Compare commits

..

11 Commits

Author SHA1 Message Date
Clément Renault
af2b722fed Make the CI happy about the never type 2024-09-16 11:40:26 +02:00
Clément Renault
8cb7001755 Expose an experimental parameter to control the generation of prefix dbs 2024-09-16 10:57:52 +02:00
meili-bors[bot]
882663bf7f Merge #4891
4891: Update version for the next release (v1.9.1) in Cargo.toml r=dureuill a=meili-bot

⚠️ This PR is automatically generated. Check the new version is the expected one and Cargo.lock has been updated before merging.

Co-authored-by: dureuill <dureuill@users.noreply.github.com>
2024-08-27 16:04:18 +00:00
dureuill
3234f63c00 Update version for the next release (v1.9.1) in Cargo.toml 2024-08-27 16:02:43 +00:00
meili-bors[bot]
9fff081043 Merge #4889
4889: When `retrieveVectors` is true, retrieve `_vectors.embedder` even if … r=Kerollmops a=dureuill

…there are no vector for that embedder


backports a bug fix from v1.10.0: 82647bcded

Co-authored-by: Louis Dureuil <louis@meilisearch.com>
2024-08-27 15:14:58 +00:00
Louis Dureuil
575b7b7a0b Fix tests 2024-08-27 17:14:10 +02:00
Louis Dureuil
6287f5b204 Remove unexecuted test 2024-08-27 16:54:33 +02:00
Louis Dureuil
5dac8e7168 Allow fuzzing cfg 2024-08-27 16:43:44 +02:00
Louis Dureuil
e669af1e49 CI: Add ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION workaround to keep using Ubuntu 18.04 2024-08-27 16:29:45 +02:00
Louis Dureuil
0e0e29459c Update time 2024-08-27 16:27:05 +02:00
Louis Dureuil
c25f7e3450 When retrieveVectors is true, retrieve _vectors.embedder even if there are no vector for that embedder 2024-08-27 16:26:41 +02:00
261 changed files with 3626 additions and 20879 deletions

View File

@@ -18,9 +18,11 @@ jobs:
timeout-minutes: 180 # 3h timeout-minutes: 180 # 3h
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
- name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }} - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
run: | run: |

View File

@@ -16,37 +16,6 @@ jobs:
runs-on: benchmarks runs-on: benchmarks
timeout-minutes: 180 # 3h timeout-minutes: 180 # 3h
steps: steps:
- name: Check permissions
id: permission
env:
PR_AUTHOR: ${{github.event.issue.user.login }}
COMMENT_AUTHOR: ${{github.event.comment.user.login }}
REPOSITORY: ${{github.repository}}
PR_ID: ${{github.event.issue.number}}
run: |
PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
then
echo "::notice title=Authentication success::PR author authenticated"
else
echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
exit 1
fi
if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
then
echo "::notice title=Authentication success::Comment author authenticated"
else
echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
exit 1
fi
if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
then
echo "::notice title=Authentication success::PR started from main repository"
else
echo "::error title=Authentication error::PR started from a fork"
exit 1
fi
- name: Check for Command - name: Check for Command
id: command id: command
uses: xt0rted/slash-command-action@v2 uses: xt0rted/slash-command-action@v2
@@ -66,9 +35,11 @@ jobs:
fetch-depth: 0 # fetch full history to be able to get main commit sha fetch-depth: 0 # fetch full history to be able to get main commit sha
ref: ${{ steps.comment-branch.outputs.head_ref }} ref: ${{ steps.comment-branch.outputs.head_ref }}
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
- name: Run benchmarks on PR ${{ github.event.issue.id }} - name: Run benchmarks on PR ${{ github.event.issue.id }}
run: | run: |

View File

@@ -12,9 +12,11 @@ jobs:
timeout-minutes: 180 # 3h timeout-minutes: 180 # 3h
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Run benchmarks # Run benchmarks
- name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }} - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}

View File

@@ -18,9 +18,11 @@ jobs:
timeout-minutes: 4320 # 72h timeout-minutes: 4320 # 72h
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Set variables # Set variables
- name: Set current branch name - name: Set current branch name

View File

@@ -13,40 +13,11 @@ jobs:
runs-on: benchmarks runs-on: benchmarks
timeout-minutes: 4320 # 72h timeout-minutes: 4320 # 72h
steps: steps:
- name: Check permissions - uses: actions-rs/toolchain@v1
id: permission
env:
PR_AUTHOR: ${{github.event.issue.user.login }}
COMMENT_AUTHOR: ${{github.event.comment.user.login }}
REPOSITORY: ${{github.repository}}
PR_ID: ${{github.event.issue.number}}
run: |
PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
then
echo "::notice title=Authentication success::PR author authenticated"
else
echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
exit 1
fi
if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
then
echo "::notice title=Authentication success::Comment author authenticated"
else
echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
exit 1
fi
if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
then
echo "::notice title=Authentication success::PR started from main repository"
else
echo "::error title=Authentication error::PR started from a fork"
exit 1
fi
- uses: dtolnay/rust-toolchain@1.79
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
- name: Check for Command - name: Check for Command
id: command id: command

View File

@@ -16,9 +16,11 @@ jobs:
timeout-minutes: 4320 # 72h timeout-minutes: 4320 # 72h
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Set variables # Set variables
- name: Set current branch name - name: Set current branch name

View File

@@ -15,9 +15,11 @@ jobs:
runs-on: benchmarks runs-on: benchmarks
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Set variables # Set variables
- name: Set current branch name - name: Set current branch name

View File

@@ -15,9 +15,11 @@ jobs:
runs-on: benchmarks runs-on: benchmarks
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Set variables # Set variables
- name: Set current branch name - name: Set current branch name

View File

@@ -15,9 +15,11 @@ jobs:
runs-on: benchmarks runs-on: benchmarks
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Set variables # Set variables
- name: Set current branch name - name: Set current branch name

View File

@@ -1,5 +1,6 @@
name: Look for flaky tests name: Look for flaky tests
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
on: on:
workflow_dispatch: workflow_dispatch:
schedule: schedule:
@@ -9,15 +10,18 @@ jobs:
flaky: flaky:
runs-on: ubuntu-latest runs-on: ubuntu-latest
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
image: ubuntu:20.04 image: ubuntu:18.04
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- name: Install needed dependencies - name: Install needed dependencies
run: | run: |
apt-get update && apt-get install -y curl apt-get update && apt-get install -y curl
apt-get install build-essential -y apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Install cargo-flaky - name: Install cargo-flaky
run: cargo install cargo-flaky run: cargo install cargo-flaky
- name: Run cargo flaky in the dumps - name: Run cargo flaky in the dumps

View File

@@ -1,5 +1,6 @@
name: Run the indexing fuzzer name: Run the indexing fuzzer
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
on: on:
push: push:
branches: branches:
@@ -12,9 +13,11 @@ jobs:
timeout-minutes: 4320 # 72h timeout-minutes: 4320 # 72h
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
# Run benchmarks # Run benchmarks
- name: Run the fuzzer - name: Run the fuzzer

View File

@@ -15,17 +15,22 @@ jobs:
debian: debian:
name: Publish debian packagge name: Publish debian packagge
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
runs-on: ubuntu-latest runs-on: ubuntu-latest
needs: check-version needs: check-version
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27
image: ubuntu:20.04 image: ubuntu:18.04
steps: steps:
- name: Install needed dependencies - name: Install needed dependencies
run: | run: |
apt-get update && apt-get install -y curl apt-get update && apt-get install -y curl
apt-get install build-essential -y apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Install cargo-deb - name: Install cargo-deb
run: cargo install cargo-deb run: cargo install cargo-deb
- uses: actions/checkout@v3 - uses: actions/checkout@v3

View File

@@ -35,17 +35,22 @@ jobs:
publish-linux: publish-linux:
name: Publish binary for Linux name: Publish binary for Linux
runs-on: ubuntu-latest runs-on: ubuntu-latest
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
needs: check-version needs: check-version
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27
image: ubuntu:20.04 image: ubuntu:18.04
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- name: Install needed dependencies - name: Install needed dependencies
run: | run: |
apt-get update && apt-get install -y curl apt-get update && apt-get install -y curl
apt-get install build-essential -y apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Build - name: Build
run: cargo build --release --locked run: cargo build --release --locked
# No need to upload binaries for dry run (cron) # No need to upload binaries for dry run (cron)
@@ -75,7 +80,10 @@ jobs:
asset_name: meilisearch-windows-amd64.exe asset_name: meilisearch-windows-amd64.exe
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Build - name: Build
run: cargo build --release --locked run: cargo build --release --locked
# No need to upload binaries for dry run (cron) # No need to upload binaries for dry run (cron)
@@ -101,10 +109,12 @@ jobs:
- name: Checkout repository - name: Checkout repository
uses: actions/checkout@v3 uses: actions/checkout@v3
- name: Installing Rust toolchain - name: Installing Rust toolchain
uses: dtolnay/rust-toolchain@1.79 uses: actions-rs/toolchain@v1
with: with:
toolchain: stable
profile: minimal profile: minimal
target: ${{ matrix.target }} target: ${{ matrix.target }}
override: true
- name: Cargo build - name: Cargo build
uses: actions-rs/cargo@v1 uses: actions-rs/cargo@v1
with: with:
@@ -125,10 +135,10 @@ jobs:
runs-on: ubuntu-latest runs-on: ubuntu-latest
needs: check-version needs: check-version
env: env:
DEBIAN_FRONTEND: noninteractive ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27
image: ubuntu:20.04 image: ubuntu:18.04
strategy: strategy:
matrix: matrix:
include: include:
@@ -148,10 +158,12 @@ jobs:
add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
apt-get update -y && apt-get install -y docker-ce apt-get update -y && apt-get install -y docker-ce
- name: Installing Rust toolchain - name: Installing Rust toolchain
uses: dtolnay/rust-toolchain@1.79 uses: actions-rs/toolchain@v1
with: with:
toolchain: stable
profile: minimal profile: minimal
target: ${{ matrix.target }} target: ${{ matrix.target }}
override: true
- name: Configure target aarch64 GNU - name: Configure target aarch64 GNU
## Environment variable is not passed using env: ## Environment variable is not passed using env:
## LD gold won't work with MUSL ## LD gold won't work with MUSL
@@ -162,9 +174,6 @@ jobs:
echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config
echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config
echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV
- name: Install a default toolchain that will be used to build cargo cross
run: |
rustup default stable
- name: Cargo build - name: Cargo build
uses: actions-rs/cargo@v1 uses: actions-rs/cargo@v1
with: with:

View File

@@ -80,11 +80,10 @@ jobs:
type=ref,event=tag type=ref,event=tag
type=raw,value=nightly,enable=${{ github.event_name != 'push' }} type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }} type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
type=semver,pattern=v{{major}},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' }} type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
- name: Build and push - name: Build and push
uses: docker/build-push-action@v6 uses: docker/build-push-action@v5
with: with:
push: true push: true
platforms: linux/amd64,linux/arm64 platforms: linux/amd64,linux/arm64

View File

@@ -19,11 +19,13 @@ env:
jobs: jobs:
test-linux: test-linux:
name: Tests on ubuntu-20.04 name: Tests on ubuntu-18.04
runs-on: ubuntu-latest runs-on: ubuntu-latest
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
image: ubuntu:20.04 image: ubuntu:18.04
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- name: Install needed dependencies - name: Install needed dependencies
@@ -31,7 +33,10 @@ jobs:
apt-get update && apt-get install -y curl apt-get update && apt-get install -y curl
apt-get install build-essential -y apt-get install build-essential -y
- name: Setup test with Rust stable - name: Setup test with Rust stable
uses: dtolnay/rust-toolchain@1.79 uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Cache dependencies - name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1 uses: Swatinem/rust-cache@v2.7.1
- name: Run cargo check without any default features - name: Run cargo check without any default features
@@ -56,7 +61,10 @@ jobs:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- name: Cache dependencies - name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1 uses: Swatinem/rust-cache@v2.7.1
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Run cargo check without any default features - name: Run cargo check without any default features
uses: actions-rs/cargo@v1 uses: actions-rs/cargo@v1
with: with:
@@ -71,9 +79,11 @@ jobs:
test-all-features: test-all-features:
name: Tests almost all features name: Tests almost all features
runs-on: ubuntu-latest runs-on: ubuntu-latest
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
image: ubuntu:20.04 image: ubuntu:18.04
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
@@ -81,7 +91,10 @@ jobs:
run: | run: |
apt-get update apt-get update
apt-get install --assume-yes build-essential curl apt-get install --assume-yes build-essential curl
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Run cargo build with almost all features - name: Run cargo build with almost all features
run: | run: |
cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)" cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
@@ -91,9 +104,11 @@ jobs:
test-disabled-tokenization: test-disabled-tokenization:
name: Test disabled tokenization name: Test disabled tokenization
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
runs-on: ubuntu-latest runs-on: ubuntu-latest
container: container:
image: ubuntu:20.04 image: ubuntu:18.04
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
@@ -101,7 +116,10 @@ jobs:
run: | run: |
apt-get update apt-get update
apt-get install --assume-yes build-essential curl apt-get install --assume-yes build-essential curl
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Run cargo tree without default features and check lindera is not present - name: Run cargo tree without default features and check lindera is not present
run: | run: |
if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
@@ -115,17 +133,22 @@ jobs:
# We run tests in debug also, to make sure that the debug_assertions are hit # We run tests in debug also, to make sure that the debug_assertions are hit
test-debug: test-debug:
name: Run tests in debug name: Run tests in debug
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
runs-on: ubuntu-latest runs-on: ubuntu-latest
container: container:
# Use ubuntu-20.04 to compile with glibc 2.28 # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
image: ubuntu:20.04 image: ubuntu:18.04
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- name: Install needed dependencies - name: Install needed dependencies
run: | run: |
apt-get update && apt-get install -y curl apt-get update && apt-get install -y curl
apt-get install build-essential -y apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Cache dependencies - name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1 uses: Swatinem/rust-cache@v2.7.1
- name: Run tests in debug - name: Run tests in debug
@@ -139,9 +162,11 @@ jobs:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: 1.75.0
override: true
components: clippy components: clippy
- name: Cache dependencies - name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1 uses: Swatinem/rust-cache@v2.7.1
@@ -156,10 +181,10 @@ jobs:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: nightly-2024-07-09 toolchain: nightly
override: true override: true
components: rustfmt components: rustfmt
- name: Cache dependencies - name: Cache dependencies

View File

@@ -18,9 +18,11 @@ jobs:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79 - uses: actions-rs/toolchain@v1
with: with:
profile: minimal profile: minimal
toolchain: stable
override: true
- name: Install sd - name: Install sd
run: cargo install sd run: cargo install sd
- name: Update Cargo.toml file - name: Update Cargo.toml file

View File

@@ -109,12 +109,6 @@ They are JSON files with the following structure (comments are not actually supp
"run_count": 3, "run_count": 3,
// List of arguments to add to the Meilisearch command line. // List of arguments to add to the Meilisearch command line.
"extra_cli_args": ["--max-indexing-threads=1"], "extra_cli_args": ["--max-indexing-threads=1"],
// An expression that can be parsed as a comma-separated list of targets and levels
// as described in [tracing_subscriber's documentation](https://docs.rs/tracing-subscriber/latest/tracing_subscriber/filter/targets/struct.Targets.html#examples).
// The expression is used to filter the spans that are measured for profiling purposes.
// Optional, defaults to "indexing::=trace" (for indexing workloads), common other values is
// "search::=trace"
"target": "indexing::=trace",
// List of named assets that can be used in the commands. // List of named assets that can be used in the commands.
"assets": { "assets": {
// name of the asset. // name of the asset.

View File

@@ -52,20 +52,6 @@ cargo test
This command will be triggered to each PR as a requirement for merging it. This command will be triggered to each PR as a requirement for merging it.
#### Faster build
You can set the `LINDERA_CACHE` environment variable to speed up your successive builds by up to 2 minutes.
It'll store some built artifacts in the directory of your choice.
We recommend using the standard `$HOME/.cache/lindera` directory:
```sh
export LINDERA_CACHE=$HOME/.cache/lindera
```
Furthermore, you can improve incremental compilation by setting the `MEILI_NO_VERGEN` environment variable.
Setting this variable will prevent the Meilisearch binary from being rebuilt each time the directory that hosts the Meilisearch repository changes.
Do not enable this environment variable for production builds (as it will break the `version` route, among other things).
#### Snapshot-based tests #### Snapshot-based tests
We are using [insta](https://insta.rs) to perform snapshot-based testing. We are using [insta](https://insta.rs) to perform snapshot-based testing.
@@ -77,7 +63,7 @@ Furthermore, we provide some macros on top of insta, notably a way to use snapsh
To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally: To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally:
```sh ```
export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ... export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ...
``` ```

1733
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -22,7 +22,7 @@ members = [
] ]
[workspace.package] [workspace.package]
version = "1.10.3" version = "1.9.1"
authors = [ authors = [
"Quentin de Quelen <quentin@dequelen.me>", "Quentin de Quelen <quentin@dequelen.me>",
"Clément Renault <clement@meilisearch.com>", "Clément Renault <clement@meilisearch.com>",

View File

@@ -1,7 +1,7 @@
# Compile # Compile
FROM rust:1.79.0-alpine3.20 AS compiler FROM rust:1.75.0-alpine3.18 AS compiler
RUN apk add -q --no-cache build-base openssl-dev RUN apk add -q --update-cache --no-cache build-base openssl-dev
WORKDIR / WORKDIR /
@@ -20,12 +20,13 @@ RUN set -eux; \
cargo build --release -p meilisearch -p meilitool cargo build --release -p meilisearch -p meilitool
# Run # Run
FROM alpine:3.20 FROM alpine:3.16
ENV MEILI_HTTP_ADDR 0.0.0.0:7700 ENV MEILI_HTTP_ADDR 0.0.0.0:7700
ENV MEILI_SERVER_PROVIDER docker ENV MEILI_SERVER_PROVIDER docker
RUN apk add -q --no-cache libgcc tini curl RUN apk update --quiet \
&& apk add -q --no-cache libgcc tini curl
# add meilisearch and meilitool to the `/bin` so you can run it from anywhere # add meilisearch and meilitool to the `/bin` so you can run it from anywhere
# and it's easy to find. # and it's easy to find.

View File

@@ -1,6 +1,9 @@
<p align="center"> <p align="center">
<a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo" target="_blank"> <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-light-mode-only" target="_blank">
<img src="assets/meilisearch-logo-kawaii.png"> <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
</a>
<a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-dark-mode-only" target="_blank">
<img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
</a> </a>
</p> </p>
@@ -22,7 +25,7 @@
<p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p> <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
[Meilisearch](https://www.meilisearch.com?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=intro) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow. [Meilisearch](https://www.meilisearch.com) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
<p align="center" name="demo"> <p align="center" name="demo">
<a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank"> <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
@@ -33,18 +36,11 @@
</a> </a>
</p> </p>
## 🖥 Examples 🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
- [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
- [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
- [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
See the list of all our example apps in our [demos repository](https://github.com/meilisearch/demos).
## ✨ Features ## ✨ Features
- **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) & full-text search to get the most relevant results - **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search) & full-text search to get the most relevant results
- **Search-as-you-type:** Find & display results in less than 50 milliseconds to provide an intuitive experience - **Search-as-you-type:** find & display results in less than 50 milliseconds to provide an intuitive experience
- **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings - **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code - **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need - **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
@@ -63,7 +59,7 @@ You can consult Meilisearch's documentation at [meilisearch.com/docs](https://ww
## 🚀 Getting started ## 🚀 Getting started
For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [documentation](https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide. For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
## 🌍 Supercharge your Meilisearch experience ## 🌍 Supercharge your Meilisearch experience
@@ -87,7 +83,7 @@ Finally, for more in-depth information, refer to our articles explaining fundame
## 📊 Telemetry ## 📊 Telemetry
Meilisearch collects **anonymized** user data to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want. Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data. To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
@@ -109,11 +105,11 @@ Thank you for your support!
## 👩‍💻 Contributing ## 👩‍💻 Contributing
Meilisearch is, and will always be, open-source! If you want to contribute to the project, please look at [our contribution guidelines](CONTRIBUTING.md). Meilisearch is, and will always be, open-source! If you want to contribute to the project, please take a look at [our contribution guidelines](CONTRIBUTING.md).
## 📦 Versioning ## 📦 Versioning
Meilisearch releases and their associated binaries are available on the project's [releases page](https://github.com/meilisearch/meilisearch/releases). Meilisearch releases and their associated binaries are available [in this GitHub page](https://github.com/meilisearch/meilisearch/releases).
The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](https://github.com/meilisearch/engine-team/blob/main/resources/versioning-policy.md). The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](https://github.com/meilisearch/engine-team/blob/main/resources/versioning-policy.md).

Binary file not shown.

Before

Width:  |  Height:  |  Size: 98 KiB

View File

@@ -11,24 +11,24 @@ edition.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
anyhow = "1.0.86" anyhow = "1.0.79"
csv = "1.3.0" csv = "1.3.0"
milli = { path = "../milli" } milli = { path = "../milli" }
mimalloc = { version = "0.1.43", default-features = false } mimalloc = { version = "0.1.39", default-features = false }
serde_json = { version = "1.0.120", features = ["preserve_order"] } serde_json = { version = "1.0.111", features = ["preserve_order"] }
[dev-dependencies] [dev-dependencies]
criterion = { version = "0.5.1", features = ["html_reports"] } criterion = { version = "0.5.1", features = ["html_reports"] }
rand = "0.8.5" rand = "0.8.5"
rand_chacha = "0.3.1" rand_chacha = "0.3.1"
roaring = "0.10.6" roaring = "0.10.2"
[build-dependencies] [build-dependencies]
anyhow = "1.0.86" anyhow = "1.0.79"
bytes = "1.6.0" bytes = "1.5.0"
convert_case = "0.6.0" convert_case = "0.6.0"
flate2 = "1.0.30" flate2 = "1.0.28"
reqwest = { version = "0.12.5", features = ["blocking", "rustls-tls"], default-features = false } reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
[features] [features]
default = ["milli/all-tokenizations"] default = ["milli/all-tokenizations"]

View File

@@ -1,5 +1,5 @@
status = [ status = [
'Tests on ubuntu-20.04', 'Tests on ubuntu-18.04',
'Tests on macos-12', 'Tests on macos-12',
'Tests on windows-2022', 'Tests on windows-2022',
'Run Clippy', 'Run Clippy',

View File

@@ -11,8 +11,8 @@ license.workspace = true
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies] [dependencies]
time = { version = "0.3.36", features = ["parsing"] } time = { version = "0.3.34", features = ["parsing"] }
[build-dependencies] [build-dependencies]
anyhow = "1.0.86" anyhow = "1.0.80"
vergen-git2 = "1.0.0" vergen-git2 = "1.0.0-beta.2"

View File

@@ -5,13 +5,6 @@ fn main() {
} }
fn emit_git_variables() -> anyhow::Result<()> { fn emit_git_variables() -> anyhow::Result<()> {
println!("cargo::rerun-if-env-changed=MEILI_NO_VERGEN");
let has_vergen =
!matches!(std::env::var_os("MEILI_NO_VERGEN"), Some(x) if x != "false" && x != "0");
anyhow::ensure!(has_vergen, "disabled via `MEILI_NO_VERGEN`");
// Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
// in the corresponding GitHub workflow (publish_docker.yml). // in the corresponding GitHub workflow (publish_docker.yml).
// This is due to the Dockerfile building the binary outside of the git directory. // This is due to the Dockerfile building the binary outside of the git directory.

View File

@@ -11,21 +11,22 @@ readme.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
anyhow = "1.0.86" anyhow = "1.0.79"
flate2 = "1.0.30" flate2 = "1.0.28"
http = "1.1.0" http = "0.2.11"
meilisearch-auth = { path = "../meilisearch-auth" }
meilisearch-types = { path = "../meilisearch-types" } meilisearch-types = { path = "../meilisearch-types" }
once_cell = "1.19.0" once_cell = "1.19.0"
regex = "1.10.5" regex = "1.10.2"
roaring = { version = "0.10.6", features = ["serde"] } roaring = { version = "0.10.2", features = ["serde"] }
serde = { version = "1.0.204", features = ["derive"] } serde = { version = "1.0.195", features = ["derive"] }
serde_json = { version = "1.0.120", features = ["preserve_order"] } serde_json = { version = "1.0.111", features = ["preserve_order"] }
tar = "0.4.41" tar = "0.4.40"
tempfile = "3.10.1" tempfile = "3.9.0"
thiserror = "1.0.61" thiserror = "1.0.56"
time = { version = "0.3.36", features = ["serde-well-known", "formatting", "parsing", "macros"] } time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
tracing = "0.1.40" tracing = "0.1.40"
uuid = { version = "1.10.0", features = ["serde", "v4"] } uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies] [dev-dependencies]
big_s = "1.0.2" big_s = "1.0.2"

View File

@@ -104,11 +104,6 @@ pub enum KindDump {
DocumentDeletionByFilter { DocumentDeletionByFilter {
filter: serde_json::Value, filter: serde_json::Value,
}, },
DocumentEdition {
filter: Option<serde_json::Value>,
context: Option<serde_json::Map<String, serde_json::Value>>,
function: String,
},
Settings { Settings {
settings: Box<meilisearch_types::settings::Settings<Unchecked>>, settings: Box<meilisearch_types::settings::Settings<Unchecked>>,
is_deletion: bool, is_deletion: bool,
@@ -177,9 +172,6 @@ impl From<KindWithContent> for KindDump {
KindWithContent::DocumentDeletionByFilter { filter_expr, .. } => { KindWithContent::DocumentDeletionByFilter { filter_expr, .. } => {
KindDump::DocumentDeletionByFilter { filter: filter_expr } KindDump::DocumentDeletionByFilter { filter: filter_expr }
} }
KindWithContent::DocumentEdition { filter_expr, context, function, .. } => {
KindDump::DocumentEdition { filter: filter_expr, context, function }
}
KindWithContent::DocumentClear { .. } => KindDump::DocumentClear, KindWithContent::DocumentClear { .. } => KindDump::DocumentClear,
KindWithContent::SettingsUpdate { KindWithContent::SettingsUpdate {
new_settings, new_settings,
@@ -286,7 +278,6 @@ pub(crate) mod test {
pagination: Setting::NotSet, pagination: Setting::NotSet,
embedders: Setting::NotSet, embedders: Setting::NotSet,
search_cutoff_ms: Setting::NotSet, search_cutoff_ms: Setting::NotSet,
localized_attributes: Setting::NotSet,
_kind: std::marker::PhantomData, _kind: std::marker::PhantomData,
}; };
settings.check() settings.check()

View File

@@ -425,7 +425,7 @@ pub(crate) mod test {
let mut dump = v2::V2Reader::open(dir).unwrap().to_v3(); let mut dump = v2::V2Reader::open(dir).unwrap().to_v3();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -358,7 +358,7 @@ pub(crate) mod test {
let mut dump = v3::V3Reader::open(dir).unwrap().to_v4(); let mut dump = v3::V3Reader::open(dir).unwrap().to_v4();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -394,8 +394,8 @@ pub(crate) mod test {
let mut dump = v4::V4Reader::open(dir).unwrap().to_v5(); let mut dump = v4::V4Reader::open(dir).unwrap().to_v5();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d"); insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -379,7 +379,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
v5::Setting::NotSet => v6::Setting::NotSet, v5::Setting::NotSet => v6::Setting::NotSet,
}, },
embedders: v6::Setting::NotSet, embedders: v6::Setting::NotSet,
localized_attributes: v6::Setting::NotSet,
search_cutoff_ms: v6::Setting::NotSet, search_cutoff_ms: v6::Setting::NotSet,
_kind: std::marker::PhantomData, _kind: std::marker::PhantomData,
} }
@@ -443,8 +442,8 @@ pub(crate) mod test {
let mut dump = v5::V5Reader::open(dir).unwrap().to_v6(); let mut dump = v5::V5Reader::open(dir).unwrap().to_v6();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d"); insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks // tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -216,7 +216,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None"); insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
// tasks // tasks
@@ -337,7 +337,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None"); insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
// tasks // tasks
@@ -383,8 +383,8 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d"); insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks // tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
@@ -463,8 +463,8 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d"); insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks // tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
@@ -540,7 +540,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
assert_eq!(dump.instance_uid().unwrap(), None); assert_eq!(dump.instance_uid().unwrap(), None);
// tasks // tasks
@@ -633,7 +633,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
assert_eq!(dump.instance_uid().unwrap(), None); assert_eq!(dump.instance_uid().unwrap(), None);
// tasks // tasks
@@ -726,7 +726,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap(); let mut dump = DumpReader::open(dump).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
assert_eq!(dump.instance_uid().unwrap(), None); assert_eq!(dump.instance_uid().unwrap(), None);
// tasks // tasks

