_task(task_id).await;
+    assert_eq!(code, 200);
+    assert_eq!(response["status"], "succeeded");
+
+    // try to create a index via add settings route
+    let index = server.index("test1");
+    let settings = json!({ "distinctAttribute": "test"});
+
+    let (response, code) = index.update_settings(settings).await;
+    assert_eq!(code, 202);
+    let task_id = response["uid"].as_u64().unwrap();
+
+    index.wait_task(task_id).await;
+
+    let (response, code) = index.get_task(task_id).await;
+    assert_eq!(code, 200);
+    assert_eq!(response["status"], "succeeded");
+
+    // try to create a index via add specialized settings route
+    let index = server.index("test2");
+    let (response, code) = index.update_distinct_attribute(json!("test")).await;
+    assert_eq!(code, 202);
+    let task_id = response["uid"].as_u64().unwrap();
+
+    index.wait_task(task_id).await;
+
+    let (response, code) = index.get_task(task_id).await;
+    assert_eq!(code, 200);
+    assert_eq!(response["status"], "succeeded");
+}

meilisearch-http/tests/auth/mod.rs

@@ -0,0 +1,54 @@
+mod api_keys;
+mod authorization;
+mod payload;
+
+use crate::common::Server;
+use actix_web::http::StatusCode;
+
+use serde_json::{json, Value};
+
+impl Server {
+    pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {
+        self.service.api_key = Some(api_key.as_ref().to_string());
+    }
+
+    pub async fn add_api_key(&self, content: Value) -> (Value, StatusCode) {
+        let url = "/keys";
+        self.service.post(url, content).await
+    }
+
+    pub async fn get_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/keys/{}", key.as_ref());
+        self.service.get(url).await
+    }
+
+    pub async fn patch_api_key(&self, key: impl AsRef<str>, content: Value) -> (Value, StatusCode) {
+        let url = format!("/keys/{}", key.as_ref());
+        self.service.patch(url, content).await
+    }
+
+    pub async fn list_api_keys(&self) -> (Value, StatusCode) {
+        let url = "/keys";
+        self.service.get(url).await
+    }
+
+    pub async fn delete_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/keys/{}", key.as_ref());
+        self.service.delete(url).await
+    }
+
+    pub async fn dummy_request(
+        &self,
+        method: impl AsRef<str>,
+        url: impl AsRef<str>,
+    ) -> (Value, StatusCode) {
+        match method.as_ref() {
+            "POST" => self.service.post(url, json!({})).await,
+            "PUT" => self.service.put(url, json!({})).await,
+            "PATCH" => self.service.patch(url, json!({})).await,
+            "GET" => self.service.get(url).await,
+            "DELETE" => self.service.delete(url).await,
+            _ => unreachable!(),
+        }
+    }
+}

meilisearch-http/tests/auth/payload.rs

@@ -0,0 +1,340 @@
+use crate::common::Server;
+use actix_web::test;
+use meilisearch_http::{analytics, create_app};
+use serde_json::{json, Value};
+
+#[actix_rt::test]
+async fn error_api_key_bad_content_types() {
+    let content = json!({
+        "indexes": ["products"],
+        "actions": [
+            "documents.add"
+        ],
+        "expiresAt": "2050-11-13T00:00:00Z"
+    });
+
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+
+    // post
+    let req = test::TestRequest::post()
+        .uri("/keys")
+        .set_payload(content.to_string())
+        .insert_header(("content-type", "text/plain"))
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 415);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The Content-Type `text/plain` is invalid. Accepted values for the Content-Type header are: `application/json`"#
+        )
+    );
+    assert_eq!(response["code"], "invalid_content_type");
+    assert_eq!(response["type"], "invalid_request");
+    assert_eq!(
+        response["link"],
+        "https://docs.meilisearch.com/errors#invalid_content_type"
+    );
+
+    // patch
+    let req = test::TestRequest::patch()
+        .uri("/keys/d0552b41536279a0ad88bd595327b96f01176a60c2243e906c52ac02375f9bc4")
+        .set_payload(content.to_string())
+        .insert_header(("content-type", "text/plain"))
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 415);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The Content-Type `text/plain` is invalid. Accepted values for the Content-Type header are: `application/json`"#
+        )
+    );
+    assert_eq!(response["code"], "invalid_content_type");
+    assert_eq!(response["type"], "invalid_request");
+    assert_eq!(
+        response["link"],
+        "https://docs.meilisearch.com/errors#invalid_content_type"
+    );
+}
+
+#[actix_rt::test]
+async fn error_api_key_empty_content_types() {
+    let content = json!({
+        "indexes": ["products"],
+        "actions": [
+            "documents.add"
+        ],
+        "expiresAt": "2050-11-13T00:00:00Z"
+    });
+
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+
+    // post
+    let req = test::TestRequest::post()
+        .uri("/keys")
+        .set_payload(content.to_string())
+        .insert_header(("content-type", ""))
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 415);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The Content-Type `` is invalid. Accepted values for the Content-Type header are: `application/json`"#
+        )
+    );
+    assert_eq!(response["code"], "invalid_content_type");
+    assert_eq!(response["type"], "invalid_request");
+    assert_eq!(
+        response["link"],
+        "https://docs.meilisearch.com/errors#invalid_content_type"
+    );
+
+    // patch
+    let req = test::TestRequest::patch()
+        .uri("/keys/d0552b41536279a0ad88bd595327b96f01176a60c2243e906c52ac02375f9bc4")
+        .set_payload(content.to_string())
+        .insert_header(("content-type", ""))
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 415);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The Content-Type `` is invalid. Accepted values for the Content-Type header are: `application/json`"#
+        )
+    );
+    assert_eq!(response["code"], "invalid_content_type");
+    assert_eq!(response["type"], "invalid_request");
+    assert_eq!(
+        response["link"],
+        "https://docs.meilisearch.com/errors#invalid_content_type"
+    );
+}
+
+#[actix_rt::test]
+async fn error_api_key_missing_content_types() {
+    let content = json!({
+        "indexes": ["products"],
+        "actions": [
+            "documents.add"
+        ],
+        "expiresAt": "2050-11-13T00:00:00Z"
+    });
+
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+
+    // post
+    let req = test::TestRequest::post()
+        .uri("/keys")
+        .set_payload(content.to_string())
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 415);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"A Content-Type header is missing. Accepted values for the Content-Type header are: `application/json`"#
+        )
+    );
+    assert_eq!(response["code"], "missing_content_type");
+    assert_eq!(response["type"], "invalid_request");
+    assert_eq!(
+        response["link"],
+        "https://docs.meilisearch.com/errors#missing_content_type"
+    );
+
+    // patch
+    let req = test::TestRequest::patch()
+        .uri("/keys/d0552b41536279a0ad88bd595327b96f01176a60c2243e906c52ac02375f9bc4")
+        .set_payload(content.to_string())
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 415);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"A Content-Type header is missing. Accepted values for the Content-Type header are: `application/json`"#
+        )
+    );
+    assert_eq!(response["code"], "missing_content_type");
+    assert_eq!(response["type"], "invalid_request");
+    assert_eq!(
+        response["link"],
+        "https://docs.meilisearch.com/errors#missing_content_type"
+    );
+}
+
+#[actix_rt::test]
+async fn error_api_key_empty_payload() {
+    let content = "";
+
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+
+    // post
+    let req = test::TestRequest::post()
+        .uri("/keys")
+        .set_payload(content)
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .insert_header(("content-type", "application/json"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 400);
+    assert_eq!(response["code"], json!("missing_payload"));
+    assert_eq!(response["type"], json!("invalid_request"));
+    assert_eq!(
+        response["link"],
+        json!("https://docs.meilisearch.com/errors#missing_payload")
+    );
+    assert_eq!(response["message"], json!(r#"A json payload is missing."#));
+
+    // patch
+    let req = test::TestRequest::patch()
+        .uri("/keys/d0552b41536279a0ad88bd595327b96f01176a60c2243e906c52ac02375f9bc4")
+        .set_payload(content)
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .insert_header(("content-type", "application/json"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 400);
+    assert_eq!(response["code"], json!("missing_payload"));
+    assert_eq!(response["type"], json!("invalid_request"));
+    assert_eq!(
+        response["link"],
+        json!("https://docs.meilisearch.com/errors#missing_payload")
+    );
+    assert_eq!(response["message"], json!(r#"A json payload is missing."#));
+}
+
+#[actix_rt::test]
+async fn error_api_key_malformed_payload() {
+    let content = r#"{"malormed": "payload""#;
+
+    let mut server = Server::new_auth().await;
+    server.use_api_key("MASTER_KEY");
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+
+    // post
+    let req = test::TestRequest::post()
+        .uri("/keys")
+        .set_payload(content)
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .insert_header(("content-type", "application/json"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 400);
+    assert_eq!(response["code"], json!("malformed_payload"));
+    assert_eq!(response["type"], json!("invalid_request"));
+    assert_eq!(
+        response["link"],
+        json!("https://docs.meilisearch.com/errors#malformed_payload")
+    );
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The json payload provided is malformed. `EOF while parsing an object at line 1 column 22`."#
+        )
+    );
+
+    // patch
+    let req = test::TestRequest::patch()
+        .uri("/keys/d0552b41536279a0ad88bd595327b96f01176a60c2243e906c52ac02375f9bc4")
+        .set_payload(content)
+        .insert_header(("Authorization", "Bearer MASTER_KEY"))
+        .insert_header(("content-type", "application/json"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 400);
+    assert_eq!(response["code"], json!("malformed_payload"));
+    assert_eq!(response["type"], json!("invalid_request"));
+    assert_eq!(
+        response["link"],
+        json!("https://docs.meilisearch.com/errors#malformed_payload")
+    );
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The json payload provided is malformed. `EOF while parsing an object at line 1 column 22`."#
+        )
+    );
+}

meilisearch-http/tests/common/index.rs

@@ -7,6 +7,7 @@ use actix_web::http::StatusCode;
 use paste::paste;
 use serde_json::{json, Value};
 use tokio::time::sleep;
+use urlencoding::encode;
 
 use super::service::Service;
 
@@ -14,12 +15,12 @@ macro_rules! make_settings_test_routes {
     ($($name:ident),+) => {
         $(paste! {
             pub async fn [<update_$name>](&self, value: Value) -> (Value, StatusCode) {
-                let url = format!("/indexes/{}/settings/{}", self.uid, stringify!($name).replace("_", "-"));
+                let url = format!("/indexes/{}/settings/{}", encode(self.uid.as_ref()).to_string(), stringify!($name).replace("_", "-"));
                 self.service.post(url, value).await
             }
 
             pub async fn [<get_$name>](&self) -> (Value, StatusCode) {
-                let url = format!("/indexes/{}/settings/{}", self.uid, stringify!($name).replace("_", "-"));
+                let url = format!("/indexes/{}/settings/{}", encode(self.uid.as_ref()).to_string(), stringify!($name).replace("_", "-"));
                 self.service.get(url).await
             }
         })*
@@ -34,19 +35,19 @@ pub struct Index<'a> {
 #[allow(dead_code)]
 impl Index<'_> {
     pub async fn get(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", self.uid);
+        let url = format!("/indexes/{}", encode(self.uid.as_ref()));
         self.service.get(url).await
     }
 
     pub async fn load_test_set(&self) -> u64 {
-        let url = format!("/indexes/{}/documents", self.uid);
+        let url = format!("/indexes/{}/documents", encode(self.uid.as_ref()));
         let (response, code) = self
             .service
             .post_str(url, include_str!("../assets/test_set.json"))
             .await;
         assert_eq!(code, 202);
-        let update_id = response["updateId"].as_i64().unwrap();
-        self.wait_update_id(update_id as u64).await;
+        let update_id = response["uid"].as_i64().unwrap();
+        self.wait_task(update_id as u64).await;
         update_id as u64
     }
 