View File

@@ -252,7 +252,7 @@ pub(crate) mod test {
let mut dump = V2Reader::open(dir).unwrap(); let mut dump = V2Reader::open(dir).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();
@@ -349,7 +349,7 @@ pub(crate) mod test {
let mut dump = V2Reader::open(dir).unwrap(); let mut dump = V2Reader::open(dir).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -267,7 +267,7 @@ pub(crate) mod test {
let mut dump = V3Reader::open(dir).unwrap(); let mut dump = V3Reader::open(dir).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -262,8 +262,8 @@ pub(crate) mod test {
let mut dump = V4Reader::open(dir).unwrap(); let mut dump = V4Reader::open(dir).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d"); insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -299,8 +299,8 @@ pub(crate) mod test {
let mut dump = V5Reader::open(dir).unwrap(); let mut dump = V5Reader::open(dir).unwrap();
// top level infos // top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00"); insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d"); insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks // tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap(); let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -281,7 +281,7 @@ pub(crate) mod test {
let dump_path = dump.path(); let dump_path = dump.path();
// ==== checking global file hierarchy (we want to be sure there isn't too many files or too few) // ==== checking global file hierarchy (we want to be sure there isn't too many files or too few)
insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r###" insta::assert_display_snapshot!(create_directory_hierarchy(dump_path), @r###"
. .
├---- indexes/ ├---- indexes/
│ └---- doggos/ │ └---- doggos/

View File

@@ -11,7 +11,10 @@ edition.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
tempfile = "3.10.1" tempfile = "3.9.0"
thiserror = "1.0.61" thiserror = "1.0.56"
tracing = "0.1.40" tracing = "0.1.40"
uuid = { version = "1.10.0", features = ["serde", "v4"] } uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies]
faux = "0.1.10"

View File

@@ -14,7 +14,7 @@ license.workspace = true
[dependencies] [dependencies]
nom = "7.1.3" nom = "7.1.3"
nom_locate = "4.2.0" nom_locate = "4.2.0"
unescaper = "0.1.5" unescaper = "0.1.3"
[dev-dependencies] [dev-dependencies]
insta = "1.39.0" insta = "1.34.0"

View File

@@ -26,7 +26,6 @@ pub enum Condition<'a> {
LowerThan(Token<'a>), LowerThan(Token<'a>),
LowerThanOrEqual(Token<'a>), LowerThanOrEqual(Token<'a>),
Between { from: Token<'a>, to: Token<'a> }, Between { from: Token<'a>, to: Token<'a> },
Contains { keyword: Token<'a>, word: Token<'a> },
} }
/// condition = value ("==" | ">" ...) value /// condition = value ("==" | ">" ...) value
@@ -93,34 +92,6 @@ pub fn parse_not_exists(input: Span) -> IResult<FilterCondition> {
Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Exists })))) Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Exists }))))
} }
/// contains = value "CONTAINS" value
pub fn parse_contains(input: Span) -> IResult<FilterCondition> {
let (input, (fid, contains, value)) =
tuple((parse_value, tag("CONTAINS"), cut(parse_value)))(input)?;
Ok((
input,
FilterCondition::Condition {
fid,
op: Contains { keyword: Token { span: contains, value: None }, word: value },
},
))
}
/// contains = value "NOT" WS+ "CONTAINS" value
pub fn parse_not_contains(input: Span) -> IResult<FilterCondition> {
let keyword = tuple((tag("NOT"), multispace1, tag("CONTAINS")));
let (input, (fid, (_not, _spaces, contains), value)) =
tuple((parse_value, keyword, cut(parse_value)))(input)?;
Ok((
input,
FilterCondition::Not(Box::new(FilterCondition::Condition {
fid,
op: Contains { keyword: Token { span: contains, value: None }, word: value },
})),
))
}
/// to = value value "TO" WS+ value /// to = value value "TO" WS+ value
pub fn parse_to(input: Span) -> IResult<FilterCondition> { pub fn parse_to(input: Span) -> IResult<FilterCondition> {
let (input, (key, from, _, _, to)) = let (input, (key, from, _, _, to)) =

View File

@@ -146,7 +146,7 @@ impl<'a> Display for Error<'a> {
} }
ErrorKind::InvalidPrimary => { ErrorKind::InvalidPrimary => {
let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) }; let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) };
writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` {}", text)? writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
} }
ErrorKind::InvalidEscapedNumber => { ErrorKind::InvalidEscapedNumber => {
writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)? writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)?

View File

@@ -48,8 +48,8 @@ use std::fmt::Debug;
pub use condition::{parse_condition, parse_to, Condition}; pub use condition::{parse_condition, parse_to, Condition};
use condition::{ use condition::{
parse_contains, parse_exists, parse_is_empty, parse_is_not_empty, parse_is_not_null, parse_exists, parse_is_empty, parse_is_not_empty, parse_is_not_null, parse_is_null,
parse_is_null, parse_not_contains, parse_not_exists, parse_not_exists,
}; };
use error::{cut_with_err, ExpectedValueKind, NomErrorExt}; use error::{cut_with_err, ExpectedValueKind, NomErrorExt};
pub use error::{Error, ErrorKind}; pub use error::{Error, ErrorKind};
@@ -147,37 +147,7 @@ pub enum FilterCondition<'a> {
GeoBoundingBox { top_right_point: [Token<'a>; 2], bottom_left_point: [Token<'a>; 2] }, GeoBoundingBox { top_right_point: [Token<'a>; 2], bottom_left_point: [Token<'a>; 2] },
} }
pub enum TraversedElement<'a> {
FilterCondition(&'a FilterCondition<'a>),
Condition(&'a Condition<'a>),
}
impl<'a> FilterCondition<'a> { impl<'a> FilterCondition<'a> {
pub fn use_contains_operator(&self) -> Option<&Token> {
match self {
FilterCondition::Condition { fid: _, op } => match op {
Condition::GreaterThan(_)
| Condition::GreaterThanOrEqual(_)
| Condition::Equal(_)
| Condition::NotEqual(_)
| Condition::Null
| Condition::Empty
| Condition::Exists
| Condition::LowerThan(_)
| Condition::LowerThanOrEqual(_)
| Condition::Between { .. } => None,
Condition::Contains { keyword, word: _ } => Some(keyword),
},
FilterCondition::Not(this) => this.use_contains_operator(),
FilterCondition::Or(seq) | FilterCondition::And(seq) => {
seq.iter().find_map(|filter| filter.use_contains_operator())
}
FilterCondition::GeoLowerThan { .. }
| FilterCondition::GeoBoundingBox { .. }
| FilterCondition::In { .. } => None,
}
}
/// Returns the first token found at the specified depth, `None` if no token at this depth. /// Returns the first token found at the specified depth, `None` if no token at this depth.
pub fn token_at_depth(&self, depth: usize) -> Option<&Token> { pub fn token_at_depth(&self, depth: usize) -> Option<&Token> {
match self { match self {
@@ -482,8 +452,6 @@ fn parse_primary(input: Span, depth: usize) -> IResult<FilterCondition> {
parse_exists, parse_exists,
parse_not_exists, parse_not_exists,
parse_to, parse_to,
parse_contains,
parse_not_contains,
// the next lines are only for error handling and are written at the end to have the less possible performance impact // the next lines are only for error handling and are written at the end to have the less possible performance impact
parse_geo, parse_geo,
parse_geo_distance, parse_geo_distance,
@@ -566,7 +534,6 @@ impl<'a> std::fmt::Display for Condition<'a> {
Condition::LowerThan(token) => write!(f, "< {token}"), Condition::LowerThan(token) => write!(f, "< {token}"),
Condition::LowerThanOrEqual(token) => write!(f, "<= {token}"), Condition::LowerThanOrEqual(token) => write!(f, "<= {token}"),
Condition::Between { from, to } => write!(f, "{from} TO {to}"), Condition::Between { from, to } => write!(f, "{from} TO {to}"),
Condition::Contains { word, keyword: _ } => write!(f, "CONTAINS {word}"),
} }
} }
} }
@@ -591,135 +558,127 @@ pub mod tests {
unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into() unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into()
} }
#[track_caller]
fn p(s: &str) -> impl std::fmt::Display + '_ { fn p(s: &str) -> impl std::fmt::Display + '_ {
Fc::parse(s).unwrap().unwrap() Fc::parse(s).unwrap().unwrap()
} }
#[test] #[test]
fn parse_escaped() { fn parse_escaped() {
insta::assert_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#); insta::assert_display_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#);
insta::assert_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#); insta::assert_display_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#);
insta::assert_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#); insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#);
insta::assert_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#); insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
// but it also works with other sequences // but it also works with other sequences
insta::assert_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}"); insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
} }
#[test] #[test]
fn parse() { fn parse() {
// Test equal // Test equal
insta::assert_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}"); insta::assert_display_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
insta::assert_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}"); insta::assert_display_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");
insta::assert_snapshot!(p("channel = 'Mister Mv'"), @"{channel} = {Mister Mv}"); insta::assert_display_snapshot!(p("channel = 'Mister Mv'"), @"{channel} = {Mister Mv}");
insta::assert_snapshot!(p("channel = \"Mister Mv\""), @"{channel} = {Mister Mv}"); insta::assert_display_snapshot!(p("channel = \"Mister Mv\""), @"{channel} = {Mister Mv}");
insta::assert_snapshot!(p("'dog race' = Borzoi"), @"{dog race} = {Borzoi}"); insta::assert_display_snapshot!(p("'dog race' = Borzoi"), @"{dog race} = {Borzoi}");
insta::assert_snapshot!(p("\"dog race\" = Chusky"), @"{dog race} = {Chusky}"); insta::assert_display_snapshot!(p("\"dog race\" = Chusky"), @"{dog race} = {Chusky}");
insta::assert_snapshot!(p("\"dog race\" = \"Bernese Mountain\""), @"{dog race} = {Bernese Mountain}"); insta::assert_display_snapshot!(p("\"dog race\" = \"Bernese Mountain\""), @"{dog race} = {Bernese Mountain}");
insta::assert_snapshot!(p("'dog race' = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}"); insta::assert_display_snapshot!(p("'dog race' = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
insta::assert_snapshot!(p("\"dog race\" = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}"); insta::assert_display_snapshot!(p("\"dog race\" = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
// Test IN // Test IN
insta::assert_snapshot!(p("colour IN[]"), @"{colour} IN[]"); insta::assert_display_snapshot!(p("colour IN[]"), @"{colour} IN[]");
insta::assert_snapshot!(p("colour IN[green]"), @"{colour} IN[{green}, ]"); insta::assert_display_snapshot!(p("colour IN[green]"), @"{colour} IN[{green}, ]");
insta::assert_snapshot!(p("colour IN[green,]"), @"{colour} IN[{green}, ]"); insta::assert_display_snapshot!(p("colour IN[green,]"), @"{colour} IN[{green}, ]");
insta::assert_snapshot!(p("colour NOT IN[green,blue]"), @"NOT ({colour} IN[{green}, {blue}, ])"); insta::assert_display_snapshot!(p("colour NOT IN[green,blue]"), @"NOT ({colour} IN[{green}, {blue}, ])");
insta::assert_snapshot!(p(" colour IN [ green , blue , ]"), @"{colour} IN[{green}, {blue}, ]"); insta::assert_display_snapshot!(p(" colour IN [ green , blue , ]"), @"{colour} IN[{green}, {blue}, ]");
// Test IN + OR/AND/() // Test IN + OR/AND/()
insta::assert_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]"); insta::assert_display_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
insta::assert_snapshot!(p("NOT (colour IN [green, blue]) AND color = green "), @"AND[NOT ({colour} IN[{green}, {blue}, ]), {color} = {green}, ]"); insta::assert_display_snapshot!(p("NOT (colour IN [green, blue]) AND color = green "), @"AND[NOT ({colour} IN[{green}, {blue}, ]), {color} = {green}, ]");
insta::assert_snapshot!(p("x = 1 OR NOT (colour IN [green, blue] OR color = green) "), @"OR[{x} = {1}, NOT (OR[{colour} IN[{green}, {blue}, ], {color} = {green}, ]), ]"); insta::assert_display_snapshot!(p("x = 1 OR NOT (colour IN [green, blue] OR color = green) "), @"OR[{x} = {1}, NOT (OR[{colour} IN[{green}, {blue}, ], {color} = {green}, ]), ]");
// Test whitespace start/end // Test whitespace start/end
insta::assert_snapshot!(p(" colour = green "), @"{colour} = {green}"); insta::assert_display_snapshot!(p(" colour = green "), @"{colour} = {green}");
insta::assert_snapshot!(p(" (colour = green OR colour = red) "), @"OR[{colour} = {green}, {colour} = {red}, ]"); insta::assert_display_snapshot!(p(" (colour = green OR colour = red) "), @"OR[{colour} = {green}, {colour} = {red}, ]");
insta::assert_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]"); insta::assert_display_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
insta::assert_snapshot!(p(" colour NOT IN [green, blue] "), @"NOT ({colour} IN[{green}, {blue}, ])"); insta::assert_display_snapshot!(p(" colour NOT IN [green, blue] "), @"NOT ({colour} IN[{green}, {blue}, ])");
insta::assert_snapshot!(p(" colour IN [green, blue] "), @"{colour} IN[{green}, {blue}, ]"); insta::assert_display_snapshot!(p(" colour IN [green, blue] "), @"{colour} IN[{green}, {blue}, ]");
// Test conditions // Test conditions
insta::assert_snapshot!(p("channel != ponce"), @"{channel} != {ponce}"); insta::assert_display_snapshot!(p("channel != ponce"), @"{channel} != {ponce}");
insta::assert_snapshot!(p("NOT channel = ponce"), @"NOT ({channel} = {ponce})"); insta::assert_display_snapshot!(p("NOT channel = ponce"), @"NOT ({channel} = {ponce})");
insta::assert_snapshot!(p("subscribers < 1000"), @"{subscribers} < {1000}"); insta::assert_display_snapshot!(p("subscribers < 1000"), @"{subscribers} < {1000}");
insta::assert_snapshot!(p("subscribers > 1000"), @"{subscribers} > {1000}"); insta::assert_display_snapshot!(p("subscribers > 1000"), @"{subscribers} > {1000}");
insta::assert_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}"); insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
insta::assert_snapshot!(p("subscribers >= 1000"), @"{subscribers} >= {1000}"); insta::assert_display_snapshot!(p("subscribers >= 1000"), @"{subscribers} >= {1000}");
insta::assert_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}"); insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
insta::assert_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}"); insta::assert_display_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}");
// Test NOT // Test NOT
insta::assert_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})"); insta::assert_display_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})");
insta::assert_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})"); insta::assert_display_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
// Test NULL + NOT NULL // Test NULL + NOT NULL
insta::assert_snapshot!(p("subscribers IS NULL"), @"{subscribers} IS NULL"); insta::assert_display_snapshot!(p("subscribers IS NULL"), @"{subscribers} IS NULL");
insta::assert_snapshot!(p("NOT subscribers IS NULL"), @"NOT ({subscribers} IS NULL)"); insta::assert_display_snapshot!(p("NOT subscribers IS NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)"); insta::assert_display_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_snapshot!(p("NOT subscribers IS NOT NULL"), @"{subscribers} IS NULL"); insta::assert_display_snapshot!(p("NOT subscribers IS NOT NULL"), @"{subscribers} IS NULL");
insta::assert_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)"); insta::assert_display_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
// Test EMPTY + NOT EMPTY // Test EMPTY + NOT EMPTY
insta::assert_snapshot!(p("subscribers IS EMPTY"), @"{subscribers} IS EMPTY"); insta::assert_display_snapshot!(p("subscribers IS EMPTY"), @"{subscribers} IS EMPTY");
insta::assert_snapshot!(p("NOT subscribers IS EMPTY"), @"NOT ({subscribers} IS EMPTY)"); insta::assert_display_snapshot!(p("NOT subscribers IS EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)"); insta::assert_display_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY"); insta::assert_display_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY");
insta::assert_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)"); insta::assert_display_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
// Test EXISTS + NOT EXITS // Test EXISTS + NOT EXITS
insta::assert_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS"); insta::assert_display_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
insta::assert_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)"); insta::assert_display_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)"); insta::assert_display_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS"); insta::assert_display_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
insta::assert_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)"); insta::assert_display_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
// Test CONTAINS + NOT CONTAINS
insta::assert_snapshot!(p("subscribers CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
insta::assert_snapshot!(p("NOT subscribers CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
insta::assert_snapshot!(p("subscribers NOT CONTAINS hello"), @"NOT ({subscribers} CONTAINS {hello})");
insta::assert_snapshot!(p("NOT subscribers NOT CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
insta::assert_snapshot!(p("subscribers NOT CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
// Test nested NOT // Test nested NOT
insta::assert_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}"); insta::assert_display_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
insta::assert_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}"); insta::assert_display_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
// Test geo radius // Test geo radius
insta::assert_snapshot!(p("_geoRadius(12, 13, 14)"), @"_geoRadius({12}, {13}, {14})"); insta::assert_display_snapshot!(p("_geoRadius(12, 13, 14)"), @"_geoRadius({12}, {13}, {14})");
insta::assert_snapshot!(p("NOT _geoRadius(12, 13, 14)"), @"NOT (_geoRadius({12}, {13}, {14}))"); insta::assert_display_snapshot!(p("NOT _geoRadius(12, 13, 14)"), @"NOT (_geoRadius({12}, {13}, {14}))");
insta::assert_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})"); insta::assert_display_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})");
// Test geo bounding box // Test geo bounding box
insta::assert_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])"); insta::assert_display_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
insta::assert_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))"); insta::assert_display_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))");
insta::assert_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])"); insta::assert_display_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
// Test OR + AND // Test OR + AND
insta::assert_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]"); insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
insta::assert_snapshot!(p("channel = ponce OR 'dog race' != 'bernese mountain'"), @"OR[{channel} = {ponce}, {dog race} != {bernese mountain}, ]"); insta::assert_display_snapshot!(p("channel = ponce OR 'dog race' != 'bernese mountain'"), @"OR[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
insta::assert_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000"), @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ]"); insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000"), @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ]");
insta::assert_snapshot!( insta::assert_display_snapshot!(
p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000 OR colour = red OR colour = blue AND size = 7"), p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000 OR colour = red OR colour = blue AND size = 7"),
@"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, {colour} = {red}, AND[{colour} = {blue}, {size} = {7}, ], ]" @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, {colour} = {red}, AND[{colour} = {blue}, {size} = {7}, ], ]"
); );
// Test parentheses // Test parentheses
insta::assert_snapshot!(p("channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )"), @"AND[{channel} = {ponce}, OR[{dog race} != {bernese mountain}, {subscribers} > {1000}, ], ]"); insta::assert_display_snapshot!(p("channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )"), @"AND[{channel} = {ponce}, OR[{dog race} != {bernese mountain}, {subscribers} > {1000}, ], ]");
insta::assert_snapshot!(p("(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)"), @"AND[OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ], _geoRadius({12}, {13}, {14}), ]"); insta::assert_display_snapshot!(p("(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)"), @"AND[OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ], _geoRadius({12}, {13}, {14}), ]");
// Test recursion // Test recursion
// This is the most that is allowed // This is the most that is allowed
insta::assert_snapshot!( insta::assert_display_snapshot!(
p("(((((((((((((((((((((((((((((((((((((((((((((((((x = 1)))))))))))))))))))))))))))))))))))))))))))))))))"), p("(((((((((((((((((((((((((((((((((((((((((((((((((x = 1)))))))))))))))))))))))))))))))))))))))))))))))))"),
@"{x} = {1}" @"{x} = {1}"
); );
insta::assert_snapshot!( insta::assert_display_snapshot!(
p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"), p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"),
@"NOT ({x} = {1})" @"NOT ({x} = {1})"
); );
// Confusing keywords // Confusing keywords
insta::assert_snapshot!(p(r#"NOT "OR" EXISTS AND "EXISTS" NOT EXISTS"#), @"AND[NOT ({OR} EXISTS), NOT ({EXISTS} EXISTS), ]"); insta::assert_display_snapshot!(p(r#"NOT "OR" EXISTS AND "EXISTS" NOT EXISTS"#), @"AND[NOT ({OR} EXISTS), NOT ({EXISTS} EXISTS), ]");
} }
#[test] #[test]
@@ -730,182 +689,182 @@ pub mod tests {
Fc::parse(s).unwrap_err().to_string() Fc::parse(s).unwrap_err().to_string()
} }
insta::assert_snapshot!(p("channel = Ponce = 12"), @r###" insta::assert_display_snapshot!(p("channel = Ponce = 12"), @r###"
Found unexpected characters at the end of the filter: `= 12`. You probably forgot an `OR` or an `AND` rule. Found unexpected characters at the end of the filter: `= 12`. You probably forgot an `OR` or an `AND` rule.
17:21 channel = Ponce = 12 17:21 channel = Ponce = 12
"###); "###);
insta::assert_snapshot!(p("channel = "), @r###" insta::assert_display_snapshot!(p("channel = "), @r###"
Was expecting a value but instead got nothing. Was expecting a value but instead got nothing.
14:14 channel = 14:14 channel =
"###); "###);
insta::assert_snapshot!(p("channel = 🐻"), @r###" insta::assert_display_snapshot!(p("channel = 🐻"), @r###"
Was expecting a value but instead got `🐻`. Was expecting a value but instead got `🐻`.
11:12 channel = 🐻 11:12 channel = 🐻
"###); "###);
insta::assert_snapshot!(p("channel = 🐻 AND followers < 100"), @r###" insta::assert_display_snapshot!(p("channel = 🐻 AND followers < 100"), @r###"
Was expecting a value but instead got `🐻`. Was expecting a value but instead got `🐻`.
11:12 channel = 🐻 AND followers < 100 11:12 channel = 🐻 AND followers < 100
"###); "###);
insta::assert_snapshot!(p("'OR'"), @r###" insta::assert_display_snapshot!(p("'OR'"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
1:5 'OR' 1:5 'OR'
"###); "###);
insta::assert_snapshot!(p("OR"), @r###" insta::assert_display_snapshot!(p("OR"), @r###"
Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes. Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
1:3 OR 1:3 OR
"###); "###);
insta::assert_snapshot!(p("channel Ponce"), @r###" insta::assert_display_snapshot!(p("channel Ponce"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
1:14 channel Ponce 1:14 channel Ponce
"###); "###);
insta::assert_snapshot!(p("channel = Ponce OR"), @r###" insta::assert_display_snapshot!(p("channel = Ponce OR"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
19:19 channel = Ponce OR 19:19 channel = Ponce OR
"###); "###);
insta::assert_snapshot!(p("_geoRadius"), @r###" insta::assert_display_snapshot!(p("_geoRadius"), @r###"
The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`. The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.
1:11 _geoRadius 1:11 _geoRadius
"###); "###);
insta::assert_snapshot!(p("_geoRadius = 12"), @r###" insta::assert_display_snapshot!(p("_geoRadius = 12"), @r###"
The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`. The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.
1:16 _geoRadius = 12 1:16 _geoRadius = 12
"###); "###);
insta::assert_snapshot!(p("_geoBoundingBox"), @r###" insta::assert_display_snapshot!(p("_geoBoundingBox"), @r###"
The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`. The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
1:16 _geoBoundingBox 1:16 _geoBoundingBox
"###); "###);
insta::assert_snapshot!(p("_geoBoundingBox = 12"), @r###" insta::assert_display_snapshot!(p("_geoBoundingBox = 12"), @r###"
The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`. The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
1:21 _geoBoundingBox = 12 1:21 _geoBoundingBox = 12
"###); "###);
insta::assert_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###" insta::assert_display_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###"
The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`. The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
1:26 _geoBoundingBox(1.0, 1.0) 1:26 _geoBoundingBox(1.0, 1.0)
"###); "###);
insta::assert_snapshot!(p("_geoPoint(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("_geoPoint(12, 13, 14)"), @r###"
`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates. `_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
1:22 _geoPoint(12, 13, 14) 1:22 _geoPoint(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###"
`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates. `_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
13:34 position <= _geoPoint(12, 13, 14) 13:34 position <= _geoPoint(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("_geoDistance(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("_geoDistance(12, 13, 14)"), @r###"
`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates. `_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
1:25 _geoDistance(12, 13, 14) 1:25 _geoDistance(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("position <= _geoDistance(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("position <= _geoDistance(12, 13, 14)"), @r###"
`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates. `_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
13:37 position <= _geoDistance(12, 13, 14) 13:37 position <= _geoDistance(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("_geo(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("_geo(12, 13, 14)"), @r###"
`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates. `_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
1:17 _geo(12, 13, 14) 1:17 _geo(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("position <= _geo(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("position <= _geo(12, 13, 14)"), @r###"
`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates. `_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
13:29 position <= _geo(12, 13, 14) 13:29 position <= _geo(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("position <= _geoRadius(12, 13, 14)"), @r###" insta::assert_display_snapshot!(p("position <= _geoRadius(12, 13, 14)"), @r###"
The `_geoRadius` filter is an operation and can't be used as a value. The `_geoRadius` filter is an operation and can't be used as a value.
13:35 position <= _geoRadius(12, 13, 14) 13:35 position <= _geoRadius(12, 13, 14)
"###); "###);
insta::assert_snapshot!(p("channel = 'ponce"), @r###" insta::assert_display_snapshot!(p("channel = 'ponce"), @r###"
Expression `\'ponce` is missing the following closing delimiter: `'`. Expression `\'ponce` is missing the following closing delimiter: `'`.
11:17 channel = 'ponce 11:17 channel = 'ponce
"###); "###);
insta::assert_snapshot!(p("channel = \"ponce"), @r###" insta::assert_display_snapshot!(p("channel = \"ponce"), @r###"
Expression `\"ponce` is missing the following closing delimiter: `"`. Expression `\"ponce` is missing the following closing delimiter: `"`.
11:17 channel = "ponce 11:17 channel = "ponce
"###); "###);
insta::assert_snapshot!(p("channel = mv OR (followers >= 1000"), @r###" insta::assert_display_snapshot!(p("channel = mv OR (followers >= 1000"), @r###"
Expression `(followers >= 1000` is missing the following closing delimiter: `)`. Expression `(followers >= 1000` is missing the following closing delimiter: `)`.
17:35 channel = mv OR (followers >= 1000 17:35 channel = mv OR (followers >= 1000
"###); "###);
insta::assert_snapshot!(p("channel = mv OR followers >= 1000)"), @r###" insta::assert_display_snapshot!(p("channel = mv OR followers >= 1000)"), @r###"
Found unexpected characters at the end of the filter: `)`. You probably forgot an `OR` or an `AND` rule. Found unexpected characters at the end of the filter: `)`. You probably forgot an `OR` or an `AND` rule.
34:35 channel = mv OR followers >= 1000) 34:35 channel = mv OR followers >= 1000)
"###); "###);
insta::assert_snapshot!(p("colour NOT EXIST"), @r###" insta::assert_display_snapshot!(p("colour NOT EXIST"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
1:17 colour NOT EXIST 1:17 colour NOT EXIST
"###); "###);
insta::assert_snapshot!(p("subscribers 100 TO1000"), @r###" insta::assert_display_snapshot!(p("subscribers 100 TO1000"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
1:23 subscribers 100 TO1000 1:23 subscribers 100 TO1000
"###); "###);
insta::assert_snapshot!(p("channel = ponce ORdog != 'bernese mountain'"), @r###" insta::assert_display_snapshot!(p("channel = ponce ORdog != 'bernese mountain'"), @r###"
Found unexpected characters at the end of the filter: `ORdog != \'bernese mountain\'`. You probably forgot an `OR` or an `AND` rule. Found unexpected characters at the end of the filter: `ORdog != \'bernese mountain\'`. You probably forgot an `OR` or an `AND` rule.
17:44 channel = ponce ORdog != 'bernese mountain' 17:44 channel = ponce ORdog != 'bernese mountain'
"###); "###);
insta::assert_snapshot!(p("colour IN blue, green]"), @r###" insta::assert_display_snapshot!(p("colour IN blue, green]"), @r###"
Expected `[` after `IN` keyword. Expected `[` after `IN` keyword.
11:23 colour IN blue, green] 11:23 colour IN blue, green]
"###); "###);
insta::assert_snapshot!(p("colour IN [blue, green, 'blue' > 2]"), @r###" insta::assert_display_snapshot!(p("colour IN [blue, green, 'blue' > 2]"), @r###"
Expected only comma-separated field names inside `IN[..]` but instead found `> 2]`. Expected only comma-separated field names inside `IN[..]` but instead found `> 2]`.
32:36 colour IN [blue, green, 'blue' > 2] 32:36 colour IN [blue, green, 'blue' > 2]
"###); "###);
insta::assert_snapshot!(p("colour IN [blue, green, AND]"), @r###" insta::assert_display_snapshot!(p("colour IN [blue, green, AND]"), @r###"
Expected only comma-separated field names inside `IN[..]` but instead found `AND]`. Expected only comma-separated field names inside `IN[..]` but instead found `AND]`.
25:29 colour IN [blue, green, AND] 25:29 colour IN [blue, green, AND]
"###); "###);
insta::assert_snapshot!(p("colour IN [blue, green"), @r###" insta::assert_display_snapshot!(p("colour IN [blue, green"), @r###"
Expected matching `]` after the list of field names given to `IN[` Expected matching `]` after the list of field names given to `IN[`
23:23 colour IN [blue, green 23:23 colour IN [blue, green
"###); "###);
insta::assert_snapshot!(p("colour IN ['blue, green"), @r###" insta::assert_display_snapshot!(p("colour IN ['blue, green"), @r###"
Expression `\'blue, green` is missing the following closing delimiter: `'`. Expression `\'blue, green` is missing the following closing delimiter: `'`.
12:24 colour IN ['blue, green 12:24 colour IN ['blue, green
"###); "###);
insta::assert_snapshot!(p("x = EXISTS"), @r###" insta::assert_display_snapshot!(p("x = EXISTS"), @r###"
Was expecting a value but instead got `EXISTS`, which is a reserved keyword. To use `EXISTS` as a field name or a value, surround it by quotes. Was expecting a value but instead got `EXISTS`, which is a reserved keyword. To use `EXISTS` as a field name or a value, surround it by quotes.
5:11 x = EXISTS 5:11 x = EXISTS
"###); "###);
insta::assert_snapshot!(p("AND = 8"), @r###" insta::assert_display_snapshot!(p("AND = 8"), @r###"
Was expecting a value but instead got `AND`, which is a reserved keyword. To use `AND` as a field name or a value, surround it by quotes. Was expecting a value but instead got `AND`, which is a reserved keyword. To use `AND` as a field name or a value, surround it by quotes.
1:4 AND = 8 1:4 AND = 8
"###); "###);
insta::assert_snapshot!(p("((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))"), @r###" insta::assert_display_snapshot!(p("((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))"), @r###"
The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions. The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions.
51:106 ((((((((((((((((((((((((((((((((((((((((((((((((((x = 1)))))))))))))))))))))))))))))))))))))))))))))))))) 51:106 ((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))
"###); "###);
insta::assert_snapshot!( insta::assert_display_snapshot!(
p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"), p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"),
@r###" @r###"
The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions. The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions.
@@ -913,41 +872,41 @@ pub mod tests {
"### "###
); );
insta::assert_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###" insta::assert_display_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###"
Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes. Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
5:7 NOT OR EXISTS AND EXISTS NOT EXISTS 5:7 NOT OR EXISTS AND EXISTS NOT EXISTS
"###); "###);
insta::assert_snapshot!(p(r#"value NULL"#), @r###" insta::assert_display_snapshot!(p(r#"value NULL"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
1:11 value NULL 1:11 value NULL
"###); "###);
insta::assert_snapshot!(p(r#"value NOT NULL"#), @r###" insta::assert_display_snapshot!(p(r#"value NOT NULL"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
1:15 value NOT NULL 1:15 value NOT NULL
"###); "###);
insta::assert_snapshot!(p(r#"value EMPTY"#), @r###" insta::assert_display_snapshot!(p(r#"value EMPTY"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
1:12 value EMPTY 1:12 value EMPTY
"###); "###);
insta::assert_snapshot!(p(r#"value NOT EMPTY"#), @r###" insta::assert_display_snapshot!(p(r#"value NOT EMPTY"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
1:16 value NOT EMPTY 1:16 value NOT EMPTY
"###); "###);
insta::assert_snapshot!(p(r#"value IS"#), @r###" insta::assert_display_snapshot!(p(r#"value IS"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
1:9 value IS 1:9 value IS
"###); "###);
insta::assert_snapshot!(p(r#"value IS NOT"#), @r###" insta::assert_display_snapshot!(p(r#"value IS NOT"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
1:13 value IS NOT 1:13 value IS NOT
"###); "###);
insta::assert_snapshot!(p(r#"value IS EXISTS"#), @r###" insta::assert_display_snapshot!(p(r#"value IS EXISTS"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
1:16 value IS EXISTS 1:16 value IS EXISTS
"###); "###);
insta::assert_snapshot!(p(r#"value IS NOT EXISTS"#), @r###" insta::assert_display_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`. Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
1:20 value IS NOT EXISTS 1:20 value IS NOT EXISTS
"###); "###);
} }