@@ -62,13 +63,13 @@ impl Index<'_> {
         let body = json!({
             "primaryKey": primary_key,
         });
-        let url = format!("/indexes/{}", self.uid);
+        let url = format!("/indexes/{}", encode(self.uid.as_ref()));
 
         self.service.put(url, body).await
     }
 
     pub async fn delete(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", self.uid);
+        let url = format!("/indexes/{}", encode(self.uid.as_ref()));
         self.service.delete(url).await
     }
 
@@ -78,8 +79,12 @@ impl Index<'_> {
         primary_key: Option<&str>,
     ) -> (Value, StatusCode) {
         let url = match primary_key {
-            Some(key) => format!("/indexes/{}/documents?primaryKey={}", self.uid, key),
-            None => format!("/indexes/{}/documents", self.uid),
+            Some(key) => format!(
+                "/indexes/{}/documents?primaryKey={}",
+                encode(self.uid.as_ref()),
+                key
+            ),
+            None => format!("/indexes/{}/documents", encode(self.uid.as_ref())),
         };
         self.service.post(url, documents).await
     }
@@ -90,20 +95,24 @@ impl Index<'_> {
         primary_key: Option<&str>,
     ) -> (Value, StatusCode) {
         let url = match primary_key {
-            Some(key) => format!("/indexes/{}/documents?primaryKey={}", self.uid, key),
-            None => format!("/indexes/{}/documents", self.uid),
+            Some(key) => format!(
+                "/indexes/{}/documents?primaryKey={}",
+                encode(self.uid.as_ref()),
+                key
+            ),
+            None => format!("/indexes/{}/documents", encode(self.uid.as_ref())),
         };
         self.service.put(url, documents).await
     }
 
-    pub async fn wait_update_id(&self, update_id: u64) -> Value {
+    pub async fn wait_task(&self, update_id: u64) -> Value {
         // try 10 times to get status, or panic to not wait forever
-        let url = format!("/indexes/{}/updates/{}", self.uid, update_id);
+        let url = format!("/tasks/{}", update_id);
         for _ in 0..10 {
             let (response, status_code) = self.service.get(&url).await;
             assert_eq!(status_code, 200, "response: {}", response);
 
-            if response["status"] == "processed" || response["status"] == "failed" {
+            if response["status"] == "succeeded" || response["status"] == "failed" {
                 return response;
             }
 
@@ -112,13 +121,13 @@ impl Index<'_> {
         panic!("Timeout waiting for update id");
     }
 
-    pub async fn get_update(&self, update_id: u64) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/updates/{}", self.uid, update_id);
+    pub async fn get_task(&self, update_id: u64) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/tasks/{}", self.uid, update_id);
         self.service.get(url).await
     }
 
-    pub async fn list_updates(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/updates", self.uid);
+    pub async fn list_tasks(&self) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/tasks", self.uid);
         self.service.get(url).await
     }
 
@@ -127,12 +136,12 @@ impl Index<'_> {
         id: u64,
         _options: Option<GetDocumentOptions>,
     ) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/{}", self.uid, id);
+        let url = format!("/indexes/{}/documents/{}", encode(self.uid.as_ref()), id);
         self.service.get(url).await
     }
 
     pub async fn get_all_documents(&self, options: GetAllDocumentsOptions) -> (Value, StatusCode) {
-        let mut url = format!("/indexes/{}/documents?", self.uid);
+        let mut url = format!("/indexes/{}/documents?", encode(self.uid.as_ref()));
         if let Some(limit) = options.limit {
             url.push_str(&format!("limit={}&", limit));
         }
@@ -152,39 +161,42 @@ impl Index<'_> {
     }
 
     pub async fn delete_document(&self, id: u64) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/{}", self.uid, id);
+        let url = format!("/indexes/{}/documents/{}", encode(self.uid.as_ref()), id);
         self.service.delete(url).await
     }
 
     pub async fn clear_all_documents(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents", self.uid);
+        let url = format!("/indexes/{}/documents", encode(self.uid.as_ref()));
         self.service.delete(url).await
     }
 
     pub async fn delete_batch(&self, ids: Vec<u64>) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/delete-batch", self.uid);
+        let url = format!(
+            "/indexes/{}/documents/delete-batch",
+            encode(self.uid.as_ref())
+        );
         self.service
             .post(url, serde_json::to_value(&ids).unwrap())
             .await
     }
 
     pub async fn settings(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", self.uid);
+        let url = format!("/indexes/{}/settings", encode(self.uid.as_ref()));
         self.service.get(url).await
     }
 
     pub async fn update_settings(&self, settings: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", self.uid);
+        let url = format!("/indexes/{}/settings", encode(self.uid.as_ref()));
         self.service.post(url, settings).await
     }
 
     pub async fn delete_settings(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", self.uid);
+        let url = format!("/indexes/{}/settings", encode(self.uid.as_ref()));
         self.service.delete(url).await
     }
 
     pub async fn stats(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/stats", self.uid);
+        let url = format!("/indexes/{}/stats", encode(self.uid.as_ref()));
         self.service.get(url).await
     }
 
@@ -209,13 +221,13 @@ impl Index<'_> {
     }
 
     pub async fn search_post(&self, query: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/search", self.uid);
+        let url = format!("/indexes/{}/search", encode(self.uid.as_ref()));
         self.service.post(url, query).await
     }
 
     pub async fn search_get(&self, query: Value) -> (Value, StatusCode) {
         let params = serde_url_params::to_string(&query).unwrap();
-        let url = format!("/indexes/{}/search?{}", self.uid, params);
+        let url = format!("/indexes/{}/search?{}", encode(self.uid.as_ref()), params);
         self.service.get(url).await
     }
 

meilisearch-http/tests/common/server.rs

@@ -1,13 +1,16 @@
+#![allow(dead_code)]
 use std::path::Path;
 
 use actix_web::http::StatusCode;
 use byte_unit::{Byte, ByteUnit};
+use meilisearch_auth::AuthController;
+use meilisearch_http::setup_meilisearch;
+use meilisearch_lib::options::{IndexerOpts, MaxMemory};
+use once_cell::sync::Lazy;
 use serde_json::Value;
-use tempdir::TempDir;
-use urlencoding::encode;
+use tempfile::TempDir;
 