View File

@@ -211,7 +211,6 @@ fn is_keyword(s: &str) -> bool {
| "IS" | "IS"
| "NULL" | "NULL"
| "EMPTY" | "EMPTY"
| "CONTAINS"
| "_geoRadius" | "_geoRadius"
| "_geoBoundingBox" | "_geoBoundingBox"
) )

View File

@@ -12,9 +12,9 @@ license.workspace = true
[dependencies] [dependencies]
arbitrary = { version = "1.3.2", features = ["derive"] } arbitrary = { version = "1.3.2", features = ["derive"] }
clap = { version = "4.5.9", features = ["derive"] } clap = { version = "4.4.17", features = ["derive"] }
fastrand = "2.1.0" fastrand = "2.0.1"
milli = { path = "../milli" } milli = { path = "../milli" }
serde = { version = "1.0.204", features = ["derive"] } serde = { version = "1.0.195", features = ["derive"] }
serde_json = { version = "1.0.120", features = ["preserve_order"] } serde_json = { version = "1.0.111", features = ["preserve_order"] }
tempfile = "3.10.1" tempfile = "3.9.0"

View File

@@ -11,38 +11,38 @@ edition.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
anyhow = "1.0.86" anyhow = "1.0.79"
bincode = "1.3.3" bincode = "1.3.3"
csv = "1.3.0" csv = "1.3.0"
derive_builder = "0.20.0" derive_builder = "0.12.0"
dump = { path = "../dump" } dump = { path = "../dump" }
enum-iterator = "2.1.0" enum-iterator = "1.5.0"
file-store = { path = "../file-store" } file-store = { path = "../file-store" }
flate2 = "1.0.30" flate2 = "1.0.28"
meilisearch-auth = { path = "../meilisearch-auth" } meilisearch-auth = { path = "../meilisearch-auth" }
meilisearch-types = { path = "../meilisearch-types" } meilisearch-types = { path = "../meilisearch-types" }
page_size = "0.6.0" page_size = "0.5.0"
rayon = "1.10.0" rayon = "1.8.1"
roaring = { version = "0.10.6", features = ["serde"] } roaring = { version = "0.10.2", features = ["serde"] }
serde = { version = "1.0.204", features = ["derive"] } serde = { version = "1.0.195", features = ["derive"] }
serde_json = { version = "1.0.120", features = ["preserve_order"] } serde_json = { version = "1.0.111", features = ["preserve_order"] }
synchronoise = "1.0.1" synchronoise = "1.0.1"
tempfile = "3.10.1" tempfile = "3.9.0"
thiserror = "1.0.61" thiserror = "1.0.56"
time = { version = "0.3.36", features = [ time = { version = "0.3.31", features = [
"serde-well-known", "serde-well-known",
"formatting", "formatting",
"parsing", "parsing",
"macros", "macros",
] } ] }
tracing = "0.1.40" tracing = "0.1.40"
ureq = "2.10.0" ureq = "2.9.7"
uuid = { version = "1.10.0", features = ["serde", "v4"] } uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies] [dev-dependencies]
arroy = "0.4.0" arroy = "0.4.0"
big_s = "1.0.2" big_s = "1.0.2"
crossbeam = "0.8.4" crossbeam = "0.8.4"
insta = { version = "1.39.0", features = ["json", "redactions"] } insta = { version = "1.34.0", features = ["json", "redactions"] }
maplit = "1.0.2" maplit = "1.0.2"
meili-snap = { path = "../meili-snap" } meili-snap = { path = "../meili-snap" }

View File

@@ -24,10 +24,8 @@ enum AutobatchKind {
allow_index_creation: bool, allow_index_creation: bool,
primary_key: Option<String>, primary_key: Option<String>,
}, },
DocumentEdition, DocumentDeletion,
DocumentDeletion { DocumentDeletionByFilter,
by_filter: bool,
},
DocumentClear, DocumentClear,
Settings { Settings {
allow_index_creation: bool, allow_index_creation: bool,
@@ -65,13 +63,10 @@ impl From<KindWithContent> for AutobatchKind {
primary_key, primary_key,
.. ..
} => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key }, } => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key },
KindWithContent::DocumentEdition { .. } => AutobatchKind::DocumentEdition, KindWithContent::DocumentDeletion { .. } => AutobatchKind::DocumentDeletion,
KindWithContent::DocumentDeletion { .. } => {
AutobatchKind::DocumentDeletion { by_filter: false }
}
KindWithContent::DocumentClear { .. } => AutobatchKind::DocumentClear, KindWithContent::DocumentClear { .. } => AutobatchKind::DocumentClear,
KindWithContent::DocumentDeletionByFilter { .. } => { KindWithContent::DocumentDeletionByFilter { .. } => {
AutobatchKind::DocumentDeletion { by_filter: true } AutobatchKind::DocumentDeletionByFilter
} }
KindWithContent::SettingsUpdate { allow_index_creation, is_deletion, .. } => { KindWithContent::SettingsUpdate { allow_index_creation, is_deletion, .. } => {
AutobatchKind::Settings { AutobatchKind::Settings {
@@ -103,12 +98,11 @@ pub enum BatchKind {
primary_key: Option<String>, primary_key: Option<String>,
operation_ids: Vec<TaskId>, operation_ids: Vec<TaskId>,
}, },
DocumentEdition {
id: TaskId,
},
DocumentDeletion { DocumentDeletion {
deletion_ids: Vec<TaskId>, deletion_ids: Vec<TaskId>,
includes_by_filter: bool, },
DocumentDeletionByFilter {
id: TaskId,
}, },
ClearAndSettings { ClearAndSettings {
other: Vec<TaskId>, other: Vec<TaskId>,
@@ -205,14 +199,12 @@ impl BatchKind {
}), }),
allow_index_creation, allow_index_creation,
), ),
K::DocumentEdition => (Break(BatchKind::DocumentEdition { id: task_id }), false), K::DocumentDeletion => {
K::DocumentDeletion { by_filter: includes_by_filter } => ( (Continue(BatchKind::DocumentDeletion { deletion_ids: vec![task_id] }), false)
Continue(BatchKind::DocumentDeletion { }
deletion_ids: vec![task_id], K::DocumentDeletionByFilter => {
includes_by_filter, (Break(BatchKind::DocumentDeletionByFilter { id: task_id }), false)
}), }
false,
),
K::Settings { allow_index_creation } => ( K::Settings { allow_index_creation } => (
Continue(BatchKind::Settings { allow_index_creation, settings_ids: vec![task_id] }), Continue(BatchKind::Settings { allow_index_creation, settings_ids: vec![task_id] }),
allow_index_creation, allow_index_creation,
@@ -230,7 +222,7 @@ impl BatchKind {
match (self, kind) { match (self, kind) {
// We don't batch any of these operations // We don't batch any of these operations
(this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => Break(this), (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentDeletionByFilter) => Break(this),
// We must not batch tasks that don't have the same index creation rights if the index doesn't already exists. // We must not batch tasks that don't have the same index creation rights if the index doesn't already exists.
(this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => { (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
Break(this) Break(this)
@@ -266,7 +258,7 @@ impl BatchKind {
// The index deletion can batch with everything but must stop after // The index deletion can batch with everything but must stop after
( (
BatchKind::DocumentClear { mut ids } BatchKind::DocumentClear { mut ids }
| BatchKind::DocumentDeletion { deletion_ids: mut ids, includes_by_filter: _ } | BatchKind::DocumentDeletion { deletion_ids: mut ids }
| BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, operation_ids: mut ids } | BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, operation_ids: mut ids }
| BatchKind::Settings { allow_index_creation: _, settings_ids: mut ids }, | BatchKind::Settings { allow_index_creation: _, settings_ids: mut ids },
K::IndexDeletion, K::IndexDeletion,
@@ -286,7 +278,7 @@ impl BatchKind {
( (
BatchKind::DocumentClear { mut ids }, BatchKind::DocumentClear { mut ids },
K::DocumentClear | K::DocumentDeletion { by_filter: _ }, K::DocumentClear | K::DocumentDeletion,
) => { ) => {
ids.push(id); ids.push(id);
Continue(BatchKind::DocumentClear { ids }) Continue(BatchKind::DocumentClear { ids })
@@ -330,7 +322,7 @@ impl BatchKind {
} }
( (
BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids }, BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
K::DocumentDeletion { by_filter: false }, K::DocumentDeletion,
) => { ) => {
operation_ids.push(id); operation_ids.push(id);
@@ -341,13 +333,6 @@ impl BatchKind {
operation_ids, operation_ids,
}) })
} }
// We can't batch a document operation with a delete by filter
(
this @ BatchKind::DocumentOperation { .. },
K::DocumentDeletion { by_filter: true },
) => {
Break(this)
}
// but we can't autobatch documents if it's not the same kind // but we can't autobatch documents if it's not the same kind
// this match branch MUST be AFTER the previous one // this match branch MUST be AFTER the previous one
( (
@@ -366,18 +351,13 @@ impl BatchKind {
operation_ids, operation_ids,
}), }),
(BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: _ }, K::DocumentClear) => { (BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentClear) => {
deletion_ids.push(id); deletion_ids.push(id);
Continue(BatchKind::DocumentClear { ids: deletion_ids }) Continue(BatchKind::DocumentClear { ids: deletion_ids })
} }
// we can't autobatch the deletion and import if the document deletion contained a filter
(
this @ BatchKind::DocumentDeletion { deletion_ids: _, includes_by_filter: true },
K::DocumentImport { .. }
) => Break(this),
// we can autobatch the deletion and import if the index already exists // we can autobatch the deletion and import if the index already exists
( (
BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false }, BatchKind::DocumentDeletion { mut deletion_ids },
K::DocumentImport { method, allow_index_creation, primary_key } K::DocumentImport { method, allow_index_creation, primary_key }
) if index_already_exists => { ) if index_already_exists => {
deletion_ids.push(id); deletion_ids.push(id);
@@ -391,7 +371,7 @@ impl BatchKind {
} }
// we can autobatch the deletion and import if both can't create an index // we can autobatch the deletion and import if both can't create an index
( (
BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false }, BatchKind::DocumentDeletion { mut deletion_ids },
K::DocumentImport { method, allow_index_creation, primary_key } K::DocumentImport { method, allow_index_creation, primary_key }
) if !allow_index_creation => { ) if !allow_index_creation => {
deletion_ids.push(id); deletion_ids.push(id);
@@ -410,9 +390,9 @@ impl BatchKind {
) => { ) => {
Break(this) Break(this)
} }
(BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter }, K::DocumentDeletion { by_filter }) => { (BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentDeletion) => {
deletion_ids.push(id); deletion_ids.push(id);
Continue(BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: includes_by_filter | by_filter }) Continue(BatchKind::DocumentDeletion { deletion_ids })
} }
(this @ BatchKind::DocumentDeletion { .. }, K::Settings { .. }) => Break(this), (this @ BatchKind::DocumentDeletion { .. }, K::Settings { .. }) => Break(this),
@@ -426,7 +406,7 @@ impl BatchKind {
}), }),
( (
this @ BatchKind::Settings { .. }, this @ BatchKind::Settings { .. },
K::DocumentImport { .. } | K::DocumentDeletion { .. }, K::DocumentImport { .. } | K::DocumentDeletion,
) => Break(this), ) => Break(this),
( (
BatchKind::Settings { mut settings_ids, allow_index_creation }, BatchKind::Settings { mut settings_ids, allow_index_creation },
@@ -457,7 +437,7 @@ impl BatchKind {
settings_ids, settings_ids,
allow_index_creation, allow_index_creation,
}, },
K::DocumentDeletion { .. }, K::DocumentDeletion,
) => { ) => {
other.push(id); other.push(id);
Continue(BatchKind::ClearAndSettings { Continue(BatchKind::ClearAndSettings {
@@ -519,7 +499,7 @@ impl BatchKind {
// this MUST be AFTER the two previous branch // this MUST be AFTER the two previous branch
( (
this @ BatchKind::SettingsAndDocumentOperation { .. }, this @ BatchKind::SettingsAndDocumentOperation { .. },
K::DocumentDeletion { .. } | K::DocumentImport { .. }, K::DocumentDeletion | K::DocumentImport { .. },
) => Break(this), ) => Break(this),
( (
BatchKind::SettingsAndDocumentOperation { mut settings_ids, method, allow_index_creation,primary_key, operation_ids }, BatchKind::SettingsAndDocumentOperation { mut settings_ids, method, allow_index_creation,primary_key, operation_ids },
@@ -539,7 +519,7 @@ impl BatchKind {
| BatchKind::IndexDeletion { .. } | BatchKind::IndexDeletion { .. }
| BatchKind::IndexUpdate { .. } | BatchKind::IndexUpdate { .. }
| BatchKind::IndexSwap { .. } | BatchKind::IndexSwap { .. }
| BatchKind::DocumentEdition { .. }, | BatchKind::DocumentDeletionByFilter { .. },
_, _,
) => { ) => {
unreachable!() unreachable!()
@@ -629,13 +609,6 @@ mod tests {
} }
} }
fn doc_del_fil() -> KindWithContent {
KindWithContent::DocumentDeletionByFilter {
index_uid: String::from("doggo"),
filter_expr: serde_json::json!("cuteness > 100"),
}
}
fn doc_clr() -> KindWithContent { fn doc_clr() -> KindWithContent {
KindWithContent::DocumentClear { index_uid: String::from("doggo") } KindWithContent::DocumentClear { index_uid: String::from("doggo") }
} }
@@ -696,16 +669,10 @@ mod tests {
debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
// we can autobatch one or multiple DocumentDeletion together // we can autobatch one or multiple DocumentDeletion together
debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
// we can autobatch one or multiple DocumentDeletionByFilter together
debug_snapshot!(autobatch_from(true, None, [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false))");
// we can autobatch one or multiple Settings together // we can autobatch one or multiple Settings together
debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
@@ -748,63 +715,25 @@ mod tests {
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
// But we can't autobatch document addition with document deletion by filter
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
// And the other way around
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
} }
#[test] #[test]
fn simple_document_operation_dont_autobatch_with_other() { fn simple_document_operation_dont_autobatch_with_other() {
// addition, updates and deletion by filter can't batch together // addition, updates and deletion can't batch together
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
} }
#[test] #[test]
@@ -871,7 +800,6 @@ mod tests {
debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
@@ -881,7 +809,6 @@ mod tests {
debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
@@ -893,7 +820,6 @@ mod tests {
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(true, None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(true, None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))"); debug_snapshot!(autobatch_from(true, None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
debug_snapshot!(autobatch_from(true, None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(true, None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
@@ -903,7 +829,6 @@ mod tests {
debug_snapshot!(autobatch_from(false,None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
debug_snapshot!(autobatch_from(false,None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))"); debug_snapshot!(autobatch_from(false,None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
debug_snapshot!(autobatch_from(false,None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))"); debug_snapshot!(autobatch_from(false,None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
@@ -969,10 +894,10 @@ mod tests {
debug_snapshot!(autobatch_from(false,None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))"); debug_snapshot!(autobatch_from(false,None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
// batch deletion and addition // batch deletion and addition
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))"); debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
} }
#[test] #[test]

View File

@@ -34,7 +34,7 @@ use meilisearch_types::milli::update::{
use meilisearch_types::milli::vector::parsed_vectors::{ use meilisearch_types::milli::vector::parsed_vectors::{
ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME, ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME,
}; };
use meilisearch_types::milli::{self, Filter, Object}; use meilisearch_types::milli::{self, Filter};
use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked}; use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task}; use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
use meilisearch_types::{compression, Index, VERSION_FILE_NAME}; use meilisearch_types::{compression, Index, VERSION_FILE_NAME};
@@ -106,14 +106,10 @@ pub(crate) enum IndexOperation {
operations: Vec<DocumentOperation>, operations: Vec<DocumentOperation>,
tasks: Vec<Task>, tasks: Vec<Task>,
}, },
DocumentEdition { IndexDocumentDeletionByFilter {
index_uid: String, index_uid: String,
task: Task, task: Task,
}, },
DocumentDeletion {
index_uid: String,
tasks: Vec<Task>,
},
DocumentClear { DocumentClear {
index_uid: String, index_uid: String,
tasks: Vec<Task>, tasks: Vec<Task>,
@@ -165,11 +161,10 @@ impl Batch {
Batch::IndexOperation { op, .. } => match op { Batch::IndexOperation { op, .. } => match op {
IndexOperation::DocumentOperation { tasks, .. } IndexOperation::DocumentOperation { tasks, .. }
| IndexOperation::Settings { tasks, .. } | IndexOperation::Settings { tasks, .. }
| IndexOperation::DocumentDeletion { tasks, .. }
| IndexOperation::DocumentClear { tasks, .. } => { | IndexOperation::DocumentClear { tasks, .. } => {
RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid)) RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
} }
IndexOperation::DocumentEdition { task, .. } => { IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap() RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
} }
IndexOperation::SettingsAndDocumentOperation { IndexOperation::SettingsAndDocumentOperation {
@@ -233,8 +228,7 @@ impl IndexOperation {
pub fn index_uid(&self) -> &str { pub fn index_uid(&self) -> &str {
match self { match self {
IndexOperation::DocumentOperation { index_uid, .. } IndexOperation::DocumentOperation { index_uid, .. }
| IndexOperation::DocumentEdition { index_uid, .. } | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
| IndexOperation::DocumentDeletion { index_uid, .. }
| IndexOperation::DocumentClear { index_uid, .. } | IndexOperation::DocumentClear { index_uid, .. }
| IndexOperation::Settings { index_uid, .. } | IndexOperation::Settings { index_uid, .. }
| IndexOperation::DocumentClearAndSetting { index_uid, .. } | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -249,11 +243,8 @@ impl fmt::Display for IndexOperation {
IndexOperation::DocumentOperation { .. } => { IndexOperation::DocumentOperation { .. } => {
f.write_str("IndexOperation::DocumentOperation") f.write_str("IndexOperation::DocumentOperation")
} }
IndexOperation::DocumentEdition { .. } => { IndexOperation::IndexDocumentDeletionByFilter { .. } => {
f.write_str("IndexOperation::DocumentEdition") f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
}
IndexOperation::DocumentDeletion { .. } => {
f.write_str("IndexOperation::DocumentDeletion")
} }
IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"), IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"),
IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"), IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"),
@@ -289,12 +280,12 @@ impl IndexScheduler {
}, },
must_create_index, must_create_index,
})), })),
BatchKind::DocumentEdition { id } => { BatchKind::DocumentDeletionByFilter { id } => {
let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?; let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
match &task.kind { match &task.kind {
KindWithContent::DocumentEdition { index_uid, .. } => { KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
Ok(Some(Batch::IndexOperation { Ok(Some(Batch::IndexOperation {
op: IndexOperation::DocumentEdition { op: IndexOperation::IndexDocumentDeletionByFilter {
index_uid: index_uid.clone(), index_uid: index_uid.clone(),
task, task,
}, },
@@ -351,11 +342,30 @@ impl IndexScheduler {
must_create_index, must_create_index,
})) }))
} }
BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: _ } => { BatchKind::DocumentDeletion { deletion_ids } => {
let tasks = self.get_existing_tasks(rtxn, deletion_ids)?; let tasks = self.get_existing_tasks(rtxn, deletion_ids)?;
let mut operations = Vec::with_capacity(tasks.len());
let mut documents_counts = Vec::with_capacity(tasks.len());
for task in &tasks {
match task.kind {
KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
operations.push(DocumentOperation::Delete(documents_ids.clone()));
documents_counts.push(documents_ids.len() as u64);
}
_ => unreachable!(),
}
}
Ok(Some(Batch::IndexOperation { Ok(Some(Batch::IndexOperation {
op: IndexOperation::DocumentDeletion { index_uid, tasks }, op: IndexOperation::DocumentOperation {
index_uid,
primary_key: None,
method: IndexDocumentsMethod::ReplaceDocuments,
documents_counts,
operations,
tasks,
},
must_create_index, must_create_index,
})) }))
} }
@@ -887,91 +897,95 @@ impl IndexScheduler {
dump_tasks.flush()?; dump_tasks.flush()?;
// 3. Dump the indexes // 3. Dump the indexes
self.index_mapper.try_for_each_index(&rtxn, |uid, index| -> Result<()> { let () =
let rtxn = index.read_txn()?; self.index_mapper.try_for_each_index(&rtxn, |uid, index| -> Result<()> {
let metadata = IndexMetadata { let rtxn = index.read_txn()?;
uid: uid.to_owned(), let metadata = IndexMetadata {
primary_key: index.primary_key(&rtxn)?.map(String::from), uid: uid.to_owned(),
created_at: index.created_at(&rtxn)?, primary_key: index.primary_key(&rtxn)?.map(String::from),
updated_at: index.updated_at(&rtxn)?, created_at: index.created_at(&rtxn)?,
}; updated_at: index.updated_at(&rtxn)?,
let mut index_dumper = dump.create_index(uid, &metadata)?; };
let mut index_dumper = dump.create_index(uid, &metadata)?;
let fields_ids_map = index.fields_ids_map(&rtxn)?; let fields_ids_map = index.fields_ids_map(&rtxn)?;
let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect(); let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
let embedding_configs = index.embedding_configs(&rtxn)?; let embedding_configs = index.embedding_configs(&rtxn)?;
// 3.1. Dump the documents // 3.1. Dump the documents
for ret in index.all_documents(&rtxn)? { for ret in index.all_documents(&rtxn)? {
if self.must_stop_processing.get() { if self.must_stop_processing.get() {
return Err(Error::AbortedTask); return Err(Error::AbortedTask);
}
let (id, doc) = ret?;
let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
'inject_vectors: {
let embeddings = index.embeddings(&rtxn, id)?;
if embeddings.is_empty() {
break 'inject_vectors;
} }
let vectors = document let (id, doc) = ret?;
.entry(RESERVED_VECTORS_FIELD_NAME.to_owned())
.or_insert(serde_json::Value::Object(Default::default()));
let serde_json::Value::Object(vectors) = vectors else { let mut document =
return Err(milli::Error::UserError( milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
milli::UserError::InvalidVectorsMapType {
document_id: { 'inject_vectors: {
if let Ok(Some(Ok(index))) = index let embeddings = index.embeddings(&rtxn, id)?;
.external_id_of(&rtxn, std::iter::once(id))
.map(|it| it.into_iter().next()) if embeddings.is_empty() {
{ break 'inject_vectors;
index }
} else {
format!("internal docid={id}") let vectors = document
} .entry(RESERVED_VECTORS_FIELD_NAME.to_owned())
.or_insert(serde_json::Value::Object(Default::default()));
let serde_json::Value::Object(vectors) = vectors else {
return Err(milli::Error::UserError(
milli::UserError::InvalidVectorsMapType {
document_id: {
if let Ok(Some(Ok(index))) = index
.external_id_of(&rtxn, std::iter::once(id))
.map(|it| it.into_iter().next())
{
index
} else {
format!("internal docid={id}")
}
},
value: vectors.clone(),
}, },
value: vectors.clone(), )
}, .into());
)
.into());
};
for (embedder_name, embeddings) in embeddings {
let user_provided = embedding_configs
.iter()
.find(|conf| conf.name == embedder_name)
.is_some_and(|conf| conf.user_provided.contains(id));
let embeddings = ExplicitVectors {
embeddings: Some(
VectorOrArrayOfVectors::from_array_of_vectors(embeddings),
),
regenerate: !user_provided,
}; };
vectors.insert(
embedder_name, for (embedder_name, embeddings) in embeddings {
serde_json::to_value(embeddings).unwrap(), let user_provided = embedding_configs
); .iter()
.find(|conf| conf.name == embedder_name)
.is_some_and(|conf| conf.user_provided.contains(id));
let embeddings = ExplicitVectors {
embeddings: Some(
VectorOrArrayOfVectors::from_array_of_vectors(
embeddings,
),
),
regenerate: !user_provided,
};
vectors.insert(
embedder_name,
serde_json::to_value(embeddings).unwrap(),
);
}
} }
index_dumper.push_document(&document)?;
} }
index_dumper.push_document(&document)?; // 3.2. Dump the settings
} let settings = meilisearch_types::settings::settings(
index,
// 3.2. Dump the settings &rtxn,
let settings = meilisearch_types::settings::settings( meilisearch_types::settings::SecretPolicy::RevealSecrets,
index, )?;
&rtxn, index_dumper.settings(&settings)?;
meilisearch_types::settings::SecretPolicy::RevealSecrets, Ok(())
)?; })?;
index_dumper.settings(&settings)?;
Ok(())
})?;
// 4. Dump experimental feature settings // 4. Dump experimental feature settings
let features = self.features().runtime_features(); let features = self.features().runtime_features();
@@ -1247,7 +1261,6 @@ impl IndexScheduler {
operations, operations,
mut tasks, mut tasks,
} => { } => {
let started_processing_at = std::time::Instant::now();
let mut primary_key_has_been_set = false; let mut primary_key_has_been_set = false;
let must_stop_processing = self.must_stop_processing.clone(); let must_stop_processing = self.must_stop_processing.clone();
let indexer_config = self.index_mapper.indexer_config(); let indexer_config = self.index_mapper.indexer_config();
@@ -1279,7 +1292,11 @@ impl IndexScheduler {
} }
} }
let config = IndexDocumentsConfig { update_method: method, ..Default::default() }; let config = IndexDocumentsConfig {
update_method: method,
compute_prefix_databases: self.compute_prefix_databases,
..Default::default()
};
let embedder_configs = index.embedding_configs(index_wtxn)?; let embedder_configs = index.embedding_configs(index_wtxn)?;
// TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense) // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
@@ -1362,7 +1379,7 @@ impl IndexScheduler {
if !tasks.iter().all(|res| res.error.is_some()) { if !tasks.iter().all(|res| res.error.is_some()) {
let addition = builder.execute()?; let addition = builder.execute()?;
tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done"); tracing::info!(indexing_result = ?addition, "document indexing done");
} else if primary_key_has_been_set { } else if primary_key_has_been_set {
// Everything failed but we've set a primary key. // Everything failed but we've set a primary key.
// We need to remove it. // We need to remove it.
@@ -1377,57 +1394,47 @@ impl IndexScheduler {
Ok(tasks) Ok(tasks)
} }
IndexOperation::DocumentEdition { mut task, .. } => { IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
let (filter, context, function) = let filter =
if let KindWithContent::DocumentEdition { if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
filter_expr, context, function, .. &task.kind
} = &task.kind
{ {
(filter_expr, context, function) filter_expr
} else { } else {
unreachable!() unreachable!()
}; };
let result_count = edit_documents_by_function( let deleted_documents = delete_document_by_filter(
index_wtxn, index_wtxn,
filter, filter,
context.clone(), self.compute_prefix_databases,
function,
self.index_mapper.indexer_config(), self.index_mapper.indexer_config(),
self.must_stop_processing.clone(), self.must_stop_processing.clone(),
index, index,
); );
let (original_filter, context, function) = if let Some(Details::DocumentEdition { let original_filter = if let Some(Details::DocumentDeletionByFilter {
original_filter, original_filter,
context, deleted_documents: _,
function,
..
}) = task.details }) = task.details
{ {
(original_filter, context, function) original_filter
} else { } else {
// In the case of a `documentEdition` the details MUST be set // In the case of a `documentDeleteByFilter` the details MUST be set
unreachable!(); unreachable!();
}; };
match result_count { match deleted_documents {
Ok((deleted_documents, edited_documents)) => { Ok(deleted_documents) => {
task.status = Status::Succeeded; task.status = Status::Succeeded;
task.details = Some(Details::DocumentEdition { task.details = Some(Details::DocumentDeletionByFilter {
original_filter, original_filter,
context,
function,
deleted_documents: Some(deleted_documents), deleted_documents: Some(deleted_documents),
edited_documents: Some(edited_documents),
}); });
} }
Err(e) => { Err(e) => {
task.status = Status::Failed; task.status = Status::Failed;
task.details = Some(Details::DocumentEdition { task.details = Some(Details::DocumentDeletionByFilter {
original_filter, original_filter,
context,
function,
deleted_documents: Some(0), deleted_documents: Some(0),
edited_documents: Some(0),
}); });
task.error = Some(e.into()); task.error = Some(e.into());
} }
@@ -1435,103 +1442,6 @@ impl IndexScheduler {
Ok(vec![task]) Ok(vec![task])
} }
IndexOperation::DocumentDeletion { mut tasks, index_uid: _ } => {
let mut to_delete = RoaringBitmap::new();
let external_documents_ids = index.external_documents_ids();
for task in tasks.iter_mut() {
let before = to_delete.len();
task.status = Status::Succeeded;
match &task.kind {
KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
for id in documents_ids {
if let Some(id) = external_documents_ids.get(index_wtxn, id)? {
to_delete.insert(id);
}
}
let will_be_removed = to_delete.len() - before;
task.details = Some(Details::DocumentDeletion {
provided_ids: documents_ids.len(),
deleted_documents: Some(will_be_removed),
});
}
KindWithContent::DocumentDeletionByFilter { index_uid: _, filter_expr } => {
let before = to_delete.len();
let filter = match Filter::from_json(filter_expr) {
Ok(filter) => filter,
Err(err) => {
// theorically, this should be catched by deserr before reaching the index-scheduler and cannot happens
task.status = Status::Failed;
task.error = match err {
milli::Error::UserError(
milli::UserError::InvalidFilterExpression { .. },
) => Some(
Error::from(err)
.with_custom_error_code(Code::InvalidDocumentFilter)
.into(),
),
e => Some(e.into()),
};
None
}
};
if let Some(filter) = filter {
let candidates =
filter.evaluate(index_wtxn, index).map_err(|err| match err {
milli::Error::UserError(
milli::UserError::InvalidFilter(_),
) => Error::from(err)
.with_custom_error_code(Code::InvalidDocumentFilter),
e => e.into(),
});
match candidates {
Ok(candidates) => to_delete |= candidates,
Err(err) => {
task.status = Status::Failed;
task.error = Some(err.into());
}
};
}
let will_be_removed = to_delete.len() - before;
if let Some(Details::DocumentDeletionByFilter {
original_filter: _,
deleted_documents,
}) = &mut task.details
{
*deleted_documents = Some(will_be_removed);
} else {
// In the case of a `documentDeleteByFilter` the details MUST be set
unreachable!()
}
}
_ => unreachable!(),
}
}
let config = IndexDocumentsConfig {
update_method: IndexDocumentsMethod::ReplaceDocuments,
..Default::default()
};
let must_stop_processing = self.must_stop_processing.clone();
let mut builder = milli::update::IndexDocuments::new(
index_wtxn,
index,
self.index_mapper.indexer_config(),
config,
|indexing_step| tracing::debug!(update = ?indexing_step),
|| must_stop_processing.get(),
)?;
let (new_builder, _count) =
builder.remove_documents_from_db_no_batch(&to_delete)?;
builder = new_builder;
let _ = builder.execute()?;
Ok(tasks)
}
IndexOperation::Settings { index_uid: _, settings, mut tasks } => { IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
let indexer_config = self.index_mapper.indexer_config(); let indexer_config = self.index_mapper.indexer_config();
let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config); let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config);
@@ -1734,43 +1644,44 @@ impl IndexScheduler {
} }
} }
fn edit_documents_by_function<'a>( fn delete_document_by_filter<'a>(
wtxn: &mut RwTxn<'a>, wtxn: &mut RwTxn<'a>,
filter: &Option<serde_json::Value>, filter: &serde_json::Value,
context: Option<Object>, compute_prefix_databases: bool,
code: &str,
indexer_config: &IndexerConfig, indexer_config: &IndexerConfig,
must_stop_processing: MustStopProcessing, must_stop_processing: MustStopProcessing,
index: &'a Index, index: &'a Index,
) -> Result<(u64, u64)> { ) -> Result<u64> {
let candidates = match filter.as_ref().map(Filter::from_json) { let filter = Filter::from_json(filter)?;
Some(Ok(Some(filter))) => filter.evaluate(wtxn, index).map_err(|err| match err { Ok(if let Some(filter) = filter {
let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
milli::Error::UserError(milli::UserError::InvalidFilter(_)) => { milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter) Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
} }
e => e.into(), e => e.into(),
})?, })?;
None | Some(Ok(None)) => index.documents_ids(wtxn)?,
Some(Err(e)) => return Err(e.into()),
};
let config = IndexDocumentsConfig { let config = IndexDocumentsConfig {
update_method: IndexDocumentsMethod::ReplaceDocuments, update_method: IndexDocumentsMethod::ReplaceDocuments,
..Default::default() compute_prefix_databases,
}; ..Default::default()
};
let mut builder = milli::update::IndexDocuments::new( let mut builder = milli::update::IndexDocuments::new(
wtxn, wtxn,
index, index,
indexer_config, indexer_config,
config, config,
|indexing_step| tracing::debug!(update = ?indexing_step), |indexing_step| tracing::debug!(update = ?indexing_step),
|| must_stop_processing.get(), || must_stop_processing.get(),
)?; )?;
let (new_builder, count) = builder.edit_documents(&candidates, context, code)?; let (new_builder, count) = builder.remove_documents_from_db_no_batch(&candidates)?;
builder = new_builder; builder = new_builder;
let _ = builder.execute()?; let _ = builder.execute()?;
Ok(count.unwrap()) count
} else {
0
})
} }

View File

@@ -68,32 +68,6 @@ impl RoFeatures {
.into()) .into())
} }
} }
pub fn check_edit_documents_by_function(&self, disabled_action: &'static str) -> Result<()> {
if self.runtime.edit_documents_by_function {
Ok(())
} else {
Err(FeatureNotEnabledError {
disabled_action,
feature: "edit documents by function",
issue_link: "https://github.com/orgs/meilisearch/discussions/762",
}
.into())
}
}
pub fn check_contains_filter(&self) -> Result<()> {
if self.runtime.contains_filter {
Ok(())
} else {
Err(FeatureNotEnabledError {
disabled_action: "Using `CONTAINS` in a filter",
feature: "contains filter",
issue_link: "https://github.com/orgs/meilisearch/discussions/763",
}
.into())
}
}
} }
impl FeatureData { impl FeatureData {
@@ -105,11 +79,9 @@ impl FeatureData {
let txn = env.read_txn()?; let txn = env.read_txn()?;
let persisted_features: RuntimeTogglableFeatures = let persisted_features: RuntimeTogglableFeatures =
runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default(); runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default();
let InstanceTogglableFeatures { metrics, logs_route, contains_filter } = instance_features;
let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures { let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
metrics: metrics || persisted_features.metrics, metrics: instance_features.metrics || persisted_features.metrics,
logs_route: logs_route || persisted_features.logs_route, logs_route: instance_features.logs_route || persisted_features.logs_route,
contains_filter: contains_filter || persisted_features.contains_filter,
..persisted_features ..persisted_features
})); }));

View File

@@ -108,10 +108,8 @@ pub struct IndexStats {
/// Association of every field name with the number of times it occurs in the documents. /// Association of every field name with the number of times it occurs in the documents.
pub field_distribution: FieldDistribution, pub field_distribution: FieldDistribution,
/// Creation date of the index. /// Creation date of the index.
#[serde(with = "time::serde::rfc3339")]
pub created_at: OffsetDateTime, pub created_at: OffsetDateTime,
/// Date of the last update of the index. /// Date of the last update of the index.
#[serde(with = "time::serde::rfc3339")]
pub updated_at: OffsetDateTime, pub updated_at: OffsetDateTime,
} }

View File

@@ -32,6 +32,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
features: _, features: _,
max_number_of_tasks: _, max_number_of_tasks: _,
max_number_of_batched_tasks: _, max_number_of_batched_tasks: _,
compute_prefix_databases: _,
wake_up: _, wake_up: _,
dumps_path: _, dumps_path: _,
snapshots_path: _, snapshots_path: _,
@@ -177,17 +178,6 @@ fn snapshot_details(d: &Details) -> String {
} => { } => {
format!("{{ received_documents: {received_documents}, indexed_documents: {indexed_documents:?} }}") format!("{{ received_documents: {received_documents}, indexed_documents: {indexed_documents:?} }}")
} }
Details::DocumentEdition {
deleted_documents,
edited_documents,
original_filter,
context,
function,
} => {
format!(
"{{ deleted_documents: {deleted_documents:?}, edited_documents: {edited_documents:?}, context: {context:?}, function: {function:?}, original_filter: {original_filter:?} }}"
)
}
Details::SettingsUpdate { settings } => { Details::SettingsUpdate { settings } => {
format!("{{ settings: {settings:?} }}") format!("{{ settings: {settings:?} }}")
} }

View File

@@ -35,7 +35,6 @@ pub type TaskId = u32;
use std::collections::{BTreeMap, HashMap}; use std::collections::{BTreeMap, HashMap};
use std::io::{self, BufReader, Read}; use std::io::{self, BufReader, Read};
use std::ops::{Bound, RangeBounds}; use std::ops::{Bound, RangeBounds};
use std::panic::{catch_unwind, AssertUnwindSafe};
use std::path::{Path, PathBuf}; use std::path::{Path, PathBuf};
use std::sync::atomic::Ordering::{self, Relaxed}; use std::sync::atomic::Ordering::{self, Relaxed};
use std::sync::atomic::{AtomicBool, AtomicU32}; use std::sync::atomic::{AtomicBool, AtomicU32};
@@ -277,6 +276,8 @@ pub struct IndexSchedulerOptions {
pub max_number_of_batched_tasks: usize, pub max_number_of_batched_tasks: usize,
/// The experimental features enabled for this instance. /// The experimental features enabled for this instance.
pub instance_features: InstanceTogglableFeatures, pub instance_features: InstanceTogglableFeatures,
/// An experimental option to control the generation of prefix databases.
pub compute_prefix_databases: bool,
} }
/// Structure which holds meilisearch's indexes and schedules the tasks /// Structure which holds meilisearch's indexes and schedules the tasks
@@ -284,19 +285,13 @@ pub struct IndexSchedulerOptions {
pub struct IndexScheduler { pub struct IndexScheduler {
/// The LMDB environment which the DBs are associated with. /// The LMDB environment which the DBs are associated with.
pub(crate) env: Env, pub(crate) env: Env,
/// A boolean that can be set to true to stop the currently processing tasks. /// A boolean that can be set to true to stop the currently processing tasks.
pub(crate) must_stop_processing: MustStopProcessing, pub(crate) must_stop_processing: MustStopProcessing,
/// The list of tasks currently processing /// The list of tasks currently processing
pub(crate) processing_tasks: Arc<RwLock<ProcessingTasks>>, pub(crate) processing_tasks: Arc<RwLock<ProcessingTasks>>,
/// The list of files referenced by the tasks /// The list of files referenced by the tasks
pub(crate) file_store: FileStore, pub(crate) file_store: FileStore, // The main database, it contains all the tasks accessible by their Id.
// The main database, it contains all the tasks accessible by their Id.
pub(crate) all_tasks: Database<BEU32, SerdeJson<Task>>, pub(crate) all_tasks: Database<BEU32, SerdeJson<Task>>,
/// All the tasks ids grouped by their status. /// All the tasks ids grouped by their status.
// TODO we should not be able to serialize a `Status::Processing` in this database. // TODO we should not be able to serialize a `Status::Processing` in this database.
pub(crate) status: Database<SerdeBincode<Status>, RoaringBitmapCodec>, pub(crate) status: Database<SerdeBincode<Status>, RoaringBitmapCodec>,
@@ -304,58 +299,43 @@ pub struct IndexScheduler {
pub(crate) kind: Database<SerdeBincode<Kind>, RoaringBitmapCodec>, pub(crate) kind: Database<SerdeBincode<Kind>, RoaringBitmapCodec>,
/// Store the tasks associated to an index. /// Store the tasks associated to an index.
pub(crate) index_tasks: Database<Str, RoaringBitmapCodec>, pub(crate) index_tasks: Database<Str, RoaringBitmapCodec>,
/// Store the tasks that were canceled by a task uid /// Store the tasks that were canceled by a task uid
pub(crate) canceled_by: Database<BEU32, RoaringBitmapCodec>, pub(crate) canceled_by: Database<BEU32, RoaringBitmapCodec>,
/// Store the task ids of tasks which were enqueued at a specific date /// Store the task ids of tasks which were enqueued at a specific date
pub(crate) enqueued_at: Database<BEI128, CboRoaringBitmapCodec>, pub(crate) enqueued_at: Database<BEI128, CboRoaringBitmapCodec>,
/// Store the task ids of finished tasks which started being processed at a specific date /// Store the task ids of finished tasks which started being processed at a specific date
pub(crate) started_at: Database<BEI128, CboRoaringBitmapCodec>, pub(crate) started_at: Database<BEI128, CboRoaringBitmapCodec>,
/// Store the task ids of tasks which finished at a specific date /// Store the task ids of tasks which finished at a specific date
pub(crate) finished_at: Database<BEI128, CboRoaringBitmapCodec>, pub(crate) finished_at: Database<BEI128, CboRoaringBitmapCodec>,
/// In charge of creating, opening, storing and returning indexes. /// In charge of creating, opening, storing and returning indexes.
pub(crate) index_mapper: IndexMapper, pub(crate) index_mapper: IndexMapper,
/// In charge of fetching and setting the status of experimental features. /// In charge of fetching and setting the status of experimental features.
features: features::FeatureData, features: features::FeatureData,
/// Get a signal when a batch needs to be processed. /// Get a signal when a batch needs to be processed.
pub(crate) wake_up: Arc<SignalEvent>, pub(crate) wake_up: Arc<SignalEvent>,
/// Whether auto-batching is enabled or not. /// Whether auto-batching is enabled or not.
pub(crate) autobatching_enabled: bool, pub(crate) autobatching_enabled: bool,
/// Whether we should automatically cleanup the task queue or not. /// Whether we should automatically cleanup the task queue or not.
pub(crate) cleanup_enabled: bool, pub(crate) cleanup_enabled: bool,
/// The max number of tasks allowed before the scheduler starts to delete /// The max number of tasks allowed before the scheduler starts to delete
/// the finished tasks automatically. /// the finished tasks automatically.
pub(crate) max_number_of_tasks: usize, pub(crate) max_number_of_tasks: usize,
/// The maximum number of tasks that will be batched together. /// The maximum number of tasks that will be batched together.
pub(crate) max_number_of_batched_tasks: usize, pub(crate) max_number_of_batched_tasks: usize,
/// Control wether we must generate the prefix databases or not.
pub(crate) compute_prefix_databases: bool,
/// The webhook url we should send tasks to after processing every batches. /// The webhook url we should send tasks to after processing every batches.
pub(crate) webhook_url: Option<String>, pub(crate) webhook_url: Option<String>,
/// The Authorization header to send to the webhook URL. /// The Authorization header to send to the webhook URL.
pub(crate) webhook_authorization_header: Option<String>, pub(crate) webhook_authorization_header: Option<String>,
/// The path used to create the dumps. /// The path used to create the dumps.
pub(crate) dumps_path: PathBuf, pub(crate) dumps_path: PathBuf,
/// The path used to create the snapshots. /// The path used to create the snapshots.
pub(crate) snapshots_path: PathBuf, pub(crate) snapshots_path: PathBuf,
/// The path to the folder containing the auth LMDB env. /// The path to the folder containing the auth LMDB env.
pub(crate) auth_path: PathBuf, pub(crate) auth_path: PathBuf,
/// The path to the version file of Meilisearch. /// The path to the version file of Meilisearch.
pub(crate) version_file_path: PathBuf, pub(crate) version_file_path: PathBuf,
embedders: Arc<RwLock<HashMap<EmbedderOptions, Arc<Embedder>>>>, embedders: Arc<RwLock<HashMap<EmbedderOptions, Arc<Embedder>>>>,
// ================= test // ================= test
@@ -365,13 +345,11 @@ pub struct IndexScheduler {
/// See [self.breakpoint()](`IndexScheduler::breakpoint`) for an explanation. /// See [self.breakpoint()](`IndexScheduler::breakpoint`) for an explanation.
#[cfg(test)] #[cfg(test)]
test_breakpoint_sdr: crossbeam::channel::Sender<(Breakpoint, bool)>, test_breakpoint_sdr: crossbeam::channel::Sender<(Breakpoint, bool)>,
/// A list of planned failures within the [`tick`](IndexScheduler::tick) method of the index scheduler. /// A list of planned failures within the [`tick`](IndexScheduler::tick) method of the index scheduler.
/// ///
/// The first field is the iteration index and the second field identifies a location in the code. /// The first field is the iteration index and the second field identifies a location in the code.
#[cfg(test)] #[cfg(test)]
planned_failures: Vec<(usize, tests::FailureLocation)>, planned_failures: Vec<(usize, tests::FailureLocation)>,
/// A counter that is incremented before every call to [`tick`](IndexScheduler::tick) /// A counter that is incremented before every call to [`tick`](IndexScheduler::tick)
#[cfg(test)] #[cfg(test)]
run_loop_iteration: Arc<RwLock<usize>>, run_loop_iteration: Arc<RwLock<usize>>,
@@ -398,6 +376,7 @@ impl IndexScheduler {
cleanup_enabled: self.cleanup_enabled, cleanup_enabled: self.cleanup_enabled,
max_number_of_tasks: self.max_number_of_tasks, max_number_of_tasks: self.max_number_of_tasks,
max_number_of_batched_tasks: self.max_number_of_batched_tasks, max_number_of_batched_tasks: self.max_number_of_batched_tasks,
compute_prefix_databases: self.compute_prefix_databases,
snapshots_path: self.snapshots_path.clone(), snapshots_path: self.snapshots_path.clone(),
dumps_path: self.dumps_path.clone(), dumps_path: self.dumps_path.clone(),
auth_path: self.auth_path.clone(), auth_path: self.auth_path.clone(),
@@ -500,6 +479,7 @@ impl IndexScheduler {
cleanup_enabled: options.cleanup_enabled, cleanup_enabled: options.cleanup_enabled,
max_number_of_tasks: options.max_number_of_tasks, max_number_of_tasks: options.max_number_of_tasks,
max_number_of_batched_tasks: options.max_number_of_batched_tasks, max_number_of_batched_tasks: options.max_number_of_batched_tasks,
compute_prefix_databases: options.compute_prefix_databases,
dumps_path: options.dumps_path, dumps_path: options.dumps_path,
snapshots_path: options.snapshots_path, snapshots_path: options.snapshots_path,
auth_path: options.auth_path, auth_path: options.auth_path,
@@ -613,24 +593,19 @@ impl IndexScheduler {
#[cfg(test)] #[cfg(test)]
run.breakpoint(Breakpoint::Init); run.breakpoint(Breakpoint::Init);
run.wake_up.wait_timeout(std::time::Duration::from_secs(60)); run.wake_up.wait();
loop { loop {
let ret = catch_unwind(AssertUnwindSafe(|| run.tick())); match run.tick() {
match ret { Ok(TickOutcome::TickAgain(_)) => (),
Ok(Ok(TickOutcome::TickAgain(_))) => (), Ok(TickOutcome::WaitForSignal) => run.wake_up.wait(),
Ok(Ok(TickOutcome::WaitForSignal)) => run.wake_up.wait(), Err(e) => {
Ok(Err(e)) => {
tracing::error!("{e}"); tracing::error!("{e}");
// Wait one second when an irrecoverable error occurs. // Wait one second when an irrecoverable error occurs.
if !e.is_recoverable() { if !e.is_recoverable() {
std::thread::sleep(Duration::from_secs(1)); std::thread::sleep(Duration::from_secs(1));
} }
} }
Err(_panic) => {
tracing::error!("Internal error: Unexpected panic in the `IndexScheduler::run` method.");
}
} }
} }
}) })
@@ -668,11 +643,7 @@ impl IndexScheduler {
let rtxn = self.env.read_txn()?; let rtxn = self.env.read_txn()?;
self.index_mapper.index(&rtxn, name) self.index_mapper.index(&rtxn, name)
} }
/// Return the boolean referring if index exists.
pub fn index_exists(&self, name: &str) -> Result<bool> {
let rtxn = self.env.read_txn()?;
self.index_mapper.index_exists(&rtxn, name)
}
/// Return the name of all indexes without opening them. /// Return the name of all indexes without opening them.
pub fn index_names(&self) -> Result<Vec<String>> { pub fn index_names(&self) -> Result<Vec<String>> {
let rtxn = self.env.read_txn()?; let rtxn = self.env.read_txn()?;
@@ -1613,14 +1584,6 @@ impl<'a> Dump<'a> {
index_uid: task.index_uid.ok_or(Error::CorruptedDump)?, index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
} }
} }
KindDump::DocumentEdition { filter, context, function } => {
KindWithContent::DocumentEdition {
index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
filter_expr: filter,
context,
function,
}
}
KindDump::DocumentClear => KindWithContent::DocumentClear { KindDump::DocumentClear => KindWithContent::DocumentClear {
index_uid: task.index_uid.ok_or(Error::CorruptedDump)?, index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
}, },
@@ -1764,7 +1727,6 @@ mod tests {
use crossbeam::channel::RecvTimeoutError; use crossbeam::channel::RecvTimeoutError;
use file_store::File; use file_store::File;
use insta::assert_json_snapshot; use insta::assert_json_snapshot;
use maplit::btreeset;
use meili_snap::{json_string, snapshot}; use meili_snap::{json_string, snapshot};
use meilisearch_auth::AuthFilter; use meilisearch_auth::AuthFilter;
use meilisearch_types::document_formats::DocumentFormatError; use meilisearch_types::document_formats::DocumentFormatError;
@@ -1830,7 +1792,7 @@ mod tests {
task_db_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose. task_db_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose. index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
enable_mdb_writemap: false, enable_mdb_writemap: false,
index_growth_amount: 1000 * 1000 * 1000 * 1000, // 1 TB index_growth_amount: 1000 * 1000, // 1 MB
index_count: 5, index_count: 5,
indexer_config, indexer_config,
autobatching_enabled: true, autobatching_enabled: true,
@@ -1838,6 +1800,7 @@ mod tests {
max_number_of_tasks: 1_000_000, max_number_of_tasks: 1_000_000,
max_number_of_batched_tasks: usize::MAX, max_number_of_batched_tasks: usize::MAX,
instance_features: Default::default(), instance_features: Default::default(),
compute_prefix_databases: true,
}; };
configuration(&mut options); configuration(&mut options);
@@ -2554,117 +2517,6 @@ mod tests {
snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents"); snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
} }
#[test]
fn fail_in_process_batch_for_document_deletion() {
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
use meilisearch_types::settings::{Settings, Unchecked};
let mut new_settings: Box<Settings<Unchecked>> = Box::default();
new_settings.filterable_attributes = Setting::Set(btreeset!(S("catto")));
index_scheduler
.register(
KindWithContent::SettingsUpdate {
index_uid: S("doggos"),
new_settings,
is_deletion: false,
allow_index_creation: true,
},
None,
false,
)
.unwrap();
let content = r#"[
{ "id": 1, "doggo": "jean bob" },
{ "id": 2, "catto": "jorts" },
{ "id": 3, "doggo": "bork" }
]"#;
let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
let documents_count = read_json(content.as_bytes(), &mut file).unwrap();
file.persist().unwrap();
index_scheduler
.register(
KindWithContent::DocumentAdditionOrUpdate {
index_uid: S("doggos"),
primary_key: Some(S("id")),
method: ReplaceDocuments,
content_file: uuid,
documents_count,
allow_index_creation: true,
},
None,
false,
)
.unwrap();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_setting_and_document_addition");
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_adding_the_settings");
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_adding_the_documents");
index_scheduler
.register(
KindWithContent::DocumentDeletion {
index_uid: S("doggos"),
documents_ids: vec![S("1")],
},
None,
false,
)
.unwrap();
// This one should not be catched by Meilisearch but it's still nice to handle it because if one day we break the filters it could happens
index_scheduler
.register(
KindWithContent::DocumentDeletionByFilter {
index_uid: S("doggos"),
filter_expr: serde_json::json!(true),
},
None,
false,
)
.unwrap();
// Should fail because the ids are not filterable
index_scheduler
.register(
KindWithContent::DocumentDeletionByFilter {
index_uid: S("doggos"),
filter_expr: serde_json::json!("id = 2"),
},
None,
false,
)
.unwrap();
index_scheduler
.register(
KindWithContent::DocumentDeletionByFilter {
index_uid: S("doggos"),
filter_expr: serde_json::json!("catto EXISTS"),
},
None,
false,
)
.unwrap();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_document_deletions");
// Everything should be batched together
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_removing_the_documents");
let index = index_scheduler.index("doggos").unwrap();
let rtxn = index.read_txn().unwrap();
let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
let field_ids = field_ids_map.ids().collect::<Vec<_>>();
let documents = index
.all_documents(&rtxn)
.unwrap()
.map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
.collect::<Vec<_>>();
snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents_remaining_should_only_be_bork");
}
#[test] #[test]
fn do_not_batch_task_of_different_indexes() { fn do_not_batch_task_of_different_indexes() {
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]); let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
@@ -3165,8 +3017,6 @@ mod tests {
api_key: Setting::Set(S("My super secret")), api_key: Setting::Set(S("My super secret")),
url: Setting::Set(S("http://localhost:7777")), url: Setting::Set(S("http://localhost:7777")),
dimensions: Setting::Set(4), dimensions: Setting::Set(4),
request: Setting::Set(serde_json::json!("{{text}}")),
response: Setting::Set(serde_json::json!("{{embedding}}")),
..Default::default() ..Default::default()
}; };
embedders.insert(S("default"), Setting::Set(embedding_settings)); embedders.insert(S("default"), Setting::Set(embedding_settings));
@@ -3919,15 +3769,15 @@ mod tests {
]); ]);
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_10_tasks"); snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_10_tasks");
// The index should not exist. // The index should not exists.
snapshot!(matches!(index_scheduler.index_exists("doggos"), Ok(true)), @"false"); snapshot!(format!("{}", index_scheduler.index("doggos").map(|_| ()).unwrap_err()), @"Index `doggos` not found.");
} }
#[test] #[test]
fn test_document_addition_cant_create_index_without_index_without_autobatching() { fn test_document_addition_cant_create_index_without_index_without_autobatching() {
// We're going to execute multiple document addition that don't have // We're going to execute multiple document addition that don't have
// the right to create an index while there is no index currently. // the right to create an index while there is no index currently.
// Since the auto-batching is disabled, every task should be processed // Since the autobatching is disabled, every tasks should be processed
// sequentially and throw an IndexDoesNotExists. // sequentially and throw an IndexDoesNotExists.
let (index_scheduler, mut handle) = IndexScheduler::test(false, vec![]); let (index_scheduler, mut handle) = IndexScheduler::test(false, vec![]);
@@ -3969,8 +3819,8 @@ mod tests {
handle.advance_n_failed_batches(5); handle.advance_n_failed_batches(5);
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "all_tasks_processed"); snapshot!(snapshot_index_scheduler(&index_scheduler), name: "all_tasks_processed");
// The index should not exist. // The index should not exists.
snapshot!(matches!(index_scheduler.index_exists("doggos"), Ok(true)), @"false"); snapshot!(format!("{}", index_scheduler.index("doggos").map(|_| ()).unwrap_err()), @"Index `doggos` not found.");
} }
#[test] #[test]
@@ -4876,7 +4726,6 @@ mod tests {
"types": { "types": {
"documentAdditionOrUpdate": 0, "documentAdditionOrUpdate": 0,
"documentDeletion": 0, "documentDeletion": 0,
"documentEdition": 0,
"dumpCreation": 0, "dumpCreation": 0,
"indexCreation": 3, "indexCreation": 3,
"indexDeletion": 0, "indexDeletion": 0,
@@ -4908,7 +4757,6 @@ mod tests {
"types": { "types": {
"documentAdditionOrUpdate": 0, "documentAdditionOrUpdate": 0,
"documentDeletion": 0, "documentDeletion": 0,
"documentEdition": 0,
"dumpCreation": 0, "dumpCreation": 0,
"indexCreation": 3, "indexCreation": 3,
"indexDeletion": 0, "indexDeletion": 0,
@@ -4947,7 +4795,6 @@ mod tests {
"types": { "types": {
"documentAdditionOrUpdate": 0, "documentAdditionOrUpdate": 0,
"documentDeletion": 0, "documentDeletion": 0,
"documentEdition": 0,
"dumpCreation": 0, "dumpCreation": 0,
"indexCreation": 3, "indexCreation": 3,
"indexDeletion": 0, "indexDeletion": 0,
@@ -4987,7 +4834,6 @@ mod tests {
"types": { "types": {
"documentAdditionOrUpdate": 0, "documentAdditionOrUpdate": 0,
"documentDeletion": 0, "documentDeletion": 0,
"documentEdition": 0,
"dumpCreation": 0, "dumpCreation": 0,
"indexCreation": 3, "indexCreation": 3,
"indexDeletion": 0, "indexDeletion": 0,
@@ -5126,8 +4972,6 @@ mod tests {
api_key: Setting::Set(S("My super secret")), api_key: Setting::Set(S("My super secret")),
url: Setting::Set(S("http://localhost:7777")), url: Setting::Set(S("http://localhost:7777")),
dimensions: Setting::Set(384), dimensions: Setting::Set(384),
request: Setting::Set(serde_json::json!("{{text}}")),
response: Setting::Set(serde_json::json!("{{embedding}}")),
..Default::default() ..Default::default()
}; };
embedders.insert(S("A_fakerest"), Setting::Set(embedding_settings)); embedders.insert(S("A_fakerest"), Setting::Set(embedding_settings));