-use meilisearch_http::data::Data;
-use meilisearch_http::option::{IndexerOpts, MaxMemory, Opt};
+use meilisearch_http::option::Opt;
 
 use super::index::Index;
 use super::service::Service;
@@ -15,17 +18,31 @@ use super::service::Service;
 pub struct Server {
     pub service: Service,
     // hold ownership to the tempdir while we use the server instance.
-    _dir: Option<tempdir::TempDir>,
+    _dir: Option<TempDir>,
 }
 
+pub static TEST_TEMP_DIR: Lazy<TempDir> = Lazy::new(|| TempDir::new().unwrap());
+
 impl Server {
     pub async fn new() -> Self {
-        let dir = TempDir::new("meilisearch").unwrap();
+        let dir = TempDir::new().unwrap();
 
-        let opt = default_settings(dir.path());
+        if cfg!(windows) {
+            std::env::set_var("TMP", TEST_TEMP_DIR.path());
+        } else {
+            std::env::set_var("TMPDIR", TEST_TEMP_DIR.path());
+        }
 
-        let data = Data::new(opt).unwrap();
-        let service = Service(data);
+        let options = default_settings(dir.path());
+
+        let meilisearch = setup_meilisearch(&options).unwrap();
+        let auth = AuthController::new(&options.db_path, &options.master_key).unwrap();
+        let service = Service {
+            meilisearch,
+            auth,
+            options,
+            api_key: None,
+        };
 
         Server {
             service,
@@ -33,9 +50,42 @@ impl Server {
         }
     }
 
-    pub async fn new_with_options(opt: Opt) -> Self {
-        let data = Data::new(opt).unwrap();
-        let service = Service(data);
+    pub async fn new_auth() -> Self {
+        let dir = TempDir::new().unwrap();
+
+        if cfg!(windows) {
+            std::env::set_var("TMP", TEST_TEMP_DIR.path());
+        } else {
+            std::env::set_var("TMPDIR", TEST_TEMP_DIR.path());
+        }
+
+        let mut options = default_settings(dir.path());
+        options.master_key = Some("MASTER_KEY".to_string());
+
+        let meilisearch = setup_meilisearch(&options).unwrap();
+        let auth = AuthController::new(&options.db_path, &options.master_key).unwrap();
+        let service = Service {
+            meilisearch,
+            auth,
+            options,
+            api_key: None,
+        };
+
+        Server {
+            service,
+            _dir: Some(dir),
+        }
+    }
+
+    pub async fn new_with_options(options: Opt) -> Self {
+        let meilisearch = setup_meilisearch(&options).unwrap();
+        let auth = AuthController::new(&options.db_path, &options.master_key).unwrap();
+        let service = Service {
+            meilisearch,
+            auth,
+            options,
+            api_key: None,
+        };
 
         Server {
             service,
@@ -46,7 +96,7 @@ impl Server {
     /// Returns a view to an index. There is no guarantee that the index exists.
     pub fn index(&self, uid: impl AsRef<str>) -> Index<'_> {
         Index {
-            uid: encode(uid.as_ref()),
+            uid: uid.as_ref().to_string(),
             service: &self.service,
         }
     }
@@ -62,6 +112,14 @@ impl Server {
     pub async fn stats(&self) -> (Value, StatusCode) {
         self.service.get("/stats").await
     }
+
+    pub async fn tasks(&self) -> (Value, StatusCode) {
+        self.service.get("/tasks").await
+    }
+
+    pub async fn get_dump_status(&self, uid: &str) -> (Value, StatusCode) {
+        self.service.get(format!("/dumps/{}/status", uid)).await
+    }
 }
 
 pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
@@ -72,9 +130,9 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
         master_key: None,
         env: "development".to_owned(),
         #[cfg(all(not(debug_assertions), feature = "analytics"))]
-        no_analytics: true,
+        no_analytics: Some(Some(true)),
         max_index_size: Byte::from_unit(4.0, ByteUnit::GiB).unwrap(),
-        max_udb_size: Byte::from_unit(4.0, ByteUnit::GiB).unwrap(),
+        max_task_db_size: Byte::from_unit(4.0, ByteUnit::GiB).unwrap(),
         http_payload_size_limit: Byte::from_unit(10.0, ByteUnit::MiB).unwrap(),
         ssl_cert_path: None,
         ssl_key_path: None,

meilisearch-http/tests/common/service.rs

@@ -1,19 +1,33 @@
 use actix_web::{http::StatusCode, test};
+use meilisearch_auth::AuthController;
+use meilisearch_lib::MeiliSearch;
 use serde_json::Value;
 
-use meilisearch_http::create_app;
-use meilisearch_http::data::Data;
+use meilisearch_http::{analytics, create_app, Opt};
 
-pub struct Service(pub Data);
+pub struct Service {
+    pub meilisearch: MeiliSearch,
+    pub auth: AuthController,
+    pub options: Opt,
+    pub api_key: Option<String>,
+}
 
 impl Service {
     pub async fn post(&self, url: impl AsRef<str>, body: Value) -> (Value, StatusCode) {
-        let app = test::init_service(create_app!(&self.0, true)).await;
+        let app = test::init_service(create_app!(
+            &self.meilisearch,
+            &self.auth,
+            true,
+            &self.options,
+            analytics::MockAnalytics::new(&self.options).0
+        ))
+        .await;
 
-        let req = test::TestRequest::post()
-            .uri(url.as_ref())
-            .set_json(&body)
-            .to_request();
+        let mut req = test::TestRequest::post().uri(url.as_ref()).set_json(&body);
+        if let Some(api_key) = &self.api_key {
+            req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));
+        }
+        let req = req.to_request();
         let res = test::call_service(&app, req).await;
         let status_code = res.status();
 