View File

@@ -8,9 +8,7 @@ expression: task.details
"source": "rest", "source": "rest",
"apiKey": "MyXXXX...", "apiKey": "MyXXXX...",
"dimensions": 384, "dimensions": 384,
"url": "http://localhost:7777", "url": "http://localhost:7777"
"request": "{{text}}",
"response": "{{embedding}}"
}, },
"B_small_hf": { "B_small_hf": {
"source": "huggingFace", "source": "huggingFace",

View File

@@ -8,8 +8,16 @@ expression: fakerest_config.embedder_options
"distribution": null, "distribution": null,
"dimensions": 384, "dimensions": 384,
"url": "http://localhost:7777", "url": "http://localhost:7777",
"request": "{{text}}", "query": null,
"response": "{{embedding}}", "input_field": [
"headers": {} "input"
],
"path_to_embeddings": [
"data"
],
"embedding_object": [
"embedding"
],
"input_type": "text"
} }
} }

View File

@@ -8,9 +8,7 @@ expression: task.details
"source": "rest", "source": "rest",
"apiKey": "MyXXXX...", "apiKey": "MyXXXX...",
"dimensions": 384, "dimensions": 384,
"url": "http://localhost:7777", "url": "http://localhost:7777"
"request": "{{text}}",
"response": "{{embedding}}"
}, },
"B_small_hf": { "B_small_hf": {
"source": "huggingFace", "source": "huggingFace",

View File

@@ -8,9 +8,7 @@ expression: task.details
"source": "rest", "source": "rest",
"apiKey": "MyXXXX...", "apiKey": "MyXXXX...",
"dimensions": 4, "dimensions": 4,
"url": "http://localhost:7777", "url": "http://localhost:7777"
"request": "{{text}}",
"response": "{{embedding}}"
} }
} }
} }

View File

@@ -1,6 +1,6 @@
--- ---
source: index-scheduler/src/lib.rs source: index-scheduler/src/lib.rs
expression: config.embedder_options expression: embedding_config.embedder_options
--- ---
{ {
"Rest": { "Rest": {
@@ -8,8 +8,16 @@ expression: config.embedder_options
"distribution": null, "distribution": null,
"dimensions": 4, "dimensions": 4,
"url": "http://localhost:7777", "url": "http://localhost:7777",
"request": "{{text}}", "query": null,
"response": "{{embedding}}", "input_field": [
"headers": {} "input"
],
"path_to_embeddings": [
"data"
],
"embedding_object": [
"embedding"
],
"input_type": "text"
} }
} }

View File

@@ -8,9 +8,7 @@ expression: task.details
"source": "rest", "source": "rest",
"apiKey": "MyXXXX...", "apiKey": "MyXXXX...",
"dimensions": 4, "dimensions": 4,
"url": "http://localhost:7777", "url": "http://localhost:7777"
"request": "{{text}}",
"response": "{{embedding}}"
} }
} }
} }

View File

@@ -1,44 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
----------------------------------------------------------------------
### Status:
enqueued []
succeeded [0,1,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,43 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
----------------------------------------------------------------------
### Status:
enqueued [1,]
succeeded [0,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
----------------------------------------------------------------------
### File Store:
00000000-0000-0000-0000-000000000000
----------------------------------------------------------------------

View File

@@ -1,43 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
----------------------------------------------------------------------
### Status:
enqueued [1,]
succeeded [0,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
----------------------------------------------------------------------
### File Store:
00000000-0000-0000-0000-000000000000
----------------------------------------------------------------------

View File

@@ -1,56 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
2 {uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
4 {uid: 4, status: failed, error: ResponseError { code: 200, message: "Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
5 {uid: 5, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
----------------------------------------------------------------------
### Status:
enqueued []
succeeded [0,1,2,5,]
failed [3,4,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"documentDeletion" [2,3,4,5,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,2,3,4,5,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
[timestamp] [3,]
[timestamp] [4,]
[timestamp] [5,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,3,4,5,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,3,4,5,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

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

View File

@@ -1,53 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
2 {uid: 2, status: enqueued, details: { received_document_ids: 1, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
3 {uid: 3, status: enqueued, details: { original_filter: true, deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
4 {uid: 4, status: enqueued, details: { original_filter: "id = 2", deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
5 {uid: 5, status: enqueued, details: { original_filter: "catto EXISTS", deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
----------------------------------------------------------------------
### Status:
enqueued [2,3,4,5,]
succeeded [0,1,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"documentDeletion" [2,3,4,5,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,2,3,4,5,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
[timestamp] [3,]
[timestamp] [4,]
[timestamp] [5,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,39 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
### Autobatching Enabled = true
### Processing Tasks:
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
----------------------------------------------------------------------
### Status:
enqueued [0,1,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,]
----------------------------------------------------------------------
### Index Mapper:
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Started At:
----------------------------------------------------------------------
### Finished At:
----------------------------------------------------------------------
### File Store:
00000000-0000-0000-0000-000000000000
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }} 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }} 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
@@ -46,3 +46,4 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
### File Store: ### File Store:
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }} 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }} 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
@@ -45,3 +45,4 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
00000000-0000-0000-0000-000000000001 00000000-0000-0000-0000-000000000001
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }} 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
### Status: ### Status:
@@ -42,3 +42,4 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
### File Store: ### File Store:
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }} 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
### Status: ### Status:
@@ -41,3 +41,4 @@ doggos: { number_of_documents: 0, field_distribution: {} }
00000000-0000-0000-0000-000000000000 00000000-0000-0000-0000-000000000000
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
### Status: ### Status:
enqueued [0,] enqueued [0,]
@@ -33,3 +33,4 @@ doggos [0,]
### File Store: ### File Store:
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
### Status: ### Status:
enqueued [] enqueued []
@@ -37,3 +37,4 @@ doggos: { number_of_documents: 0, field_distribution: {} }
### File Store: ### File Store:
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
### Status: ### Status:
enqueued [0,] enqueued [0,]
@@ -33,3 +33,4 @@ doggos [0,]
### File Store: ### File Store:
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[] []
---------------------------------------------------------------------- ----------------------------------------------------------------------
### All Tasks: ### All Tasks:
0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }} 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
---------------------------------------------------------------------- ----------------------------------------------------------------------
### Status: ### Status:
enqueued [] enqueued []
@@ -37,3 +37,4 @@ doggos: { number_of_documents: 0, field_distribution: {} }
### File Store: ### File Store:
---------------------------------------------------------------------- ----------------------------------------------------------------------

View File

@@ -238,7 +238,6 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
let mut index_uids = vec![]; let mut index_uids = vec![];
match &mut task.kind { match &mut task.kind {
K::DocumentAdditionOrUpdate { index_uid, .. } => index_uids.push(index_uid), K::DocumentAdditionOrUpdate { index_uid, .. } => index_uids.push(index_uid),
K::DocumentEdition { index_uid, .. } => index_uids.push(index_uid),
K::DocumentDeletion { index_uid, .. } => index_uids.push(index_uid), K::DocumentDeletion { index_uid, .. } => index_uids.push(index_uid),
K::DocumentDeletionByFilter { index_uid, .. } => index_uids.push(index_uid), K::DocumentDeletionByFilter { index_uid, .. } => index_uids.push(index_uid),
K::DocumentClear { index_uid } => index_uids.push(index_uid), K::DocumentClear { index_uid } => index_uids.push(index_uid),
@@ -409,26 +408,7 @@ impl IndexScheduler {
match status { match status {
Status::Succeeded => assert!(indexed_documents <= received_documents), Status::Succeeded => assert!(indexed_documents <= received_documents),
Status::Failed | Status::Canceled => assert_eq!(indexed_documents, 0), Status::Failed | Status::Canceled => assert_eq!(indexed_documents, 0),
status => panic!("DocumentAddition can't have an indexed_documents set if it's {}", status), status => panic!("DocumentAddition can't have an indexed_document set if it's {}", status),
}
}
None => {
assert!(matches!(status, Status::Enqueued | Status::Processing))
}
}
}
Details::DocumentEdition { edited_documents, .. } => {
assert_eq!(kind.as_kind(), Kind::DocumentEdition);
match edited_documents {
Some(edited_documents) => {
assert!(matches!(
status,
Status::Succeeded | Status::Failed | Status::Canceled
));
match status {
Status::Succeeded => (),
Status::Failed | Status::Canceled => assert_eq!(edited_documents, 0),
status => panic!("DocumentEdition can't have an edited_documents set if it's {}", status),
} }
} }
None => { None => {

View File

@@ -11,6 +11,6 @@ edition.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
insta = { version = "^1.39.0", features = ["json", "redactions"] } insta = { version = "^1.34.0", features = ["json", "redactions"] }
md5 = "0.7.0" md5 = "0.7.0"
once_cell = "1.19" once_cell = "1.19"

View File

@@ -11,16 +11,16 @@ edition.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
base64 = "0.22.1" base64 = "0.21.7"
enum-iterator = "2.1.0" enum-iterator = "1.5.0"
hmac = "0.12.1" hmac = "0.12.1"
maplit = "1.0.2" maplit = "1.0.2"
meilisearch-types = { path = "../meilisearch-types" } meilisearch-types = { path = "../meilisearch-types" }
rand = "0.8.5" rand = "0.8.5"
roaring = { version = "0.10.6", features = ["serde"] } roaring = { version = "0.10.2", features = ["serde"] }
serde = { version = "1.0.204", features = ["derive"] } serde = { version = "1.0.195", features = ["derive"] }
serde_json = { version = "1.0.120", features = ["preserve_order"] } serde_json = { version = "1.0.111", features = ["preserve_order"] }
sha2 = "0.10.8" sha2 = "0.10.8"
thiserror = "1.0.61" thiserror = "1.0.56"
time = { version = "0.3.36", features = ["serde-well-known", "formatting", "parsing", "macros"] } time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
uuid = { version = "1.10.0", features = ["serde", "v4"] } uuid = { version = "1.6.1", features = ["serde", "v4"] }

View File

@@ -188,12 +188,6 @@ impl AuthFilter {
self.allow_index_creation && self.is_index_authorized(index) self.allow_index_creation && self.is_index_authorized(index)
} }
#[inline]
/// Return true if a tenant token was used to generate the search rules.
pub fn is_tenant_token(&self) -> bool {
self.search_rules.is_some()
}
pub fn with_allowed_indexes(allowed_indexes: HashSet<IndexUidPattern>) -> Self { pub fn with_allowed_indexes(allowed_indexes: HashSet<IndexUidPattern>) -> Self {
Self { Self {
search_rules: None, search_rules: None,
@@ -211,7 +205,6 @@ impl AuthFilter {
.unwrap_or(true) .unwrap_or(true)
} }
/// Check if the index is authorized by the API key and the tenant token.
pub fn is_index_authorized(&self, index: &str) -> bool { pub fn is_index_authorized(&self, index: &str) -> bool {
self.key_authorized_indexes.is_index_authorized(index) self.key_authorized_indexes.is_index_authorized(index)
&& self && self
@@ -221,44 +214,6 @@ impl AuthFilter {
.unwrap_or(true) .unwrap_or(true)
} }
/// Only check if the index is authorized by the API key
pub fn api_key_is_index_authorized(&self, index: &str) -> bool {
self.key_authorized_indexes.is_index_authorized(index)
}
/// Only check if the index is authorized by the tenant token
pub fn tenant_token_is_index_authorized(&self, index: &str) -> bool {
self.search_rules
.as_ref()
.map(|search_rules| search_rules.is_index_authorized(index))
.unwrap_or(true)
}
/// Return the list of authorized indexes by the tenant token if any
pub fn tenant_token_list_index_authorized(&self) -> Vec<String> {
match self.search_rules {
Some(ref search_rules) => {
let mut indexes: Vec<_> = match search_rules {
SearchRules::Set(set) => set.iter().map(|s| s.to_string()).collect(),
SearchRules::Map(map) => map.keys().map(|s| s.to_string()).collect(),
};
indexes.sort_unstable();
indexes
}
None => Vec::new(),
}
}
/// Return the list of authorized indexes by the api key if any
pub fn api_key_list_index_authorized(&self) -> Vec<String> {
let mut indexes: Vec<_> = match self.key_authorized_indexes {
SearchRules::Set(ref set) => set.iter().map(|s| s.to_string()).collect(),
SearchRules::Map(ref map) => map.keys().map(|s| s.to_string()).collect(),
};
indexes.sort_unstable();
indexes
}
pub fn get_index_search_rules(&self, index: &str) -> Option<IndexSearchRules> { pub fn get_index_search_rules(&self, index: &str) -> Option<IndexSearchRules> {
if !self.is_index_authorized(index) { if !self.is_index_authorized(index) {
return None; return None;

View File

@@ -11,36 +11,36 @@ edition.workspace = true
license.workspace = true license.workspace = true
[dependencies] [dependencies]
actix-web = { version = "4.8.0", default-features = false } actix-web = { version = "4.6.0", default-features = false }
anyhow = "1.0.86" anyhow = "1.0.79"
convert_case = "0.6.0" convert_case = "0.6.0"
csv = "1.3.0" csv = "1.3.0"
deserr = { version = "0.6.2", features = ["actix-web"] } deserr = { version = "0.6.1", features = ["actix-web"] }
either = { version = "1.13.0", features = ["serde"] } either = { version = "1.9.0", features = ["serde"] }
enum-iterator = "2.1.0" enum-iterator = "1.5.0"
file-store = { path = "../file-store" } file-store = { path = "../file-store" }
flate2 = "1.0.30" flate2 = "1.0.28"
fst = "0.4.7" fst = "0.4.7"
memmap2 = "0.9.4" memmap2 = "0.7.1"
milli = { path = "../milli" } milli = { path = "../milli" }
roaring = { version = "0.10.6", features = ["serde"] } roaring = { version = "0.10.2", features = ["serde"] }
serde = { version = "1.0.204", features = ["derive"] } serde = { version = "1.0.195", features = ["derive"] }
serde-cs = "0.2.4" serde-cs = "0.2.4"
serde_json = "1.0.120" serde_json = "1.0.111"
tar = "0.4.41" tar = "0.4.40"
tempfile = "3.10.1" tempfile = "3.9.0"
thiserror = "1.0.61" thiserror = "1.0.56"
time = { version = "0.3.36", features = [ time = { version = "0.3.31", features = [
"serde-well-known", "serde-well-known",
"formatting", "formatting",
"parsing", "parsing",
"macros", "macros",
] } ] }
tokio = "1.38" tokio = "1.35"
uuid = { version = "1.10.0", features = ["serde", "v4"] } uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies] [dev-dependencies]
insta = "1.39.0" insta = "1.34.0"
meili-snap = { path = "../meili-snap" } meili-snap = { path = "../meili-snap" }
[features] [features]
@@ -54,8 +54,6 @@ chinese-pinyin = ["milli/chinese-pinyin"]
hebrew = ["milli/hebrew"] hebrew = ["milli/hebrew"]
# japanese specialized tokenization # japanese specialized tokenization
japanese = ["milli/japanese"] japanese = ["milli/japanese"]
# korean specialized tokenization
korean = ["milli/korean"]
# thai specialized tokenization # thai specialized tokenization
thai = ["milli/thai"] thai = ["milli/thai"]
# allow greek specialized tokenization # allow greek specialized tokenization

View File

@@ -155,10 +155,6 @@ make_missing_field_convenience_builder!(
MissingFacetSearchFacetName, MissingFacetSearchFacetName,
missing_facet_search_facet_name missing_facet_search_facet_name
); );
make_missing_field_convenience_builder!(
MissingDocumentEditionFunction,
missing_document_edition_function
);
// Integrate a sub-error into a [`DeserrError`] by taking its error message but using // Integrate a sub-error into a [`DeserrError`] by taking its error message but using
// the default error code (C) from `Self` // the default error code (C) from `Self`
@@ -192,7 +188,6 @@ merge_with_error_impl_take_error_message!(ParseOffsetDateTimeError);
merge_with_error_impl_take_error_message!(ParseTaskKindError); merge_with_error_impl_take_error_message!(ParseTaskKindError);
merge_with_error_impl_take_error_message!(ParseTaskStatusError); merge_with_error_impl_take_error_message!(ParseTaskStatusError);
merge_with_error_impl_take_error_message!(IndexUidFormatError); merge_with_error_impl_take_error_message!(IndexUidFormatError);
merge_with_error_impl_take_error_message!(InvalidMultiSearchWeight);
merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio); merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);
merge_with_error_impl_take_error_message!(InvalidSearchRankingScoreThreshold); merge_with_error_impl_take_error_message!(InvalidSearchRankingScoreThreshold);
merge_with_error_impl_take_error_message!(InvalidSimilarRankingScoreThreshold); merge_with_error_impl_take_error_message!(InvalidSimilarRankingScoreThreshold);

View File

@@ -224,7 +224,6 @@ InvalidDocumentCsvDelimiter , InvalidRequest , BAD_REQUEST ;
InvalidDocumentFields , InvalidRequest , BAD_REQUEST ; InvalidDocumentFields , InvalidRequest , BAD_REQUEST ;
InvalidDocumentRetrieveVectors , InvalidRequest , BAD_REQUEST ; InvalidDocumentRetrieveVectors , InvalidRequest , BAD_REQUEST ;
MissingDocumentFilter , InvalidRequest , BAD_REQUEST ; MissingDocumentFilter , InvalidRequest , BAD_REQUEST ;
MissingDocumentEditionFunction , InvalidRequest , BAD_REQUEST ;
InvalidDocumentFilter , InvalidRequest , BAD_REQUEST ; InvalidDocumentFilter , InvalidRequest , BAD_REQUEST ;
InvalidDocumentGeoField , InvalidRequest , BAD_REQUEST ; InvalidDocumentGeoField , InvalidRequest , BAD_REQUEST ;
InvalidVectorDimensions , InvalidRequest , BAD_REQUEST ; InvalidVectorDimensions , InvalidRequest , BAD_REQUEST ;
@@ -238,11 +237,6 @@ InvalidIndexLimit , InvalidRequest , BAD_REQUEST ;
InvalidIndexOffset , InvalidRequest , BAD_REQUEST ; InvalidIndexOffset , InvalidRequest , BAD_REQUEST ;
InvalidIndexPrimaryKey , InvalidRequest , BAD_REQUEST ; InvalidIndexPrimaryKey , InvalidRequest , BAD_REQUEST ;
InvalidIndexUid , InvalidRequest , BAD_REQUEST ; InvalidIndexUid , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFederated , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFederationOptions , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchQueryPagination , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchQueryRankingRules , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchWeight , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToSearchOn , InvalidRequest , BAD_REQUEST ; InvalidSearchAttributesToSearchOn , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToCrop , InvalidRequest , BAD_REQUEST ; InvalidSearchAttributesToCrop , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToHighlight , InvalidRequest , BAD_REQUEST ; InvalidSearchAttributesToHighlight , InvalidRequest , BAD_REQUEST ;
@@ -256,7 +250,6 @@ InvalidSearchCropLength , InvalidRequest , BAD_REQUEST ;
InvalidSearchCropMarker , InvalidRequest , BAD_REQUEST ; InvalidSearchCropMarker , InvalidRequest , BAD_REQUEST ;
InvalidSearchFacets , InvalidRequest , BAD_REQUEST ; InvalidSearchFacets , InvalidRequest , BAD_REQUEST ;
InvalidSearchSemanticRatio , InvalidRequest , BAD_REQUEST ; InvalidSearchSemanticRatio , InvalidRequest , BAD_REQUEST ;
InvalidSearchLocales , InvalidRequest , BAD_REQUEST ;
InvalidFacetSearchFacetName , InvalidRequest , BAD_REQUEST ; InvalidFacetSearchFacetName , InvalidRequest , BAD_REQUEST ;
InvalidSimilarId , InvalidRequest , BAD_REQUEST ; InvalidSimilarId , InvalidRequest , BAD_REQUEST ;
InvalidSearchFilter , InvalidRequest , BAD_REQUEST ; InvalidSearchFilter , InvalidRequest , BAD_REQUEST ;
@@ -298,7 +291,6 @@ InvalidSettingsSeparatorTokens , InvalidRequest , BAD_REQUEST ;
InvalidSettingsDictionary , InvalidRequest , BAD_REQUEST ; InvalidSettingsDictionary , InvalidRequest , BAD_REQUEST ;
InvalidSettingsSynonyms , InvalidRequest , BAD_REQUEST ; InvalidSettingsSynonyms , InvalidRequest , BAD_REQUEST ;
InvalidSettingsTypoTolerance , InvalidRequest , BAD_REQUEST ; InvalidSettingsTypoTolerance , InvalidRequest , BAD_REQUEST ;
InvalidSettingsLocalizedAttributes , InvalidRequest , BAD_REQUEST ;
InvalidState , Internal , INTERNAL_SERVER_ERROR ; InvalidState , Internal , INTERNAL_SERVER_ERROR ;
InvalidStoreFile , Internal , INTERNAL_SERVER_ERROR ; InvalidStoreFile , Internal , INTERNAL_SERVER_ERROR ;
InvalidSwapDuplicateIndexFound , InvalidRequest , BAD_REQUEST ; InvalidSwapDuplicateIndexFound , InvalidRequest , BAD_REQUEST ;
@@ -344,10 +336,7 @@ UnsupportedMediaType , InvalidRequest , UNSUPPORTED_MEDIA
// Experimental features // Experimental features
VectorEmbeddingError , InvalidRequest , BAD_REQUEST ; VectorEmbeddingError , InvalidRequest , BAD_REQUEST ;
NotFoundSimilarId , InvalidRequest , BAD_REQUEST ; NotFoundSimilarId , InvalidRequest , BAD_REQUEST
InvalidDocumentEditionContext , InvalidRequest , BAD_REQUEST ;
InvalidDocumentEditionFunctionFilter , InvalidRequest , BAD_REQUEST ;
EditDocumentsByFunctionError , InvalidRequest , BAD_REQUEST
} }
impl ErrorCode for JoinError { impl ErrorCode for JoinError {
@@ -417,15 +406,7 @@ impl ErrorCode for milli::Error {
Code::InvalidSettingsTypoTolerance Code::InvalidSettingsTypoTolerance
} }
UserError::InvalidEmbedder(_) => Code::InvalidEmbedder, UserError::InvalidEmbedder(_) => Code::InvalidEmbedder,
UserError::VectorEmbeddingError(_) | UserError::DocumentEmbeddingError(_) => { UserError::VectorEmbeddingError(_) => Code::VectorEmbeddingError,
Code::VectorEmbeddingError
}
UserError::DocumentEditionCannotModifyPrimaryKey
| UserError::DocumentEditionDocumentMustBeObject
| UserError::DocumentEditionRuntimeError(_)
| UserError::DocumentEditionCompilationError(_) => {
Code::EditDocumentsByFunctionError
}
} }
} }
} }
@@ -521,12 +502,6 @@ impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
} }
} }
impl fmt::Display for deserr_codes::InvalidMultiSearchWeight {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "the value of `weight` is invalid, expected a positive float (>= 0.0).")
}
}
impl fmt::Display for deserr_codes::InvalidSimilarId { impl fmt::Display for deserr_codes::InvalidSimilarId {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!( write!(

View File

@@ -6,13 +6,10 @@ pub struct RuntimeTogglableFeatures {
pub vector_store: bool, pub vector_store: bool,
pub metrics: bool, pub metrics: bool,
pub logs_route: bool, pub logs_route: bool,
pub edit_documents_by_function: bool,
pub contains_filter: bool,
} }
#[derive(Default, Debug, Clone, Copy)] #[derive(Default, Debug, Clone, Copy)]
pub struct InstanceTogglableFeatures { pub struct InstanceTogglableFeatures {
pub metrics: bool, pub metrics: bool,
pub logs_route: bool, pub logs_route: bool,
pub contains_filter: bool,
} }

View File

@@ -7,7 +7,6 @@ pub mod features;
pub mod index_uid; pub mod index_uid;
pub mod index_uid_pattern; pub mod index_uid_pattern;
pub mod keys; pub mod keys;
pub mod locales;
pub mod settings; pub mod settings;
pub mod star_or; pub mod star_or;
pub mod task_view; pub mod task_view;

View File

@@ -1,158 +0,0 @@
use deserr::Deserr;
use milli::LocalizedAttributesRule;
use serde::{Deserialize, Serialize};
use serde_json::json;
/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
///
/// this enum implements `Deserr` in order to be used in the API.
macro_rules! make_locale {
($($language:tt), +) => {
#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
#[deserr(rename_all = camelCase)]
#[serde(rename_all = "camelCase")]
pub enum Locale {
$($language),+,
}
impl From<milli::tokenizer::Language> for Locale {
fn from(other: milli::tokenizer::Language) -> Locale {
match other {
$(milli::tokenizer::Language::$language => Locale::$language), +
}
}
}
impl From<Locale> for milli::tokenizer::Language {
fn from(other: Locale) -> milli::tokenizer::Language {
match other {
$(Locale::$language => milli::tokenizer::Language::$language), +,
}
}
}
#[derive(Debug)]
pub struct LocaleFormatError {
pub invalid_locale: String,
}
impl std::fmt::Display for LocaleFormatError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let valid_locales = [$(Locale::$language),+].iter().map(|l| format!("`{}`", json!(l).as_str().unwrap())).collect::<Vec<_>>().join(", ");
write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales)
}
}
};
}
make_locale! {
Epo,
Eng,
Rus,
Cmn,
Spa,
Por,
Ita,
Ben,
Fra,
Deu,
Ukr,
Kat,
Ara,
Hin,
Jpn,
Heb,
Yid,
Pol,
Amh,
Jav,
Kor,
Nob,
Dan,
Swe,
Fin,
Tur,
Nld,
Hun,
Ces,
Ell,
Bul,
Bel,
Mar,
Kan,
Ron,
Slv,
Hrv,
Srp,
Mkd,
Lit,
Lav,
Est,
Tam,
Vie,
Urd,
Tha,
Guj,
Uzb,
Pan,
Aze,
Ind,
Tel,
Pes,
Mal,
Ori,
Mya,
Nep,
Sin,
Khm,
Tuk,
Aka,
Zul,
Sna,
Afr,
Lat,
Slk,
Cat,
Tgl,
Hye,
Zho
}
impl std::error::Error for LocaleFormatError {}
impl std::str::FromStr for Locale {
type Err = LocaleFormatError;
fn from_str(s: &str) -> Result<Self, Self::Err> {
milli::tokenizer::Language::from_code(s)
.map(Self::from)
.ok_or(LocaleFormatError { invalid_locale: s.to_string() })
}
}
#[derive(Debug, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize)]
#[deserr(rename_all = camelCase)]
#[serde(rename_all = "camelCase")]
pub struct LocalizedAttributesRuleView {
pub attribute_patterns: Vec<String>,
pub locales: Vec<Locale>,
}
impl From<LocalizedAttributesRule> for LocalizedAttributesRuleView {
fn from(rule: LocalizedAttributesRule) -> Self {
Self {
attribute_patterns: rule.attribute_patterns,
locales: rule.locales.into_iter().map(|l| l.into()).collect(),
}
}
}
impl From<LocalizedAttributesRuleView> for LocalizedAttributesRule {
fn from(view: LocalizedAttributesRuleView) -> Self {
Self {
attribute_patterns: view.attribute_patterns,
locales: view.locales.into_iter().map(|l| l.into()).collect(),
}
}
}

View File

@@ -17,7 +17,6 @@ use serde::{Deserialize, Serialize, Serializer};
use crate::deserr::DeserrJsonError; use crate::deserr::DeserrJsonError;
use crate::error::deserr_codes::*; use crate::error::deserr_codes::*;
use crate::facet_values_sort::FacetValuesSort; use crate::facet_values_sort::FacetValuesSort;
use crate::locales::LocalizedAttributesRuleView;
/// The maximum number of results that the engine /// The maximum number of results that the engine
/// will be able to return in one search call. /// will be able to return in one search call.
@@ -199,9 +198,6 @@ pub struct Settings<T> {
#[serde(default, skip_serializing_if = "Setting::is_not_set")] #[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default, error = DeserrJsonError<InvalidSettingsSearchCutoffMs>)] #[deserr(default, error = DeserrJsonError<InvalidSettingsSearchCutoffMs>)]
pub search_cutoff_ms: Setting<u64>, pub search_cutoff_ms: Setting<u64>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default, error = DeserrJsonError<InvalidSettingsLocalizedAttributes>)]
pub localized_attributes: Setting<Vec<LocalizedAttributesRuleView>>,
#[serde(skip)] #[serde(skip)]
#[deserr(skip)] #[deserr(skip)]
@@ -265,7 +261,6 @@ impl Settings<Checked> {
pagination: Setting::Reset, pagination: Setting::Reset,
embedders: Setting::Reset, embedders: Setting::Reset,
search_cutoff_ms: Setting::Reset, search_cutoff_ms: Setting::Reset,
localized_attributes: Setting::Reset,
_kind: PhantomData, _kind: PhantomData,
} }
} }
@@ -289,8 +284,7 @@ impl Settings<Checked> {
pagination, pagination,
embedders, embedders,
search_cutoff_ms, search_cutoff_ms,
localized_attributes: localized_attributes_rules, ..
_kind,
} = self; } = self;
Settings { Settings {
@@ -311,7 +305,6 @@ impl Settings<Checked> {
pagination, pagination,
embedders, embedders,
search_cutoff_ms, search_cutoff_ms,
localized_attributes: localized_attributes_rules,
_kind: PhantomData, _kind: PhantomData,
} }
} }
@@ -359,7 +352,6 @@ impl Settings<Unchecked> {
pagination: self.pagination, pagination: self.pagination,
embedders: self.embedders, embedders: self.embedders,
search_cutoff_ms: self.search_cutoff_ms, search_cutoff_ms: self.search_cutoff_ms,
localized_attributes: self.localized_attributes,
_kind: PhantomData, _kind: PhantomData,
} }
} }
@@ -410,7 +402,6 @@ pub fn apply_settings_to_builder(
pagination, pagination,
embedders, embedders,
search_cutoff_ms, search_cutoff_ms,
localized_attributes: localized_attributes_rules,
_kind, _kind,
} = settings; } = settings;
@@ -494,13 +485,6 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (), Setting::NotSet => (),
} }
match localized_attributes_rules {
Setting::Set(ref rules) => builder
.set_localized_attributes_rules(rules.iter().cloned().map(|r| r.into()).collect()),
Setting::Reset => builder.reset_localized_attributes_rules(),
Setting::NotSet => (),
}
match typo_tolerance { match typo_tolerance {
Setting::Set(ref value) => { Setting::Set(ref value) => {
match value.enabled { match value.enabled {
@@ -695,8 +679,6 @@ pub fn settings(
let search_cutoff_ms = index.search_cutoff(rtxn)?; let search_cutoff_ms = index.search_cutoff(rtxn)?;
let localized_attributes_rules = index.localized_attributes_rules(rtxn)?;
let mut settings = Settings { let mut settings = Settings {
displayed_attributes: match displayed_attributes { displayed_attributes: match displayed_attributes {
Some(attrs) => Setting::Set(attrs), Some(attrs) => Setting::Set(attrs),
@@ -729,10 +711,6 @@ pub fn settings(
Some(cutoff) => Setting::Set(cutoff), Some(cutoff) => Setting::Set(cutoff),
None => Setting::Reset, None => Setting::Reset,
}, },
localized_attributes: match localized_attributes_rules {
Some(rules) => Setting::Set(rules.into_iter().map(|r| r.into()).collect()),
None => Setting::Reset,
},
_kind: PhantomData, _kind: PhantomData,
}; };
@@ -924,7 +902,6 @@ pub(crate) mod test {
faceting: Setting::NotSet, faceting: Setting::NotSet,
pagination: Setting::NotSet, pagination: Setting::NotSet,
embedders: Setting::NotSet, embedders: Setting::NotSet,
localized_attributes: Setting::NotSet,
search_cutoff_ms: Setting::NotSet, search_cutoff_ms: Setting::NotSet,
_kind: PhantomData::<Unchecked>, _kind: PhantomData::<Unchecked>,
}; };
@@ -953,7 +930,6 @@ pub(crate) mod test {
faceting: Setting::NotSet, faceting: Setting::NotSet,
pagination: Setting::NotSet, pagination: Setting::NotSet,
embedders: Setting::NotSet, embedders: Setting::NotSet,
localized_attributes: Setting::NotSet,
search_cutoff_ms: Setting::NotSet, search_cutoff_ms: Setting::NotSet,
_kind: PhantomData::<Unchecked>, _kind: PhantomData::<Unchecked>,
}; };

View File

@@ -1,4 +1,3 @@
use milli::Object;
use serde::Serialize; use serde::Serialize;
use time::{Duration, OffsetDateTime}; use time::{Duration, OffsetDateTime};
@@ -55,8 +54,6 @@ pub struct DetailsView {
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
pub indexed_documents: Option<Option<u64>>, pub indexed_documents: Option<Option<u64>>,
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
pub edited_documents: Option<Option<u64>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub primary_key: Option<Option<String>>, pub primary_key: Option<Option<String>>,
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
pub provided_ids: Option<usize>, pub provided_ids: Option<usize>,
@@ -73,10 +70,6 @@ pub struct DetailsView {
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
pub dump_uid: Option<Option<String>>, pub dump_uid: Option<Option<String>>,
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
pub context: Option<Option<Object>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub function: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(flatten)] #[serde(flatten)]
pub settings: Option<Box<Settings<Unchecked>>>, pub settings: Option<Box<Settings<Unchecked>>>,
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
@@ -93,20 +86,6 @@ impl From<Details> for DetailsView {
..DetailsView::default() ..DetailsView::default()
} }
} }
Details::DocumentEdition {
deleted_documents,
edited_documents,
original_filter,
context,
function,
} => DetailsView {
deleted_documents: Some(deleted_documents),
edited_documents: Some(edited_documents),
original_filter: Some(original_filter),
context: Some(context),
function: Some(function),
..DetailsView::default()
},
Details::SettingsUpdate { mut settings } => { Details::SettingsUpdate { mut settings } => {
settings.hide_secrets(); settings.hide_secrets();
DetailsView { settings: Some(settings), ..DetailsView::default() } DetailsView { settings: Some(settings), ..DetailsView::default() }

View File

@@ -5,7 +5,6 @@ use std::str::FromStr;
use enum_iterator::Sequence; use enum_iterator::Sequence;
use milli::update::IndexDocumentsMethod; use milli::update::IndexDocumentsMethod;
use milli::Object;
use roaring::RoaringBitmap; use roaring::RoaringBitmap;
use serde::{Deserialize, Serialize, Serializer}; use serde::{Deserialize, Serialize, Serializer};
use time::{Duration, OffsetDateTime}; use time::{Duration, OffsetDateTime};
@@ -49,7 +48,6 @@ impl Task {
| TaskDeletion { .. } | TaskDeletion { .. }
| IndexSwap { .. } => None, | IndexSwap { .. } => None,
DocumentAdditionOrUpdate { index_uid, .. } DocumentAdditionOrUpdate { index_uid, .. }
| DocumentEdition { index_uid, .. }
| DocumentDeletion { index_uid, .. } | DocumentDeletion { index_uid, .. }
| DocumentDeletionByFilter { index_uid, .. } | DocumentDeletionByFilter { index_uid, .. }
| DocumentClear { index_uid } | DocumentClear { index_uid }
@@ -69,8 +67,7 @@ impl Task {
pub fn content_uuid(&self) -> Option<Uuid> { pub fn content_uuid(&self) -> Option<Uuid> {
match self.kind { match self.kind {
KindWithContent::DocumentAdditionOrUpdate { content_file, .. } => Some(content_file), KindWithContent::DocumentAdditionOrUpdate { content_file, .. } => Some(content_file),
KindWithContent::DocumentEdition { .. } KindWithContent::DocumentDeletion { .. }
| KindWithContent::DocumentDeletion { .. }
| KindWithContent::DocumentDeletionByFilter { .. } | KindWithContent::DocumentDeletionByFilter { .. }
| KindWithContent::DocumentClear { .. } | KindWithContent::DocumentClear { .. }
| KindWithContent::SettingsUpdate { .. } | KindWithContent::SettingsUpdate { .. }
@@ -105,12 +102,6 @@ pub enum KindWithContent {
index_uid: String, index_uid: String,
filter_expr: serde_json::Value, filter_expr: serde_json::Value,
}, },
DocumentEdition {
index_uid: String,
filter_expr: Option<serde_json::Value>,
context: Option<milli::Object>,
function: String,
},
DocumentClear { DocumentClear {
index_uid: String, index_uid: String,
}, },
@@ -159,7 +150,6 @@ impl KindWithContent {
pub fn as_kind(&self) -> Kind { pub fn as_kind(&self) -> Kind {
match self { match self {
KindWithContent::DocumentAdditionOrUpdate { .. } => Kind::DocumentAdditionOrUpdate, KindWithContent::DocumentAdditionOrUpdate { .. } => Kind::DocumentAdditionOrUpdate,
KindWithContent::DocumentEdition { .. } => Kind::DocumentEdition,
KindWithContent::DocumentDeletion { .. } => Kind::DocumentDeletion, KindWithContent::DocumentDeletion { .. } => Kind::DocumentDeletion,
KindWithContent::DocumentDeletionByFilter { .. } => Kind::DocumentDeletion, KindWithContent::DocumentDeletionByFilter { .. } => Kind::DocumentDeletion,
KindWithContent::DocumentClear { .. } => Kind::DocumentDeletion, KindWithContent::DocumentClear { .. } => Kind::DocumentDeletion,
@@ -184,7 +174,6 @@ impl KindWithContent {
| TaskCancelation { .. } | TaskCancelation { .. }
| TaskDeletion { .. } => vec![], | TaskDeletion { .. } => vec![],
DocumentAdditionOrUpdate { index_uid, .. } DocumentAdditionOrUpdate { index_uid, .. }
| DocumentEdition { index_uid, .. }
| DocumentDeletion { index_uid, .. } | DocumentDeletion { index_uid, .. }
| DocumentDeletionByFilter { index_uid, .. } | DocumentDeletionByFilter { index_uid, .. }
| DocumentClear { index_uid } | DocumentClear { index_uid }
@@ -213,15 +202,6 @@ impl KindWithContent {
indexed_documents: None, indexed_documents: None,
}) })
} }
KindWithContent::DocumentEdition { index_uid: _, filter_expr, context, function } => {
Some(Details::DocumentEdition {
deleted_documents: None,
edited_documents: None,
original_filter: filter_expr.as_ref().map(|v| v.to_string()),
context: context.clone(),
function: function.clone(),
})
}
KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => { KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
Some(Details::DocumentDeletion { Some(Details::DocumentDeletion {
provided_ids: documents_ids.len(), provided_ids: documents_ids.len(),
@@ -270,15 +250,6 @@ impl KindWithContent {
indexed_documents: Some(0), indexed_documents: Some(0),
}) })
} }
KindWithContent::DocumentEdition { index_uid: _, filter_expr, context, function } => {
Some(Details::DocumentEdition {
deleted_documents: Some(0),
edited_documents: Some(0),
original_filter: filter_expr.as_ref().map(|v| v.to_string()),
context: context.clone(),
function: function.clone(),
})
}
KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => { KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
Some(Details::DocumentDeletion { Some(Details::DocumentDeletion {
provided_ids: documents_ids.len(), provided_ids: documents_ids.len(),
@@ -330,7 +301,6 @@ impl From<&KindWithContent> for Option<Details> {
indexed_documents: None, indexed_documents: None,
}) })
} }
KindWithContent::DocumentEdition { .. } => None,
KindWithContent::DocumentDeletion { .. } => None, KindWithContent::DocumentDeletion { .. } => None,
KindWithContent::DocumentDeletionByFilter { .. } => None, KindWithContent::DocumentDeletionByFilter { .. } => None,
KindWithContent::DocumentClear { .. } => None, KindWithContent::DocumentClear { .. } => None,
@@ -424,7 +394,6 @@ impl std::error::Error for ParseTaskStatusError {}
#[serde(rename_all = "camelCase")] #[serde(rename_all = "camelCase")]
pub enum Kind { pub enum Kind {
DocumentAdditionOrUpdate, DocumentAdditionOrUpdate,
DocumentEdition,
DocumentDeletion, DocumentDeletion,
SettingsUpdate, SettingsUpdate,
IndexCreation, IndexCreation,
@@ -441,7 +410,6 @@ impl Kind {
pub fn related_to_one_index(&self) -> bool { pub fn related_to_one_index(&self) -> bool {
match self { match self {
Kind::DocumentAdditionOrUpdate Kind::DocumentAdditionOrUpdate
| Kind::DocumentEdition
| Kind::DocumentDeletion | Kind::DocumentDeletion
| Kind::SettingsUpdate | Kind::SettingsUpdate
| Kind::IndexCreation | Kind::IndexCreation
@@ -459,7 +427,6 @@ impl Display for Kind {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result { fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self { match self {
Kind::DocumentAdditionOrUpdate => write!(f, "documentAdditionOrUpdate"), Kind::DocumentAdditionOrUpdate => write!(f, "documentAdditionOrUpdate"),
Kind::DocumentEdition => write!(f, "documentEdition"),
Kind::DocumentDeletion => write!(f, "documentDeletion"), Kind::DocumentDeletion => write!(f, "documentDeletion"),
Kind::SettingsUpdate => write!(f, "settingsUpdate"), Kind::SettingsUpdate => write!(f, "settingsUpdate"),
Kind::IndexCreation => write!(f, "indexCreation"), Kind::IndexCreation => write!(f, "indexCreation"),
@@ -487,8 +454,6 @@ impl FromStr for Kind {
Ok(Kind::IndexDeletion) Ok(Kind::IndexDeletion)
} else if kind.eq_ignore_ascii_case("documentAdditionOrUpdate") { } else if kind.eq_ignore_ascii_case("documentAdditionOrUpdate") {
Ok(Kind::DocumentAdditionOrUpdate) Ok(Kind::DocumentAdditionOrUpdate)
} else if kind.eq_ignore_ascii_case("documentEdition") {
Ok(Kind::DocumentEdition)
} else if kind.eq_ignore_ascii_case("documentDeletion") { } else if kind.eq_ignore_ascii_case("documentDeletion") {
Ok(Kind::DocumentDeletion) Ok(Kind::DocumentDeletion)
} else if kind.eq_ignore_ascii_case("settingsUpdate") { } else if kind.eq_ignore_ascii_case("settingsUpdate") {
@@ -530,50 +495,16 @@ impl std::error::Error for ParseTaskKindError {}
#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)] #[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
pub enum Details { pub enum Details {
DocumentAdditionOrUpdate { DocumentAdditionOrUpdate { received_documents: u64, indexed_documents: Option<u64> },
received_documents: u64, SettingsUpdate { settings: Box<Settings<Unchecked>> },
indexed_documents: Option<u64>, IndexInfo { primary_key: Option<String> },
}, DocumentDeletion { provided_ids: usize, deleted_documents: Option<u64> },
SettingsUpdate { DocumentDeletionByFilter { original_filter: String, deleted_documents: Option<u64> },
settings: Box<Settings<Unchecked>>, ClearAll { deleted_documents: Option<u64> },
}, TaskCancelation { matched_tasks: u64, canceled_tasks: Option<u64>, original_filter: String },
IndexInfo { TaskDeletion { matched_tasks: u64, deleted_tasks: Option<u64>, original_filter: String },
primary_key: Option<String>, Dump { dump_uid: Option<String> },
}, IndexSwap { swaps: Vec<IndexSwap> },
DocumentDeletion {
provided_ids: usize,
deleted_documents: Option<u64>,
},
DocumentDeletionByFilter {
original_filter: String,
deleted_documents: Option<u64>,
},
DocumentEdition {
deleted_documents: Option<u64>,
edited_documents: Option<u64>,
original_filter: Option<String>,
context: Option<Object>,
function: String,
},
ClearAll {
deleted_documents: Option<u64>,
},
TaskCancelation {
matched_tasks: u64,
canceled_tasks: Option<u64>,
original_filter: String,
},
TaskDeletion {
matched_tasks: u64,
deleted_tasks: Option<u64>,
original_filter: String,
},
Dump {
dump_uid: Option<String>,
},
IndexSwap {
swaps: Vec<IndexSwap>,
},
} }
impl Details { impl Details {
@@ -583,7 +514,6 @@ impl Details {
Self::DocumentAdditionOrUpdate { indexed_documents, .. } => { Self::DocumentAdditionOrUpdate { indexed_documents, .. } => {
*indexed_documents = Some(0) *indexed_documents = Some(0)
} }
Self::DocumentEdition { edited_documents, .. } => *edited_documents = Some(0),
Self::DocumentDeletion { deleted_documents, .. } => *deleted_documents = Some(0), Self::DocumentDeletion { deleted_documents, .. } => *deleted_documents = Some(0),
Self::DocumentDeletionByFilter { deleted_documents, .. } => { Self::DocumentDeletionByFilter { deleted_documents, .. } => {
*deleted_documents = Some(0) *deleted_documents = Some(0)