@@ -28,13 +42,23 @@ impl Service {
         url: impl AsRef<str>,
         body: impl AsRef<str>,
     ) -> (Value, StatusCode) {
-        let app = test::init_service(create_app!(&self.0, true)).await;
+        let app = test::init_service(create_app!(
+            &self.meilisearch,
+            &self.auth,
+            true,
+            &self.options,
+            analytics::MockAnalytics::new(&self.options).0
+        ))
+        .await;
 
-        let req = test::TestRequest::post()
+        let mut req = test::TestRequest::post()
             .uri(url.as_ref())
             .set_payload(body.as_ref().to_string())
-            .insert_header(("content-type", "application/json"))
-            .to_request();
+            .insert_header(("content-type", "application/json"));
+        if let Some(api_key) = &self.api_key {
+            req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));
+        }
+        let req = req.to_request();
         let res = test::call_service(&app, req).await;
         let status_code = res.status();
 
@@ -44,9 +68,20 @@ impl Service {
     }
 
     pub async fn get(&self, url: impl AsRef<str>) -> (Value, StatusCode) {
-        let app = test::init_service(create_app!(&self.0, true)).await;
+        let app = test::init_service(create_app!(
+            &self.meilisearch,
+            &self.auth,
+            true,
+            &self.options,
+            analytics::MockAnalytics::new(&self.options).0
+        ))
+        .await;
 
-        let req = test::TestRequest::get().uri(url.as_ref()).to_request();
+        let mut req = test::TestRequest::get().uri(url.as_ref());
+        if let Some(api_key) = &self.api_key {
+            req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));
+        }
+        let req = req.to_request();
         let res = test::call_service(&app, req).await;
         let status_code = res.status();
 
@@ -56,12 +91,43 @@ impl Service {
     }
 
     pub async fn put(&self, url: impl AsRef<str>, body: Value) -> (Value, StatusCode) {
-        let app = test::init_service(create_app!(&self.0, true)).await;
+        let app = test::init_service(create_app!(
+            &self.meilisearch,
+            &self.auth,
+            true,
+            &self.options,
+            analytics::MockAnalytics::new(&self.options).0
+        ))
+        .await;
 
-        let req = test::TestRequest::put()
-            .uri(url.as_ref())
-            .set_json(&body)
-            .to_request();
+        let mut req = test::TestRequest::put().uri(url.as_ref()).set_json(&body);
+        if let Some(api_key) = &self.api_key {
+            req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));
+        }
+        let req = req.to_request();
+        let res = test::call_service(&app, req).await;
+        let status_code = res.status();
+
+        let body = test::read_body(res).await;
+        let response = serde_json::from_slice(&body).unwrap_or_default();
+        (response, status_code)
+    }
+
+    pub async fn patch(&self, url: impl AsRef<str>, body: Value) -> (Value, StatusCode) {
+        let app = test::init_service(create_app!(
+            &self.meilisearch,
+            &self.auth,
+            true,
+            &self.options,
+            analytics::MockAnalytics::new(&self.options).0
+        ))
+        .await;
+
+        let mut req = test::TestRequest::patch().uri(url.as_ref()).set_json(&body);
+        if let Some(api_key) = &self.api_key {
+            req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));
+        }
+        let req = req.to_request();
         let res = test::call_service(&app, req).await;
         let status_code = res.status();
 
@@ -71,9 +137,20 @@ impl Service {
     }
 
     pub async fn delete(&self, url: impl AsRef<str>) -> (Value, StatusCode) {
-        let app = test::init_service(create_app!(&self.0, true)).await;
+        let app = test::init_service(create_app!(
+            &self.meilisearch,
+            &self.auth,
+            true,
+            &self.options,
+            analytics::MockAnalytics::new(&self.options).0
+        ))
+        .await;
 
-        let req = test::TestRequest::delete().uri(url.as_ref()).to_request();
+        let mut req = test::TestRequest::delete().uri(url.as_ref());
+        if let Some(api_key) = &self.api_key {
+            req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));
+        }
+        let req = req.to_request();
         let res = test::call_service(&app, req).await;
         let status_code = res.status();
 