View File

@@ -14,126 +14,130 @@ default-run = "meilisearch"
[dependencies] [dependencies]
actix-cors = "0.7.0" actix-cors = "0.7.0"
actix-http = { version = "3.8.0", default-features = false, features = [ actix-http = { version = "3.7.0", default-features = false, features = [
"compress-brotli", "compress-brotli",
"compress-gzip", "compress-gzip",
"rustls-0_23", "rustls-0_21",
] } ] }
actix-utils = "3.0.1" actix-utils = "3.0.1"
actix-web = { version = "4.8.0", default-features = false, features = [ actix-web = { version = "4.6.0", default-features = false, features = [
"macros", "macros",
"compress-brotli", "compress-brotli",
"compress-gzip", "compress-gzip",
"cookies", "cookies",
"rustls-0_23", "rustls-0_21",
] } ] }
anyhow = { version = "1.0.86", features = ["backtrace"] } actix-web-static-files = { version = "4.0.1", optional = true }
async-trait = "0.1.81" anyhow = { version = "1.0.79", features = ["backtrace"] }
bstr = "1.9.1" async-stream = "0.3.5"
byte-unit = { version = "5.1.4", default-features = false, features = [ async-trait = "0.1.77"
bstr = "1.9.0"
byte-unit = { version = "4.0.19", default-features = false, features = [
"std", "std",
"byte",
"serde", "serde",
] } ] }
bytes = "1.6.0" bytes = "1.5.0"
clap = { version = "4.5.9", features = ["derive", "env"] } clap = { version = "4.4.17", features = ["derive", "env"] }
crossbeam-channel = "0.5.13" crossbeam-channel = "0.5.11"
deserr = { version = "0.6.2", features = ["actix-web"] } deserr = { version = "0.6.1", features = ["actix-web"] }
dump = { path = "../dump" } dump = { path = "../dump" }
either = "1.13.0" either = "1.9.0"
file-store = { path = "../file-store" } file-store = { path = "../file-store" }
flate2 = "1.0.30" flate2 = "1.0.28"
fst = "0.4.7" fst = "0.4.7"
futures = "0.3.30" futures = "0.3.30"
futures-util = "0.3.30" futures-util = "0.3.30"
http = "0.2.11"
index-scheduler = { path = "../index-scheduler" } index-scheduler = { path = "../index-scheduler" }
indexmap = { version = "2.2.6", features = ["serde"] } indexmap = { version = "2.1.0", features = ["serde"] }
is-terminal = "0.4.12" is-terminal = "0.4.10"
itertools = "0.13.0" itertools = "0.11.0"
jsonwebtoken = "9.3.0" jsonwebtoken = "9.2.0"
lazy_static = "1.5.0" lazy_static = "1.4.0"
meilisearch-auth = { path = "../meilisearch-auth" } meilisearch-auth = { path = "../meilisearch-auth" }
meilisearch-types = { path = "../meilisearch-types" } meilisearch-types = { path = "../meilisearch-types" }
mimalloc = { version = "0.1.43", default-features = false } mimalloc = { version = "0.1.39", default-features = false }
mime = "0.3.17" mime = "0.3.17"
num_cpus = "1.16.0" num_cpus = "1.16.0"
obkv = "0.2.2" obkv = "0.2.1"
once_cell = "1.19.0" once_cell = "1.19.0"
ordered-float = "4.2.1" ordered-float = "4.2.0"
parking_lot = "0.12.3" parking_lot = "0.12.1"
permissive-json-pointer = { path = "../permissive-json-pointer" } permissive-json-pointer = { path = "../permissive-json-pointer" }
pin-project-lite = "0.2.14" pin-project-lite = "0.2.13"
platform-dirs = "0.3.0" platform-dirs = "0.3.0"
prometheus = { version = "0.13.4", features = ["process"] } prometheus = { version = "0.13.3", features = ["process"] }
rand = "0.8.5" rand = "0.8.5"
rayon = "1.10.0" rayon = "1.8.0"
regex = "1.10.5" regex = "1.10.2"
reqwest = { version = "0.12.5", features = [ reqwest = { version = "0.11.23", features = [
"rustls-tls", "rustls-tls",
"json", "json",
], default-features = false } ], default-features = false }
rustls = { version = "0.23.11", features = ["ring"], default-features = false } rustls = "0.21.12"
rustls-pki-types = { version = "1.7.0", features = ["alloc"] } rustls-pemfile = "1.0.2"
rustls-pemfile = "2.1.2" segment = { version = "0.2.3", optional = true }
segment = { version = "0.2.4", optional = true } serde = { version = "1.0.195", features = ["derive"] }
serde = { version = "1.0.204", features = ["derive"] } serde_json = { version = "1.0.111", features = ["preserve_order"] }
serde_json = { version = "1.0.120", features = ["preserve_order"] }
sha2 = "0.10.8" sha2 = "0.10.8"
siphasher = "1.0.1" siphasher = "1.0.0"
slice-group-by = "0.3.1" slice-group-by = "0.3.1"
static-files = { version = "0.2.4", optional = true } static-files = { version = "0.2.3", optional = true }
sysinfo = "0.30.13" sysinfo = "0.30.5"
tar = "0.4.41" tar = "0.4.40"
tempfile = "3.10.1" tempfile = "3.9.0"
thiserror = "1.0.61" thiserror = "1.0.56"
time = { version = "0.3.36", features = [ time = { version = "0.3.31", features = [
"serde-well-known", "serde-well-known",
"formatting", "formatting",
"parsing", "parsing",
"macros", "macros",
] } ] }
tokio = { version = "1.38.0", features = ["full"] } tokio = { version = "1.35.1", features = ["full"] }
toml = "0.8.14" tokio-stream = "0.1.14"
uuid = { version = "1.10.0", features = ["serde", "v4"] } toml = "0.8.8"
uuid = { version = "1.6.1", features = ["serde", "v4"] }
walkdir = "2.4.0"
yaup = "0.2.1"
serde_urlencoded = "0.7.1" serde_urlencoded = "0.7.1"
termcolor = "1.4.1" termcolor = "1.4.1"
url = { version = "2.5.2", features = ["serde"] } url = { version = "2.5.0", features = ["serde"] }
tracing = "0.1.40" tracing = "0.1.40"
tracing-subscriber = { version = "0.3.18", features = ["json"] } tracing-subscriber = { version = "0.3.18", features = ["json"] }
tracing-trace = { version = "0.1.0", path = "../tracing-trace" } tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
tracing-actix-web = "0.7.11" tracing-actix-web = "0.7.10"
build-info = { version = "1.7.0", path = "../build-info" } build-info = { version = "1.7.0", path = "../build-info" }
roaring = "0.10.2"
[dev-dependencies] [dev-dependencies]
actix-rt = "2.10.0" actix-rt = "2.9.0"
assert-json-diff = "2.0.2"
brotli = "6.0.0" brotli = "6.0.0"
insta = "1.39.0" insta = "1.34.0"
manifest-dir-macros = "0.1.18" manifest-dir-macros = "0.1.18"
maplit = "1.0.2" maplit = "1.0.2"
meili-snap = { path = "../meili-snap" } meili-snap = { path = "../meili-snap" }
temp-env = "0.3.6" temp-env = "0.3.6"
urlencoding = "2.1.3" urlencoding = "2.1.3"
wiremock = "0.6.0" yaup = "0.2.1"
yaup = "0.3.1"
[build-dependencies] [build-dependencies]
anyhow = { version = "1.0.86", optional = true } anyhow = { version = "1.0.79", optional = true }
cargo_toml = { version = "0.20.3", optional = true } cargo_toml = { version = "0.18.0", optional = true }
hex = { version = "0.4.3", optional = true } hex = { version = "0.4.3", optional = true }
reqwest = { version = "0.12.5", features = [ reqwest = { version = "0.11.23", features = [
"blocking", "blocking",
"rustls-tls", "rustls-tls",
], default-features = false, optional = true } ], default-features = false, optional = true }
sha-1 = { version = "0.10.1", optional = true } sha-1 = { version = "0.10.1", optional = true }
static-files = { version = "0.2.4", optional = true } static-files = { version = "0.2.3", optional = true }
tempfile = { version = "3.10.1", optional = true } tempfile = { version = "3.9.0", optional = true }
zip = { version = "2.1.3", optional = true } zip = { version = "0.6.6", optional = true }
[features] [features]
default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"] default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
analytics = ["segment"] analytics = ["segment"]
mini-dashboard = [ mini-dashboard = [
"actix-web-static-files",
"static-files", "static-files",
"anyhow", "anyhow",
"cargo_toml", "cargo_toml",
@@ -147,7 +151,6 @@ chinese = ["meilisearch-types/chinese"]
chinese-pinyin = ["meilisearch-types/chinese-pinyin"] chinese-pinyin = ["meilisearch-types/chinese-pinyin"]
hebrew = ["meilisearch-types/hebrew"] hebrew = ["meilisearch-types/hebrew"]
japanese = ["meilisearch-types/japanese"] japanese = ["meilisearch-types/japanese"]
korean = ["meilisearch-types/korean"]
thai = ["meilisearch-types/thai"] thai = ["meilisearch-types/thai"]
greek = ["meilisearch-types/greek"] greek = ["meilisearch-types/greek"]
khmer = ["meilisearch-types/khmer"] khmer = ["meilisearch-types/khmer"]

View File

@@ -6,7 +6,7 @@ use meilisearch_types::InstanceUid;
use serde_json::Value; use serde_json::Value;
use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind}; use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery}; use crate::routes::indexes::documents::UpdateDocumentsQuery;
use crate::Opt; use crate::Opt;
pub struct MockAnalytics { pub struct MockAnalytics {
@@ -42,7 +42,7 @@ pub struct MultiSearchAggregator;
#[allow(dead_code)] #[allow(dead_code)]
impl MultiSearchAggregator { impl MultiSearchAggregator {
pub fn from_federated_search(_: &dyn Any, _: &dyn Any) -> Self { pub fn from_queries(_: &dyn Any, _: &dyn Any) -> Self {
Self Self
} }
@@ -97,13 +97,6 @@ impl Analytics for MockAnalytics {
_request: &HttpRequest, _request: &HttpRequest,
) { ) {
} }
fn update_documents_by_function(
&self,
_documents_query: &DocumentEditionByFunction,
_index_creation: bool,
_request: &HttpRequest,
) {
}
fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {} fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {} fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
} }

View File

@@ -13,7 +13,7 @@ use once_cell::sync::Lazy;
use platform_dirs::AppDirs; use platform_dirs::AppDirs;
use serde_json::Value; use serde_json::Value;
use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery}; use crate::routes::indexes::documents::UpdateDocumentsQuery;
// if the analytics feature is disabled // if the analytics feature is disabled
// the `SegmentAnalytics` point to the mock instead of the real analytics // the `SegmentAnalytics` point to the mock instead of the real analytics
@@ -102,7 +102,7 @@ pub trait Analytics: Sync + Send {
/// This method should be called to aggregate post facet values searches /// This method should be called to aggregate post facet values searches
fn post_facet_search(&self, aggregate: FacetSearchAggregator); fn post_facet_search(&self, aggregate: FacetSearchAggregator);
// this method should be called to aggregate an add documents request // this method should be called to aggregate a add documents request
fn add_documents( fn add_documents(
&self, &self,
documents_query: &UpdateDocumentsQuery, documents_query: &UpdateDocumentsQuery,
@@ -119,19 +119,11 @@ pub trait Analytics: Sync + Send {
// this method should be called to aggregate a add documents request // this method should be called to aggregate a add documents request
fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest); fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest);
// this method should be called to batch an update documents request // this method should be called to batch a update documents request
fn update_documents( fn update_documents(
&self, &self,
documents_query: &UpdateDocumentsQuery, documents_query: &UpdateDocumentsQuery,
index_creation: bool, index_creation: bool,
request: &HttpRequest, request: &HttpRequest,
); );
// this method should be called to batch an update documents by function request
fn update_documents_by_function(
&self,
documents_query: &DocumentEditionByFunction,
index_creation: bool,
request: &HttpRequest,
);
} }

View File

@@ -1,16 +1,16 @@
use std::collections::{BTreeSet, BinaryHeap, HashMap, HashSet}; use std::collections::{BinaryHeap, HashMap, HashSet};
use std::fs; use std::fs;
use std::mem::take; use std::mem::take;
use std::path::{Path, PathBuf}; use std::path::{Path, PathBuf};
use std::sync::Arc; use std::sync::Arc;
use std::time::{Duration, Instant}; use std::time::{Duration, Instant};
use actix_web::http::header::{CONTENT_TYPE, USER_AGENT}; use actix_web::http::header::USER_AGENT;
use actix_web::HttpRequest; use actix_web::HttpRequest;
use byte_unit::Byte; use byte_unit::Byte;
use http::header::CONTENT_TYPE;
use index_scheduler::IndexScheduler; use index_scheduler::IndexScheduler;
use meilisearch_auth::{AuthController, AuthFilter}; use meilisearch_auth::{AuthController, AuthFilter};
use meilisearch_types::locales::Locale;
use meilisearch_types::InstanceUid; use meilisearch_types::InstanceUid;
use once_cell::sync::Lazy; use once_cell::sync::Lazy;
use regex::Regex; use regex::Regex;
@@ -31,12 +31,12 @@ use crate::analytics::Analytics;
use crate::option::{ use crate::option::{
default_http_addr, IndexerOpts, LogMode, MaxMemory, MaxThreads, ScheduleSnapshot, default_http_addr, IndexerOpts, LogMode, MaxMemory, MaxThreads, ScheduleSnapshot,
}; };
use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery}; use crate::routes::indexes::documents::UpdateDocumentsQuery;
use crate::routes::indexes::facet_search::FacetSearchQuery; use crate::routes::indexes::facet_search::FacetSearchQuery;
use crate::routes::{create_all_stats, Stats}; use crate::routes::{create_all_stats, Stats};
use crate::search::{ use crate::search::{
FacetSearchResult, FederatedSearch, MatchingStrategy, SearchQuery, SearchQueryWithIndex, FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
SearchResult, SimilarQuery, SimilarResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, SimilarQuery, SimilarResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
DEFAULT_SEMANTIC_RATIO, DEFAULT_SEMANTIC_RATIO,
}; };
@@ -81,7 +81,6 @@ pub enum AnalyticsMsg {
AggregateAddDocuments(DocumentsAggregator), AggregateAddDocuments(DocumentsAggregator),
AggregateDeleteDocuments(DocumentsDeletionAggregator), AggregateDeleteDocuments(DocumentsDeletionAggregator),
AggregateUpdateDocuments(DocumentsAggregator), AggregateUpdateDocuments(DocumentsAggregator),
AggregateEditDocumentsByFunction(EditDocumentsByFunctionAggregator),
AggregateGetFetchDocuments(DocumentsFetchAggregator), AggregateGetFetchDocuments(DocumentsFetchAggregator),
AggregatePostFetchDocuments(DocumentsFetchAggregator), AggregatePostFetchDocuments(DocumentsFetchAggregator),
} }
@@ -151,7 +150,6 @@ impl SegmentAnalytics {
add_documents_aggregator: DocumentsAggregator::default(), add_documents_aggregator: DocumentsAggregator::default(),
delete_documents_aggregator: DocumentsDeletionAggregator::default(), delete_documents_aggregator: DocumentsDeletionAggregator::default(),
update_documents_aggregator: DocumentsAggregator::default(), update_documents_aggregator: DocumentsAggregator::default(),
edit_documents_by_function_aggregator: EditDocumentsByFunctionAggregator::default(),
get_fetch_documents_aggregator: DocumentsFetchAggregator::default(), get_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
post_fetch_documents_aggregator: DocumentsFetchAggregator::default(), post_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
get_similar_aggregator: SimilarAggregator::default(), get_similar_aggregator: SimilarAggregator::default(),
@@ -232,17 +230,6 @@ impl super::Analytics for SegmentAnalytics {
let _ = self.sender.try_send(AnalyticsMsg::AggregateUpdateDocuments(aggregate)); let _ = self.sender.try_send(AnalyticsMsg::AggregateUpdateDocuments(aggregate));
} }
fn update_documents_by_function(
&self,
documents_query: &DocumentEditionByFunction,
index_creation: bool,
request: &HttpRequest,
) {
let aggregate =
EditDocumentsByFunctionAggregator::from_query(documents_query, index_creation, request);
let _ = self.sender.try_send(AnalyticsMsg::AggregateEditDocumentsByFunction(aggregate));
}
fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) { fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) {
let aggregate = DocumentsFetchAggregator::from_query(documents_query, request); let aggregate = DocumentsFetchAggregator::from_query(documents_query, request);
let _ = self.sender.try_send(AnalyticsMsg::AggregateGetFetchDocuments(aggregate)); let _ = self.sender.try_send(AnalyticsMsg::AggregateGetFetchDocuments(aggregate));
@@ -262,16 +249,14 @@ impl super::Analytics for SegmentAnalytics {
#[derive(Debug, Clone, Serialize)] #[derive(Debug, Clone, Serialize)]
struct Infos { struct Infos {
env: String, env: String,
experimental_contains_filter: bool,
experimental_enable_metrics: bool, experimental_enable_metrics: bool,
experimental_search_queue_size: usize, experimental_search_queue_size: usize,
experimental_drop_search_after: usize,
experimental_nb_searches_per_core: usize,
experimental_logs_mode: LogMode, experimental_logs_mode: LogMode,
experimental_replication_parameters: bool, experimental_replication_parameters: bool,
experimental_enable_logs_route: bool, experimental_enable_logs_route: bool,
experimental_reduce_indexing_memory_usage: bool, experimental_reduce_indexing_memory_usage: bool,
experimental_max_number_of_batched_tasks: usize, experimental_max_number_of_batched_tasks: usize,
experimental_disable_prefix_db: bool,
gpu_enabled: bool, gpu_enabled: bool,
db_path: bool, db_path: bool,
import_dump: bool, import_dump: bool,
@@ -307,16 +292,14 @@ impl From<Opt> for Infos {
// Thus we must not insert `..` at the end. // Thus we must not insert `..` at the end.
let Opt { let Opt {
db_path, db_path,
experimental_contains_filter,
experimental_enable_metrics, experimental_enable_metrics,
experimental_search_queue_size, experimental_search_queue_size,
experimental_drop_search_after,
experimental_nb_searches_per_core,
experimental_logs_mode, experimental_logs_mode,
experimental_replication_parameters, experimental_replication_parameters,
experimental_enable_logs_route, experimental_enable_logs_route,
experimental_reduce_indexing_memory_usage, experimental_reduce_indexing_memory_usage,
experimental_max_number_of_batched_tasks, experimental_max_number_of_batched_tasks,
experimental_disable_prefix_db,
http_addr, http_addr,
master_key: _, master_key: _,
env, env,
@@ -360,15 +343,13 @@ impl From<Opt> for Infos {
// We consider information sensible if it contains a path, an address, or a key. // We consider information sensible if it contains a path, an address, or a key.
Self { Self {
env, env,
experimental_contains_filter,
experimental_enable_metrics, experimental_enable_metrics,
experimental_search_queue_size, experimental_search_queue_size,
experimental_drop_search_after: experimental_drop_search_after.into(),
experimental_nb_searches_per_core: experimental_nb_searches_per_core.into(),
experimental_logs_mode, experimental_logs_mode,
experimental_replication_parameters, experimental_replication_parameters,
experimental_enable_logs_route, experimental_enable_logs_route,
experimental_reduce_indexing_memory_usage, experimental_reduce_indexing_memory_usage,
experimental_disable_prefix_db,
gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(), gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(),
db_path: db_path != PathBuf::from("./data.ms"), db_path: db_path != PathBuf::from("./data.ms"),
import_dump: import_dump.is_some(), import_dump: import_dump.is_some(),
@@ -412,7 +393,6 @@ pub struct Segment {
add_documents_aggregator: DocumentsAggregator, add_documents_aggregator: DocumentsAggregator,
delete_documents_aggregator: DocumentsDeletionAggregator, delete_documents_aggregator: DocumentsDeletionAggregator,
update_documents_aggregator: DocumentsAggregator, update_documents_aggregator: DocumentsAggregator,
edit_documents_by_function_aggregator: EditDocumentsByFunctionAggregator,
get_fetch_documents_aggregator: DocumentsFetchAggregator, get_fetch_documents_aggregator: DocumentsFetchAggregator,
post_fetch_documents_aggregator: DocumentsFetchAggregator, post_fetch_documents_aggregator: DocumentsFetchAggregator,
get_similar_aggregator: SimilarAggregator, get_similar_aggregator: SimilarAggregator,
@@ -477,7 +457,6 @@ impl Segment {
Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg), Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg), Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg), Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateEditDocumentsByFunction(agreg)) => self.edit_documents_by_function_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateGetFetchDocuments(agreg)) => self.get_fetch_documents_aggregator.aggregate(agreg), Some(AnalyticsMsg::AggregateGetFetchDocuments(agreg)) => self.get_fetch_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregatePostFetchDocuments(agreg)) => self.post_fetch_documents_aggregator.aggregate(agreg), Some(AnalyticsMsg::AggregatePostFetchDocuments(agreg)) => self.post_fetch_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateGetSimilar(agreg)) => self.get_similar_aggregator.aggregate(agreg), Some(AnalyticsMsg::AggregateGetSimilar(agreg)) => self.get_similar_aggregator.aggregate(agreg),
@@ -533,7 +512,6 @@ impl Segment {
add_documents_aggregator, add_documents_aggregator,
delete_documents_aggregator, delete_documents_aggregator,
update_documents_aggregator, update_documents_aggregator,
edit_documents_by_function_aggregator,
get_fetch_documents_aggregator, get_fetch_documents_aggregator,
post_fetch_documents_aggregator, post_fetch_documents_aggregator,
get_similar_aggregator, get_similar_aggregator,
@@ -575,11 +553,6 @@ impl Segment {
{ {
let _ = self.batcher.push(update_documents).await; let _ = self.batcher.push(update_documents).await;
} }
if let Some(edit_documents_by_function) = take(edit_documents_by_function_aggregator)
.into_event(user, "Documents Edited By Function")
{
let _ = self.batcher.push(edit_documents_by_function).await;
}
if let Some(get_fetch_documents) = if let Some(get_fetch_documents) =
take(get_fetch_documents_aggregator).into_event(user, "Documents Fetched GET") take(get_fetch_documents_aggregator).into_event(user, "Documents Fetched GET")
{ {
@@ -660,9 +633,6 @@ pub struct SearchAggregator {
// every time a search is done, we increment the counter linked to the used settings // every time a search is done, we increment the counter linked to the used settings
matching_strategy: HashMap<String, usize>, matching_strategy: HashMap<String, usize>,
// List of the unique Locales passed as parameter
locales: BTreeSet<Locale>,
// pagination // pagination
max_limit: usize, max_limit: usize,
max_offset: usize, max_offset: usize,
@@ -717,7 +687,6 @@ impl SearchAggregator {
attributes_to_search_on, attributes_to_search_on,
hybrid, hybrid,
ranking_score_threshold, ranking_score_threshold,
locales,
} = query; } = query;
let mut ret = Self::default(); let mut ret = Self::default();
@@ -785,10 +754,6 @@ impl SearchAggregator {
ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1); ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1);
if let Some(locales) = locales {
ret.locales = locales.iter().copied().collect();
}
ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG(); ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG(); ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER(); ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
@@ -874,7 +839,6 @@ impl SearchAggregator {
total_degraded, total_degraded,
total_used_negative_operator, total_used_negative_operator,
ranking_score_threshold, ranking_score_threshold,
ref mut locales,
} = other; } = other;
if self.timestamp.is_none() { if self.timestamp.is_none() {
@@ -963,9 +927,6 @@ impl SearchAggregator {
self.show_ranking_score |= show_ranking_score; self.show_ranking_score |= show_ranking_score;
self.show_ranking_score_details |= show_ranking_score_details; self.show_ranking_score_details |= show_ranking_score_details;
self.ranking_score_threshold |= ranking_score_threshold; self.ranking_score_threshold |= ranking_score_threshold;
// locales
self.locales.append(locales);
} }
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> { pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -1010,7 +971,6 @@ impl SearchAggregator {
total_degraded, total_degraded,
total_used_negative_operator, total_used_negative_operator,
ranking_score_threshold, ranking_score_threshold,
locales,
} = self; } = self;
if total_received == 0 { if total_received == 0 {
@@ -1080,7 +1040,6 @@ impl SearchAggregator {
"matching_strategy": { "matching_strategy": {
"most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)), "most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
}, },
"locales": locales,
"scoring": { "scoring": {
"show_ranking_score": show_ranking_score, "show_ranking_score": show_ranking_score,
"show_ranking_score_details": show_ranking_score_details, "show_ranking_score_details": show_ranking_score_details,
@@ -1119,33 +1078,22 @@ pub struct MultiSearchAggregator {
show_ranking_score: bool, show_ranking_score: bool,
show_ranking_score_details: bool, show_ranking_score_details: bool,
// federation
use_federation: bool,
// context // context
user_agents: HashSet<String>, user_agents: HashSet<String>,
} }
impl MultiSearchAggregator { impl MultiSearchAggregator {
pub fn from_federated_search( pub fn from_queries(query: &[SearchQueryWithIndex], request: &HttpRequest) -> Self {
federated_search: &FederatedSearch,
request: &HttpRequest,
) -> Self {
let timestamp = Some(OffsetDateTime::now_utc()); let timestamp = Some(OffsetDateTime::now_utc());
let user_agents = extract_user_agents(request).into_iter().collect(); let user_agents = extract_user_agents(request).into_iter().collect();
let use_federation = federated_search.federation.is_some(); let distinct_indexes: HashSet<_> = query
let distinct_indexes: HashSet<_> = federated_search
.queries
.iter() .iter()
.map(|query| { .map(|query| {
let query = &query;
// make sure we get a compilation error if a field gets added to / removed from SearchQueryWithIndex // make sure we get a compilation error if a field gets added to / removed from SearchQueryWithIndex
let SearchQueryWithIndex { let SearchQueryWithIndex {
index_uid, index_uid,
federation_options: _,
q: _, q: _,
vector: _, vector: _,
offset: _, offset: _,
@@ -1171,17 +1119,14 @@ impl MultiSearchAggregator {
attributes_to_search_on: _, attributes_to_search_on: _,
hybrid: _, hybrid: _,
ranking_score_threshold: _, ranking_score_threshold: _,
locales: _,
} = query; } = query;
index_uid.as_str() index_uid.as_str()
}) })
.collect(); .collect();
let show_ranking_score = let show_ranking_score = query.iter().any(|query| query.show_ranking_score);
federated_search.queries.iter().any(|query| query.show_ranking_score); let show_ranking_score_details = query.iter().any(|query| query.show_ranking_score_details);
let show_ranking_score_details =
federated_search.queries.iter().any(|query| query.show_ranking_score_details);
Self { Self {
timestamp, timestamp,
@@ -1189,11 +1134,10 @@ impl MultiSearchAggregator {
total_succeeded: 0, total_succeeded: 0,
total_distinct_index_count: distinct_indexes.len(), total_distinct_index_count: distinct_indexes.len(),
total_single_index: if distinct_indexes.len() == 1 { 1 } else { 0 }, total_single_index: if distinct_indexes.len() == 1 { 1 } else { 0 },
total_search_count: federated_search.queries.len(), total_search_count: query.len(),
show_ranking_score, show_ranking_score,
show_ranking_score_details, show_ranking_score_details,
user_agents, user_agents,
use_federation,
} }
} }
@@ -1219,7 +1163,6 @@ impl MultiSearchAggregator {
let show_ranking_score_details = let show_ranking_score_details =
this.show_ranking_score_details || other.show_ranking_score_details; this.show_ranking_score_details || other.show_ranking_score_details;
let mut user_agents = this.user_agents; let mut user_agents = this.user_agents;
let use_federation = this.use_federation || other.use_federation;
for user_agent in other.user_agents.into_iter() { for user_agent in other.user_agents.into_iter() {
user_agents.insert(user_agent); user_agents.insert(user_agent);
@@ -1236,7 +1179,6 @@ impl MultiSearchAggregator {
user_agents, user_agents,
show_ranking_score, show_ranking_score,
show_ranking_score_details, show_ranking_score_details,
use_federation,
// do not add _ or ..Default::default() here // do not add _ or ..Default::default() here
}; };
@@ -1255,7 +1197,6 @@ impl MultiSearchAggregator {
user_agents, user_agents,
show_ranking_score, show_ranking_score,
show_ranking_score_details, show_ranking_score_details,
use_federation,
} = self; } = self;
if total_received == 0 { if total_received == 0 {
@@ -1280,9 +1221,6 @@ impl MultiSearchAggregator {
"scoring": { "scoring": {
"show_ranking_score": show_ranking_score, "show_ranking_score": show_ranking_score,
"show_ranking_score_details": show_ranking_score_details, "show_ranking_score_details": show_ranking_score_details,
},
"federation": {
"use_federation": use_federation,
} }
}); });
@@ -1329,7 +1267,6 @@ impl FacetSearchAggregator {
attributes_to_search_on, attributes_to_search_on,
hybrid, hybrid,
ranking_score_threshold, ranking_score_threshold,
locales,
} = query; } = query;
let mut ret = Self::default(); let mut ret = Self::default();
@@ -1345,8 +1282,7 @@ impl FacetSearchAggregator {
|| *matching_strategy != MatchingStrategy::default() || *matching_strategy != MatchingStrategy::default()
|| attributes_to_search_on.is_some() || attributes_to_search_on.is_some()
|| hybrid.is_some() || hybrid.is_some()
|| ranking_score_threshold.is_some() || ranking_score_threshold.is_some();
|| locales.is_some();
ret ret
} }
@@ -1533,75 +1469,6 @@ impl DocumentsAggregator {
} }
} }
#[derive(Default)]
pub struct EditDocumentsByFunctionAggregator {
timestamp: Option<OffsetDateTime>,
// Set to true if at least one request was filtered
filtered: bool,
// Set to true if at least one request contained a context
with_context: bool,
// context
user_agents: HashSet<String>,
index_creation: bool,
}
impl EditDocumentsByFunctionAggregator {
pub fn from_query(
documents_query: &DocumentEditionByFunction,
index_creation: bool,
request: &HttpRequest,
) -> Self {
let DocumentEditionByFunction { filter, context, function: _ } = documents_query;
Self {
timestamp: Some(OffsetDateTime::now_utc()),
user_agents: extract_user_agents(request).into_iter().collect(),
filtered: filter.is_some(),
with_context: context.is_some(),
index_creation,
}
}
/// Aggregate one [DocumentsAggregator] into another.
pub fn aggregate(&mut self, other: Self) {
let Self { timestamp, user_agents, index_creation, filtered, with_context } = other;
if self.timestamp.is_none() {
self.timestamp = timestamp;
}
// we can't create a union because there is no `into_union` method
for user_agent in user_agents {
self.user_agents.insert(user_agent);
}
self.index_creation |= index_creation;
self.filtered |= filtered;
self.with_context |= with_context;
}
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
let Self { timestamp, user_agents, index_creation, filtered, with_context } = self;
let properties = json!({
"user-agent": user_agents,
"filtered": filtered,
"with_context": with_context,
"index_creation": index_creation,
});
Some(Track {
timestamp,
user: user.clone(),
event: event_name.to_string(),
properties,
..Default::default()
})
}
}
#[derive(Default, Serialize)] #[derive(Default, Serialize)]
pub struct DocumentsDeletionAggregator { pub struct DocumentsDeletionAggregator {
#[serde(skip)] #[serde(skip)]