meilisearch-http/tests/content_type.rs

@@ -0,0 +1,150 @@
+#![allow(dead_code)]
+
+mod common;
+
+use crate::common::Server;
+use actix_web::test;
+use meilisearch_http::{analytics, create_app};
+use serde_json::{json, Value};
+
+#[actix_rt::test]
+async fn error_json_bad_content_type() {
+    let routes = [
+        // all the POST routes except the dumps that can be created without any body or content-type
+        // and the search that is not a strict json
+        "/indexes",
+        "/indexes/doggo/documents/delete-batch",
+        "/indexes/doggo/search",
+        "/indexes/doggo/settings",
+        "/indexes/doggo/settings/displayed-attributes",
+        "/indexes/doggo/settings/distinct-attribute",
+        "/indexes/doggo/settings/filterable-attributes",
+        "/indexes/doggo/settings/ranking-rules",
+        "/indexes/doggo/settings/searchable-attributes",
+        "/indexes/doggo/settings/sortable-attributes",
+        "/indexes/doggo/settings/stop-words",
+        "/indexes/doggo/settings/synonyms",
+    ];
+    let bad_content_types = [
+        "application/csv",
+        "application/x-ndjson",
+        "application/x-www-form-urlencoded",
+        "text/plain",
+        "json",
+        "application",
+        "json/application",
+    ];
+
+    let document = "{}";
+    let server = Server::new().await;
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+    for route in routes {
+        // Good content-type, we probably have an error since we didn't send anything in the json
+        // so we only ensure we didn't get a bad media type error.
+        let req = test::TestRequest::post()
+            .uri(route)
+            .set_payload(document)
+            .insert_header(("content-type", "application/json"))
+            .to_request();
+        let res = test::call_service(&app, req).await;
+        let status_code = res.status();
+        assert_ne!(status_code, 415,
+        "calling the route `{}` with a content-type of json isn't supposed to throw a bad media type error", route);
+
+        // No content-type.
+        let req = test::TestRequest::post()
+            .uri(route)
+            .set_payload(document)
+            .to_request();
+        let res = test::call_service(&app, req).await;
+        let status_code = res.status();
+        let body = test::read_body(res).await;
+        let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+        assert_eq!(status_code, 415, "calling the route `{}` without content-type is supposed to throw a bad media type error", route);
+        assert_eq!(
+            response,
+            json!({
+                    "message": r#"A Content-Type header is missing. Accepted values for the Content-Type header are: `application/json`"#,
+                    "code": "missing_content_type",
+                    "type": "invalid_request",
+                    "link": "https://docs.meilisearch.com/errors#missing_content_type",
+            }),
+            "when calling the route `{}` with no content-type",
+            route,
+        );
+
+        for bad_content_type in bad_content_types {
+            // Always bad content-type
+            let req = test::TestRequest::post()
+                .uri(route)
+                .set_payload(document.to_string())
+                .insert_header(("content-type", bad_content_type))
+                .to_request();
+            let res = test::call_service(&app, req).await;
+            let status_code = res.status();
+            let body = test::read_body(res).await;
+            let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+            assert_eq!(status_code, 415);
+            let expected_error_message = format!(
+                r#"The Content-Type `{}` is invalid. Accepted values for the Content-Type header are: `application/json`"#,
+                bad_content_type
+            );
+            assert_eq!(
+                response,
+                json!({
+                        "message": expected_error_message,
+                        "code": "invalid_content_type",
+                        "type": "invalid_request",
+                        "link": "https://docs.meilisearch.com/errors#invalid_content_type",
+                }),
+                "when calling the route `{}` with a content-type of `{}`",
+                route,
+                bad_content_type,
+            );
+        }
+    }
+}
+
+#[actix_rt::test]
+async fn extract_actual_content_type() {
+    let route = "/indexes/doggo/documents";
+    let documents = "[{}]";
+    let server = Server::new().await;
+    let app = test::init_service(create_app!(
+        &server.service.meilisearch,
+        &server.service.auth,
+        true,
+        &server.service.options,
+        analytics::MockAnalytics::new(&server.service.options).0
+    ))
+    .await;
+
+    // Good content-type, we probably have an error since we didn't send anything in the json
+    // so we only ensure we didn't get a bad media type error.
+    let req = test::TestRequest::post()
+        .uri(route)
+        .set_payload(documents)
+        .insert_header(("content-type", "application/json; charset=utf-8"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    assert_ne!(status_code, 415,
+    "calling the route `{}` with a content-type of json isn't supposed to throw a bad media type error", route);
+
+    let req = test::TestRequest::put()
+        .uri(route)
+        .set_payload(documents)
+        .insert_header(("content-type", "application/json; charset=latin-1"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let status_code = res.status();
+    assert_ne!(status_code, 415,
+    "calling the route `{}` with a content-type of json isn't supposed to throw a bad media type error", route);
+}

meilisearch-http/tests/dashboard/mod.rs

@@ -0,0 +1,24 @@
+use crate::common::Server;
+
+#[actix_rt::test]
+async fn dashboard_assets_load() {
+    let server = Server::new().await;
+
+    mod generated {
+        include!(concat!(env!("OUT_DIR"), "/generated.rs"));
+    }
+
+    let generated = generated::generate();
+
+    for (path, _) in generated.into_iter() {
+        let path = if path == "index.html" {
+            // "index.html" redirects to "/"
+            "/".to_owned()
+        } else {
+            "/".to_owned() + path
+        };
+
+        let (_, status_code) = server.service.get(&path).await;
+        assert_eq!(status_code, 200);
+    }
+}

meilisearch-http/tests/documents/delete_documents.rs

@@ -5,8 +5,13 @@ use crate::common::{GetAllDocumentsOptions, Server};
 #[actix_rt::test]
 async fn delete_one_document_unexisting_index() {
     let server = Server::new().await;
-    let (_response, code) = server.index("test").delete_document(0).await;
-    assert_eq!(code, 404);
+    let index = server.index("test");
+    let (_response, code) = index.delete_document(0).await;
+    assert_eq!(code, 202);
+
+    let response = index.wait_task(0).await;
+
+    assert_eq!(response["status"], "failed");
 }
 
 #[actix_rt::test]
@@ -16,8 +21,8 @@ async fn delete_one_unexisting_document() {
     index.create(None).await;
     let (response, code) = index.delete_document(0).await;
     assert_eq!(code, 202, "{}", response);
-    let update = index.wait_update_id(0).await;
-    assert_eq!(update["status"], "processed");
+    let update = index.wait_task(0).await;
+    assert_eq!(update["status"], "succeeded");
 }
 
 #[actix_rt::test]
@@ -27,10 +32,10 @@ async fn delete_one_document() {
     index
         .add_documents(json!([{ "id": 0, "content": "foobar" }]), None)
         .await;
-    index.wait_update_id(0).await;
+    index.wait_task(0).await;
     let (_response, code) = server.index("test").delete_document(0).await;
     assert_eq!(code, 202);
-    index.wait_update_id(1).await;
+    index.wait_task(1).await;
 
     let (_response, code) = index.get_document(0, None).await;
     assert_eq!(code, 404);
@@ -39,8 +44,13 @@ async fn delete_one_document() {
 #[actix_rt::test]
 async fn clear_all_documents_unexisting_index() {
     let server = Server::new().await;
-    let (_response, code) = server.index("test").clear_all_documents().await;
-    assert_eq!(code, 404);
+    let index = server.index("test");
+    let (_response, code) = index.clear_all_documents().await;
+    assert_eq!(code, 202);
+
+    let response = index.wait_task(0).await;
+
+    assert_eq!(response["status"], "failed");
 }
 
 #[actix_rt::test]
@@ -53,11 +63,11 @@ async fn clear_all_documents() {
             None,
         )
         .await;
-    index.wait_update_id(0).await;
+    index.wait_task(0).await;
     let (_response, code) = index.clear_all_documents().await;
     assert_eq!(code, 202);
 
-    let _update = index.wait_update_id(1).await;
+    let _update = index.wait_task(1).await;
     let (response, code) = index
         .get_all_documents(GetAllDocumentsOptions::default())
         .await;
@@ -74,7 +84,7 @@ async fn clear_all_documents_empty_index() {
     let (_response, code) = index.clear_all_documents().await;
     assert_eq!(code, 202);
 
-    let _update = index.wait_update_id(0).await;
+    let _update = index.wait_task(0).await;
     let (response, code) = index
         .get_all_documents(GetAllDocumentsOptions::default())
         .await;
@@ -83,10 +93,22 @@ async fn clear_all_documents_empty_index() {
 }
 
 #[actix_rt::test]
-async fn delete_batch_unexisting_index() {
+async fn error_delete_batch_unexisting_index() {
     let server = Server::new().await;
-    let (response, code) = server.index("test").delete_batch(vec![]).await;
-    assert_eq!(code, 404, "{}", response);
+    let index = server.index("test");
+    let (_, code) = index.delete_batch(vec![]).await;
+    let expected_response = json!({
+        "message": "Index `test` not found.",
+        "code": "index_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#index_not_found"
+    });
+    assert_eq!(code, 202);
+
+    let response = index.wait_task(0).await;
+
+    assert_eq!(response["status"], "failed");
+    assert_eq!(response["error"], expected_response);
 }
 
 #[actix_rt::test]
@@ -94,11 +116,11 @@ async fn delete_batch() {
     let server = Server::new().await;
     let index = server.index("test");
     index.add_documents(json!([{ "id": 1, "content": "foobar" }, { "id": 0, "content": "foobar" }, { "id": 3, "content": "foobar" }]), Some("id")).await;
-    index.wait_update_id(0).await;
+    index.wait_task(0).await;
     let (_response, code) = index.delete_batch(vec![1, 0]).await;
     assert_eq!(code, 202);
 
-    let _update = index.wait_update_id(1).await;
+    let _update = index.wait_task(1).await;
     let (response, code) = index
         .get_all_documents(GetAllDocumentsOptions::default())
         .await;
@@ -112,11 +134,11 @@ async fn delete_no_document_batch() {
     let server = Server::new().await;
     let index = server.index("test");
     index.add_documents(json!([{ "id": 1, "content": "foobar" }, { "id": 0, "content": "foobar" }, { "id": 3, "content": "foobar" }]), Some("id")).await;
-    index.wait_update_id(0).await;
+    index.wait_task(0).await;
     let (_response, code) = index.delete_batch(vec![]).await;
     assert_eq!(code, 202, "{}", _response);
 
-    let _update = index.wait_update_id(1).await;
+    let _update = index.wait_task(1).await;
     let (response, code) = index
         .get_all_documents(GetAllDocumentsOptions::default())
         .await;

meilisearch-http/tests/documents/get_documents.rs

@@ -13,11 +13,21 @@ async fn get_unexisting_index_single_document() {
 }
 
 #[actix_rt::test]
-async fn get_unexisting_document() {
+async fn error_get_unexisting_document() {
     let server = Server::new().await;
     let index = server.index("test");
     index.create(None).await;
-    let (_response, code) = index.get_document(1, None).await;
+    index.wait_task(0).await;
+    let (response, code) = index.get_document(1, None).await;
+
+    let expected_response = json!({
+        "message": "Document `1` not found.",
+        "code": "document_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#document_not_found"
+    });
+
+    assert_eq!(response, expected_response);
     assert_eq!(code, 404);
 }
 
@@ -34,7 +44,7 @@ async fn get_document() {
     ]);
     let (_, code) = index.add_documents(documents, None).await;
     assert_eq!(code, 202);
-    index.wait_update_id(0).await;
+    index.wait_task(0).await;
     let (response, code) = index.get_document(0, None).await;
     assert_eq!(code, 200);
     assert_eq!(
@@ -47,21 +57,32 @@ async fn get_document() {
 }
 
 #[actix_rt::test]
-async fn get_unexisting_index_all_documents() {
+async fn error_get_unexisting_index_all_documents() {
     let server = Server::new().await;
-    let (_response, code) = server
+    let (response, code) = server
         .index("test")
         .get_all_documents(GetAllDocumentsOptions::default())
         .await;
+
+    let expected_response = json!({
+        "message": "Index `test` not found.",
+        "code": "index_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#index_not_found"
+    });
+
+    assert_eq!(response, expected_response);
     assert_eq!(code, 404);
 }
 
 #[actix_rt::test]
-async fn get_no_documents() {
+async fn get_no_document() {
     let server = Server::new().await;
     let index = server.index("test");
     let (_, code) = index.create(None).await;
-    assert_eq!(code, 201);
+    assert_eq!(code, 202);
+
+    index.wait_task(0).await;
 
     let (response, code) = index
         .get_all_documents(GetAllDocumentsOptions::default())

meilisearch-http/tests/dumps.rs

@@ -0,0 +1,22 @@
+#![allow(dead_code)]
+mod common;
+
+use crate::common::Server;
+use serde_json::json;
+
+#[actix_rt::test]
+async fn get_unexisting_dump_status() {
+    let server = Server::new().await;
+
+    let (response, code) = server.get_dump_status("foobar").await;
+    assert_eq!(code, 404);
+
+    let expected_response = json!({
+    "message": "Dump `foobar` not found.",
+    "code": "dump_not_found",
+    "type": "invalid_request",
+    "link": "https://docs.meilisearch.com/errors#dump_not_found"
+    });
+
+    assert_eq!(response, expected_response);
+}

meilisearch-http/tests/index/create_index.rs

@@ -1,5 +1,5 @@
 use crate::common::Server;
-use serde_json::Value;
+use serde_json::{json, Value};
 
 #[actix_rt::test]
 async fn create_index_no_primary_key() {
@@ -7,14 +7,15 @@ async fn create_index_no_primary_key() {
     let index = server.index("test");
     let (response, code) = index.create(None).await;
 
-    assert_eq!(code, 201);
-    assert_eq!(response["uid"], "test");
-    assert_eq!(response["name"], "test");
-    assert!(response.get("createdAt").is_some());
-    assert!(response.get("updatedAt").is_some());
-    assert_eq!(response["createdAt"], response["updatedAt"]);
-    assert_eq!(response["primaryKey"], Value::Null);
-    assert_eq!(response.as_object().unwrap().len(), 5);
+    assert_eq!(code, 202);
+
+    assert_eq!(response["status"], "enqueued");
+
+    let response = index.wait_task(0).await;
+
+    assert_eq!(response["status"], "succeeded");
+    assert_eq!(response["type"], "indexCreation");
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -23,36 +24,31 @@ async fn create_index_with_primary_key() {
     let index = server.index("test");
     let (response, code) = index.create(Some("primary")).await;
 
-    assert_eq!(code, 201);
-    assert_eq!(response["uid"], "test");
-    assert_eq!(response["name"], "test");
-    assert!(response.get("createdAt").is_some());
-    assert!(response.get("updatedAt").is_some());
-    //assert_eq!(response["createdAt"], response["updatedAt"]);
-    assert_eq!(response["primaryKey"], "primary");
-    assert_eq!(response.as_object().unwrap().len(), 5);
-}
+    assert_eq!(code, 202);
 
-// TODO: partial test since we are testing error, amd error is not yet fully implemented in
-// transplant
-#[actix_rt::test]
-async fn create_existing_index() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let (_, code) = index.create(Some("primary")).await;
+    assert_eq!(response["status"], "enqueued");
 
-    assert_eq!(code, 201);
+    let response = index.wait_task(0).await;
 
-    let (_response, code) = index.create(Some("primary")).await;
-    assert_eq!(code, 400);
+    assert_eq!(response["status"], "succeeded");
+    assert_eq!(response["type"], "indexCreation");
+    assert_eq!(response["details"]["primaryKey"], "primary");
 }
 
 #[actix_rt::test]
-async fn create_with_invalid_index_uid() {
+async fn create_index_with_invalid_primary_key() {
+    let document = json!([ { "id": 2, "title": "Pride and Prejudice" } ]);
+
     let server = Server::new().await;
-    let index = server.index("test test#!");
-    let (_, code) = index.create(None).await;
-    assert_eq!(code, 400);
+    let index = server.index("movies");
+    let (_response, code) = index.add_documents(document, Some("title")).await;
+    assert_eq!(code, 202);
+
+    index.wait_task(0).await;
+
+    let (response, code) = index.get().await;
+    assert_eq!(code, 200);
+    assert_eq!(response["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -67,8 +63,51 @@ async fn test_create_multiple_indexes() {
     index2.create(None).await;
     index3.create(None).await;
 
+    index1.wait_task(0).await;
+    index1.wait_task(1).await;
+    index1.wait_task(2).await;
+
     assert_eq!(index1.get().await.1, 200);
     assert_eq!(index2.get().await.1, 200);
     assert_eq!(index3.get().await.1, 200);
     assert_eq!(index4.get().await.1, 404);
 }
+
+#[actix_rt::test]
+async fn error_create_existing_index() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    let (_, code) = index.create(Some("primary")).await;
+
+    assert_eq!(code, 202);
+
+    index.create(Some("primary")).await;
+
+    let response = index.wait_task(1).await;
+
+    let expected_response = json!({
+        "message": "Index `test` already exists.",
+        "code": "index_already_exists",
+        "type": "invalid_request",
+        "link":"https://docs.meilisearch.com/errors#index_already_exists"
+    });
+
+    assert_eq!(response["error"], expected_response);
+}
+
+#[actix_rt::test]
+async fn error_create_with_invalid_index_uid() {
+    let server = Server::new().await;
+    let index = server.index("test test#!");
+    let (response, code) = index.create(None).await;
+
+    let expected_response = json!({
+        "message": "`test test#!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+        "code": "invalid_index_uid",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
+    });
+
+    assert_eq!(response, expected_response);
+    assert_eq!(code, 400);
+}

meilisearch-http/tests/index/delete_index.rs

@@ -8,33 +8,59 @@ async fn create_and_delete_index() {
     let index = server.index("test");
     let (_response, code) = index.create(None).await;
 
-    assert_eq!(code, 201);
+    assert_eq!(code, 202);
+
+    index.wait_task(0).await;
+
+    assert_eq!(index.get().await.1, 200);
 
     let (_response, code) = index.delete().await;
 
-    assert_eq!(code, 204);
+    assert_eq!(code, 202);
+
+    index.wait_task(1).await;
 
     assert_eq!(index.get().await.1, 404);
 }
 
 #[actix_rt::test]
-async fn delete_unexisting_index() {
+async fn error_delete_unexisting_index() {
     let server = Server::new().await;
     let index = server.index("test");
-    let (_response, code) = index.delete().await;
+    let (_, code) = index.delete().await;
 
-    assert_eq!(code, 404);
+    assert_eq!(code, 202);
+
+    let expected_response = json!({
+        "message": "Index `test` not found.",
+        "code": "index_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#index_not_found"
+    });
+
+    let response = index.wait_task(0).await;
+    assert_eq!(response["status"], "failed");
+    assert_eq!(response["error"], expected_response);
 }
 
+#[cfg(not(windows))]
 #[actix_rt::test]
 async fn loop_delete_add_documents() {
     let server = Server::new().await;
     let index = server.index("test");
     let documents = json!([{"id": 1, "field1": "hello"}]);
+    let mut tasks = Vec::new();
     for _ in 0..50 {
         let (response, code) = index.add_documents(documents.clone(), None).await;
+        tasks.push(response["uid"].as_u64().unwrap());
         assert_eq!(code, 202, "{}", response);
         let (response, code) = index.delete().await;
-        assert_eq!(code, 204, "{}", response);
+        tasks.push(response["uid"].as_u64().unwrap());
+        assert_eq!(code, 202, "{}", response);
+    }
+
+    for task in tasks {
+        let response = index.wait_task(task).await;
+        assert_eq!(response["status"], "succeeded", "{}", response);
     }
 }