View File

@@ -1,6 +1,6 @@
use actix_web as aweb; use actix_web as aweb;
use aweb::error::{JsonPayloadError, QueryPayloadError}; use aweb::error::{JsonPayloadError, QueryPayloadError};
use byte_unit::{Byte, UnitType}; use byte_unit::Byte;
use meilisearch_types::document_formats::{DocumentFormatError, PayloadType}; use meilisearch_types::document_formats::{DocumentFormatError, PayloadType};
use meilisearch_types::error::{Code, ErrorCode, ResponseError}; use meilisearch_types::error::{Code, ErrorCode, ResponseError};
use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError}; use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError};
@@ -27,17 +27,13 @@ pub enum MeilisearchHttpError {
EmptyFilter, EmptyFilter,
#[error("Invalid syntax for the filter parameter: `expected {}, found: {1}`.", .0.join(", "))] #[error("Invalid syntax for the filter parameter: `expected {}, found: {1}`.", .0.join(", "))]
InvalidExpression(&'static [&'static str], Value), InvalidExpression(&'static [&'static str], Value),
#[error("Using `federationOptions` is not allowed in a non-federated search.\n Hint: remove `federationOptions` from query #{0} or add `federation: {{}}` to the request.")]
FederationOptionsInNonFederatedRequest(usize),
#[error("Inside `.queries[{0}]`: Using pagination options is not allowed in federated queries.\n Hint: remove `{1}` from query #{0} or remove `federation: {{}}` from the request")]
PaginationInFederatedQuery(usize, &'static str),
#[error("A {0} payload is missing.")] #[error("A {0} payload is missing.")]
MissingPayload(PayloadType), MissingPayload(PayloadType),
#[error("Too many search requests running at the same time: {0}. Retry after 10s.")] #[error("Too many search requests running at the same time: {0}. Retry after 10s.")]
TooManySearchRequests(usize), TooManySearchRequests(usize),
#[error("Internal error: Search limiter is down.")] #[error("Internal error: Search limiter is down.")]
SearchLimiterIsDown, SearchLimiterIsDown,
#[error("The provided payload reached the size limit. The maximum accepted payload size is {}.", Byte::from_u64(*.0 as u64).get_appropriate_unit(UnitType::Binary))] #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.", Byte::from_bytes(*.0 as u64).get_appropriate_unit(true))]
PayloadTooLarge(usize), PayloadTooLarge(usize),
#[error("Two indexes must be given for each swap. The list `[{}]` contains {} indexes.", #[error("Two indexes must be given for each swap. The list `[{}]` contains {} indexes.",
.0.iter().map(|uid| format!("\"{uid}\"")).collect::<Vec<_>>().join(", "), .0.len() .0.iter().map(|uid| format!("\"{uid}\"")).collect::<Vec<_>>().join(", "), .0.len()
@@ -90,12 +86,6 @@ impl ErrorCode for MeilisearchHttpError {
MeilisearchHttpError::DocumentFormat(e) => e.error_code(), MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
MeilisearchHttpError::Join(_) => Code::Internal, MeilisearchHttpError::Join(_) => Code::Internal,
MeilisearchHttpError::MissingSearchHybrid => Code::MissingSearchHybrid, MeilisearchHttpError::MissingSearchHybrid => Code::MissingSearchHybrid,
MeilisearchHttpError::FederationOptionsInNonFederatedRequest(_) => {
Code::InvalidMultiSearchFederationOptions
}
MeilisearchHttpError::PaginationInFederatedQuery(_, _) => {
Code::InvalidMultiSearchQueryPagination
}
} }
} }
} }
@@ -108,29 +98,14 @@ impl From<MeilisearchHttpError> for aweb::Error {
impl From<aweb::error::PayloadError> for MeilisearchHttpError { impl From<aweb::error::PayloadError> for MeilisearchHttpError {
fn from(error: aweb::error::PayloadError) -> Self { fn from(error: aweb::error::PayloadError) -> Self {
match error { MeilisearchHttpError::Payload(PayloadError::Payload(error))
aweb::error::PayloadError::Incomplete(_) => MeilisearchHttpError::Payload(
PayloadError::Payload(ActixPayloadError::IncompleteError),
),
_ => MeilisearchHttpError::Payload(PayloadError::Payload(
ActixPayloadError::OtherError(error),
)),
}
} }
} }
#[derive(Debug, thiserror::Error)]
pub enum ActixPayloadError {
#[error("The provided payload is incomplete and cannot be parsed")]
IncompleteError,
#[error(transparent)]
OtherError(aweb::error::PayloadError),
}
#[derive(Debug, thiserror::Error)] #[derive(Debug, thiserror::Error)]
pub enum PayloadError { pub enum PayloadError {
#[error(transparent)] #[error(transparent)]
Payload(ActixPayloadError), Payload(aweb::error::PayloadError),
#[error(transparent)] #[error(transparent)]
Json(JsonPayloadError), Json(JsonPayloadError),
#[error(transparent)] #[error(transparent)]
@@ -147,15 +122,13 @@ impl ErrorCode for PayloadError {
fn error_code(&self) -> Code { fn error_code(&self) -> Code {
match self { match self {
PayloadError::Payload(e) => match e { PayloadError::Payload(e) => match e {
ActixPayloadError::IncompleteError => Code::BadRequest, aweb::error::PayloadError::Incomplete(_) => Code::Internal,
ActixPayloadError::OtherError(error) => match error { aweb::error::PayloadError::EncodingCorrupted => Code::Internal,
aweb::error::PayloadError::EncodingCorrupted => Code::Internal, aweb::error::PayloadError::Overflow => Code::PayloadTooLarge,
aweb::error::PayloadError::Overflow => Code::PayloadTooLarge, aweb::error::PayloadError::UnknownLength => Code::Internal,
aweb::error::PayloadError::UnknownLength => Code::Internal, aweb::error::PayloadError::Http2Payload(_) => Code::Internal,
aweb::error::PayloadError::Http2Payload(_) => Code::Internal, aweb::error::PayloadError::Io(_) => Code::Internal,
aweb::error::PayloadError::Io(_) => Code::Internal, _ => todo!(),
_ => todo!(),
},
}, },
PayloadError::Json(err) => match err { PayloadError::Json(err) => match err {
JsonPayloadError::Overflow { .. } => Code::PayloadTooLarge, JsonPayloadError::Overflow { .. } => Code::PayloadTooLarge,

View File

@@ -12,8 +12,6 @@ use futures::Future;
use meilisearch_auth::{AuthController, AuthFilter}; use meilisearch_auth::{AuthController, AuthFilter};
use meilisearch_types::error::{Code, ResponseError}; use meilisearch_types::error::{Code, ResponseError};
use self::policies::AuthError;
pub struct GuardedData<P, D> { pub struct GuardedData<P, D> {
data: D, data: D,
filters: AuthFilter, filters: AuthFilter,
@@ -37,12 +35,12 @@ impl<P, D> GuardedData<P, D> {
let missing_master_key = auth.get_master_key().is_none(); let missing_master_key = auth.get_master_key().is_none();
match Self::authenticate(auth, token, index).await? { match Self::authenticate(auth, token, index).await? {
Ok(filters) => match data { Some(filters) => match data {
Some(data) => Ok(Self { data, filters, _marker: PhantomData }), Some(data) => Ok(Self { data, filters, _marker: PhantomData }),
None => Err(AuthenticationError::IrretrievableState.into()), None => Err(AuthenticationError::IrretrievableState.into()),
}, },
Err(_) if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()), None if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()),
Err(e) => Err(ResponseError::from_msg(e.to_string(), Code::InvalidApiKey)), None => Err(AuthenticationError::InvalidToken.into()),
} }
} }
@@ -53,12 +51,12 @@ impl<P, D> GuardedData<P, D> {
let missing_master_key = auth.get_master_key().is_none(); let missing_master_key = auth.get_master_key().is_none();
match Self::authenticate(auth, String::new(), None).await? { match Self::authenticate(auth, String::new(), None).await? {
Ok(filters) => match data { Some(filters) => match data {
Some(data) => Ok(Self { data, filters, _marker: PhantomData }), Some(data) => Ok(Self { data, filters, _marker: PhantomData }),
None => Err(AuthenticationError::IrretrievableState.into()), None => Err(AuthenticationError::IrretrievableState.into()),
}, },
Err(_) if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()), None if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()),
Err(_) => Err(AuthenticationError::MissingAuthorizationHeader.into()), None => Err(AuthenticationError::MissingAuthorizationHeader.into()),
} }
} }
@@ -66,7 +64,7 @@ impl<P, D> GuardedData<P, D> {
auth: Data<AuthController>, auth: Data<AuthController>,
token: String, token: String,
index: Option<String>, index: Option<String>,
) -> Result<Result<AuthFilter, AuthError>, ResponseError> ) -> Result<Option<AuthFilter>, ResponseError>
where where
P: Policy + 'static, P: Policy + 'static,
{ {
@@ -129,14 +127,13 @@ pub trait Policy {
auth: Data<AuthController>, auth: Data<AuthController>,
token: &str, token: &str,
index: Option<&str>, index: Option<&str>,
) -> Result<AuthFilter, policies::AuthError>; ) -> Option<AuthFilter>;
} }
pub mod policies { pub mod policies {
use actix_web::web::Data; use actix_web::web::Data;
use jsonwebtoken::{decode, Algorithm, DecodingKey, Validation}; use jsonwebtoken::{decode, Algorithm, DecodingKey, Validation};
use meilisearch_auth::{AuthController, AuthFilter, SearchRules}; use meilisearch_auth::{AuthController, AuthFilter, SearchRules};
use meilisearch_types::error::{Code, ErrorCode};
// reexport actions in policies in order to be used in routes configuration. // reexport actions in policies in order to be used in routes configuration.
pub use meilisearch_types::keys::{actions, Action}; pub use meilisearch_types::keys::{actions, Action};
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
@@ -147,53 +144,11 @@ pub mod policies {
enum TenantTokenOutcome { enum TenantTokenOutcome {
NotATenantToken, NotATenantToken,
Invalid,
Expired,
Valid(Uuid, SearchRules), Valid(Uuid, SearchRules),
} }
#[derive(thiserror::Error, Debug)]
pub enum AuthError {
#[error("Tenant token expired. Was valid up to `{exp}` and we're now `{now}`.")]
ExpiredTenantToken { exp: i64, now: i64 },
#[error("The provided API key is invalid.")]
InvalidApiKey,
#[error("The provided tenant token cannot acces the index `{index}`, allowed indexes are {allowed:?}.")]
TenantTokenAccessingnUnauthorizedIndex { index: String, allowed: Vec<String> },
#[error(
"The API key used to generate this tenant token cannot acces the index `{index}`."
)]
TenantTokenApiKeyAccessingnUnauthorizedIndex { index: String },
#[error(
"The API key cannot acces the index `{index}`, authorized indexes are {allowed:?}."
)]
ApiKeyAccessingnUnauthorizedIndex { index: String, allowed: Vec<String> },
#[error("The provided tenant token is invalid.")]
InvalidTenantToken,
#[error("Could not decode tenant token, {0}.")]
CouldNotDecodeTenantToken(jsonwebtoken::errors::Error),
#[error("Invalid action `{0}`.")]
InternalInvalidAction(u8),
}
impl From<jsonwebtoken::errors::Error> for AuthError {
fn from(error: jsonwebtoken::errors::Error) -> Self {
use jsonwebtoken::errors::ErrorKind;
match error.kind() {
ErrorKind::InvalidToken => AuthError::InvalidTenantToken,
_ => AuthError::CouldNotDecodeTenantToken(error),
}
}
}
impl ErrorCode for AuthError {
fn error_code(&self) -> Code {
match self {
AuthError::InternalInvalidAction(_) => Code::Internal,
_ => Code::InvalidApiKey,
}
}
}
fn tenant_token_validation() -> Validation { fn tenant_token_validation() -> Validation {
let mut validation = Validation::default(); let mut validation = Validation::default();
validation.validate_exp = false; validation.validate_exp = false;
@@ -203,15 +158,15 @@ pub mod policies {
} }
/// Extracts the key id used to sign the payload, without performing any validation. /// Extracts the key id used to sign the payload, without performing any validation.
fn extract_key_id(token: &str) -> Result<Uuid, AuthError> { fn extract_key_id(token: &str) -> Option<Uuid> {
let mut validation = tenant_token_validation(); let mut validation = tenant_token_validation();
validation.insecure_disable_signature_validation(); validation.insecure_disable_signature_validation();
let dummy_key = DecodingKey::from_secret(b"secret"); let dummy_key = DecodingKey::from_secret(b"secret");
let token_data = decode::<Claims>(token, &dummy_key, &validation)?; let token_data = decode::<Claims>(token, &dummy_key, &validation).ok()?;
// get token fields without validating it. // get token fields without validating it.
let Claims { api_key_uid, .. } = token_data.claims; let Claims { api_key_uid, .. } = token_data.claims;
Ok(api_key_uid) Some(api_key_uid)
} }
fn is_keys_action(action: u8) -> bool { fn is_keys_action(action: u8) -> bool {
@@ -232,102 +187,76 @@ pub mod policies {
auth: Data<AuthController>, auth: Data<AuthController>,
token: &str, token: &str,
index: Option<&str>, index: Option<&str>,
) -> Result<AuthFilter, AuthError> { ) -> Option<AuthFilter> {
// authenticate if token is the master key. // authenticate if token is the master key.
// Without a master key, all routes are accessible except the key-related routes. // Without a master key, all routes are accessible except the key-related routes.
if auth.get_master_key().map_or_else(|| !is_keys_action(A), |mk| mk == token) { if auth.get_master_key().map_or_else(|| !is_keys_action(A), |mk| mk == token) {
return Ok(AuthFilter::default()); return Some(AuthFilter::default());
} }
let (key_uuid, search_rules) = let (key_uuid, search_rules) =
match ActionPolicy::<A>::authenticate_tenant_token(&auth, token) { match ActionPolicy::<A>::authenticate_tenant_token(&auth, token) {
Ok(TenantTokenOutcome::Valid(key_uuid, search_rules)) => { TenantTokenOutcome::Valid(key_uuid, search_rules) => {
(key_uuid, Some(search_rules)) (key_uuid, Some(search_rules))
} }
Ok(TenantTokenOutcome::NotATenantToken) TenantTokenOutcome::Expired => return None,
| Err(AuthError::InvalidTenantToken) => ( TenantTokenOutcome::Invalid => return None,
auth.get_optional_uid_from_encoded_key(token.as_bytes()) TenantTokenOutcome::NotATenantToken => {
.map_err(|_e| AuthError::InvalidApiKey)? (auth.get_optional_uid_from_encoded_key(token.as_bytes()).ok()??, None)
.ok_or(AuthError::InvalidApiKey)?, }
None,
),
Err(e) => return Err(e),
}; };
// check that the indexes are allowed // check that the indexes are allowed
let action = Action::from_repr(A).ok_or(AuthError::InternalInvalidAction(A))?; let action = Action::from_repr(A)?;
let auth_filter = auth let auth_filter = auth.get_key_filters(key_uuid, search_rules).ok()?;
.get_key_filters(key_uuid, search_rules) if auth.is_key_authorized(key_uuid, action, index).unwrap_or(false)
.map_err(|_e| AuthError::InvalidApiKey)?; && index.map(|index| auth_filter.is_index_authorized(index)).unwrap_or(true)
{
// First check if the index is authorized in the tenant token, this is a public return Some(auth_filter);
// information, we can return a nice error message.
if let Some(index) = index {
if !auth_filter.tenant_token_is_index_authorized(index) {
return Err(AuthError::TenantTokenAccessingnUnauthorizedIndex {
index: index.to_string(),
allowed: auth_filter.tenant_token_list_index_authorized(),
});
}
if !auth_filter.api_key_is_index_authorized(index) {
if auth_filter.is_tenant_token() {
// If the error comes from a tenant token we cannot share the list
// of authorized indexes in the API key. This is not public information.
return Err(AuthError::TenantTokenApiKeyAccessingnUnauthorizedIndex {
index: index.to_string(),
});
} else {
// Otherwise we can share the list
// of authorized indexes in the API key.
return Err(AuthError::ApiKeyAccessingnUnauthorizedIndex {
index: index.to_string(),
allowed: auth_filter.api_key_list_index_authorized(),
});
}
}
}
if auth.is_key_authorized(key_uuid, action, index).unwrap_or(false) {
return Ok(auth_filter);
} }
Err(AuthError::InvalidApiKey) None
} }
} }
impl<const A: u8> ActionPolicy<A> { impl<const A: u8> ActionPolicy<A> {
fn authenticate_tenant_token( fn authenticate_tenant_token(auth: &AuthController, token: &str) -> TenantTokenOutcome {
auth: &AuthController,
token: &str,
) -> Result<TenantTokenOutcome, AuthError> {
// Only search action can be accessed by a tenant token. // Only search action can be accessed by a tenant token.
if A != actions::SEARCH { if A != actions::SEARCH {
return Ok(TenantTokenOutcome::NotATenantToken); return TenantTokenOutcome::NotATenantToken;
} }
let uid = extract_key_id(token)?; let uid = if let Some(uid) = extract_key_id(token) {
uid
} else {
return TenantTokenOutcome::NotATenantToken;
};
// Check if tenant token is valid. // Check if tenant token is valid.
let key = if let Some(key) = auth.generate_key(uid) { let key = if let Some(key) = auth.generate_key(uid) {
key key
} else { } else {
return Err(AuthError::InvalidTenantToken); return TenantTokenOutcome::Invalid;
}; };
let data = decode::<Claims>( let data = if let Ok(data) = decode::<Claims>(
token, token,
&DecodingKey::from_secret(key.as_bytes()), &DecodingKey::from_secret(key.as_bytes()),
&tenant_token_validation(), &tenant_token_validation(),
)?; ) {
data
} else {
return TenantTokenOutcome::Invalid;
};
// Check if token is expired. // Check if token is expired.
if let Some(exp) = data.claims.exp { if let Some(exp) = data.claims.exp {
let now = OffsetDateTime::now_utc().unix_timestamp(); if OffsetDateTime::now_utc().unix_timestamp() > exp {
if now > exp { return TenantTokenOutcome::Expired;
return Err(AuthError::ExpiredTenantToken { exp, now });
} }
} }
Ok(TenantTokenOutcome::Valid(uid, data.claims.search_rules)) TenantTokenOutcome::Valid(uid, data.claims.search_rules)
} }
} }

View File

@@ -13,23 +13,23 @@ pub mod search_queue;
use std::fs::File; use std::fs::File;
use std::io::{BufReader, BufWriter}; use std::io::{BufReader, BufWriter};
use std::num::NonZeroUsize;
use std::path::Path; use std::path::Path;
use std::str::FromStr;
use std::sync::Arc; use std::sync::Arc;
use std::thread; use std::thread::{self, available_parallelism};
use std::time::Duration; use std::time::Duration;
use actix_cors::Cors; use actix_cors::Cors;
use actix_http::body::MessageBody; use actix_http::body::MessageBody;
use actix_web::dev::{ServiceFactory, ServiceResponse}; use actix_web::dev::{ServiceFactory, ServiceResponse};
use actix_web::error::JsonPayloadError; use actix_web::error::JsonPayloadError;
use actix_web::http::header::{CONTENT_TYPE, USER_AGENT};
use actix_web::web::Data; use actix_web::web::Data;
use actix_web::{web, HttpRequest}; use actix_web::{web, HttpRequest};
use analytics::Analytics; use analytics::Analytics;
use anyhow::bail; use anyhow::bail;
use error::PayloadError; use error::PayloadError;
use extractors::payload::PayloadConfig; use extractors::payload::PayloadConfig;
use http::header::CONTENT_TYPE;
use index_scheduler::{IndexScheduler, IndexSchedulerOptions}; use index_scheduler::{IndexScheduler, IndexSchedulerOptions};
use meilisearch_auth::AuthController; use meilisearch_auth::AuthController;
use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader}; use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
@@ -117,7 +117,6 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
pub fn create_app( pub fn create_app(
index_scheduler: Data<IndexScheduler>, index_scheduler: Data<IndexScheduler>,
auth_controller: Data<AuthController>, auth_controller: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: Opt, opt: Opt,
logs: (LogRouteHandle, LogStderrHandle), logs: (LogRouteHandle, LogStderrHandle),
analytics: Arc<dyn Analytics>, analytics: Arc<dyn Analytics>,
@@ -137,7 +136,6 @@ pub fn create_app(
s, s,
index_scheduler.clone(), index_scheduler.clone(),
auth_controller.clone(), auth_controller.clone(),
search_queue.clone(),
&opt, &opt,
logs, logs,
analytics.clone(), analytics.clone(),
@@ -169,7 +167,7 @@ impl tracing_actix_web::RootSpanBuilder for AwebTracingLogger {
let conn_info = request.connection_info(); let conn_info = request.connection_info();
let headers = request.headers(); let headers = request.headers();
let user_agent = headers let user_agent = headers
.get(USER_AGENT) .get(http::header::USER_AGENT)
.map(|value| String::from_utf8_lossy(value.as_bytes()).into_owned()) .map(|value| String::from_utf8_lossy(value.as_bytes()).into_owned())
.unwrap_or_default(); .unwrap_or_default();
info_span!("HTTP request", method = %request.method(), host = conn_info.host(), route = %request.path(), query_parameters = %request.query_string(), %user_agent, status_code = Empty, error = Empty) info_span!("HTTP request", method = %request.method(), host = conn_info.host(), route = %request.path(), query_parameters = %request.query_string(), %user_agent, status_code = Empty, error = Empty)
@@ -302,17 +300,18 @@ fn open_or_create_database_unchecked(
dumps_path: opt.dump_dir.clone(), dumps_path: opt.dump_dir.clone(),
webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()), webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()),
webhook_authorization_header: opt.task_webhook_authorization_header.clone(), webhook_authorization_header: opt.task_webhook_authorization_header.clone(),
task_db_size: opt.max_task_db_size.as_u64() as usize, task_db_size: opt.max_task_db_size.get_bytes() as usize,
index_base_map_size: opt.max_index_size.as_u64() as usize, index_base_map_size: opt.max_index_size.get_bytes() as usize,
enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage, enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
indexer_config: (&opt.indexer_options).try_into()?, indexer_config: (&opt.indexer_options).try_into()?,
autobatching_enabled: true, autobatching_enabled: true,
cleanup_enabled: !opt.experimental_replication_parameters, cleanup_enabled: !opt.experimental_replication_parameters,
max_number_of_tasks: 1_000_000, max_number_of_tasks: 1_000_000,
max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks, max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().as_u64() as usize, index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
index_count: DEFAULT_INDEX_COUNT, index_count: DEFAULT_INDEX_COUNT,
instance_features, instance_features,
compute_prefix_databases: !opt.experimental_disable_prefix_db,
})?) })?)
}; };
@@ -470,16 +469,19 @@ pub fn configure_data(
config: &mut web::ServiceConfig, config: &mut web::ServiceConfig,
index_scheduler: Data<IndexScheduler>, index_scheduler: Data<IndexScheduler>,
auth: Data<AuthController>, auth: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: &Opt, opt: &Opt,
(logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle), (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
analytics: Arc<dyn Analytics>, analytics: Arc<dyn Analytics>,
) { ) {
let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize; let search_queue = SearchQueue::new(
opt.experimental_search_queue_size,
available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
);
let http_payload_size_limit = opt.http_payload_size_limit.get_bytes() as usize;
config config
.app_data(index_scheduler) .app_data(index_scheduler)
.app_data(auth) .app_data(auth)
.app_data(search_queue) .app_data(web::Data::new(search_queue))
.app_data(web::Data::from(analytics)) .app_data(web::Data::from(analytics))
.app_data(web::Data::new(logs_route)) .app_data(web::Data::new(logs_route))
.app_data(web::Data::new(logs_stderr)) .app_data(web::Data::new(logs_stderr))

View File

@@ -1,11 +1,8 @@
use std::env; use std::env;
use std::io::{stderr, LineWriter, Write}; use std::io::{stderr, LineWriter, Write};
use std::num::NonZeroUsize;
use std::path::PathBuf; use std::path::PathBuf;
use std::str::FromStr; use std::str::FromStr;
use std::sync::Arc; use std::sync::Arc;
use std::thread::available_parallelism;
use std::time::Duration;
use actix_web::http::KeepAlive; use actix_web::http::KeepAlive;
use actix_web::web::Data; use actix_web::web::Data;
@@ -14,7 +11,6 @@ use index_scheduler::IndexScheduler;
use is_terminal::IsTerminal; use is_terminal::IsTerminal;
use meilisearch::analytics::Analytics; use meilisearch::analytics::Analytics;
use meilisearch::option::LogMode; use meilisearch::option::LogMode;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{ use meilisearch::{
analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle, analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
LogStderrType, Opt, SubscriberForSecondLayer, LogStderrType, Opt, SubscriberForSecondLayer,
@@ -76,19 +72,6 @@ fn on_panic(info: &std::panic::PanicInfo) {
#[actix_web::main] #[actix_web::main]
async fn main() -> anyhow::Result<()> { async fn main() -> anyhow::Result<()> {
try_main().await.inspect_err(|error| {
tracing::error!(%error);
let mut current = error.source();
let mut depth = 0;
while let Some(source) = current {
tracing::info!(%source, depth, "Error caused by");
current = source.source();
depth += 1;
}
})
}
async fn try_main() -> anyhow::Result<()> {
let (opt, config_read_from) = Opt::try_build()?; let (opt, config_read_from) = Opt::try_build()?;
std::panic::set_hook(Box::new(on_panic)); std::panic::set_hook(Box::new(on_panic));
@@ -152,23 +135,11 @@ async fn run_http(
let opt_clone = opt.clone(); let opt_clone = opt.clone();
let index_scheduler = Data::from(index_scheduler); let index_scheduler = Data::from(index_scheduler);
let auth_controller = Data::from(auth_controller); let auth_controller = Data::from(auth_controller);
let search_queue = SearchQueue::new(
opt.experimental_search_queue_size,
available_parallelism()
.unwrap_or(NonZeroUsize::new(2).unwrap())
.checked_mul(opt.experimental_nb_searches_per_core)
.unwrap_or(NonZeroUsize::MAX),
)
.with_time_to_abort(Duration::from_secs(
usize::from(opt.experimental_drop_search_after) as u64
));
let search_queue = Data::new(search_queue);
let http_server = HttpServer::new(move || { let http_server = HttpServer::new(move || {
create_app( create_app(
index_scheduler.clone(), index_scheduler.clone(),
auth_controller.clone(), auth_controller.clone(),
search_queue.clone(),
opt.clone(), opt.clone(),
logs.clone(), logs.clone(),
analytics.clone(), analytics.clone(),
@@ -180,7 +151,7 @@ async fn run_http(
.keep_alive(KeepAlive::Os); .keep_alive(KeepAlive::Os);
if let Some(config) = opt_clone.get_ssl_config()? { if let Some(config) = opt_clone.get_ssl_config()? {
http_server.bind_rustls_0_23(opt_clone.http_addr, config)?.run().await?; http_server.bind_rustls_021(opt_clone.http_addr, config)?.run().await?;
} else { } else {
http_server.bind(&opt_clone.http_addr)?.run().await?; http_server.bind(&opt_clone.http_addr)?.run().await?;
} }

View File

@@ -2,21 +2,23 @@ use std::env::VarError;
use std::ffi::OsStr; use std::ffi::OsStr;
use std::fmt::Display; use std::fmt::Display;
use std::io::{BufReader, Read}; use std::io::{BufReader, Read};
use std::num::{NonZeroUsize, ParseIntError}; use std::num::ParseIntError;
use std::ops::Deref; use std::ops::Deref;
use std::path::PathBuf; use std::path::PathBuf;
use std::str::FromStr; use std::str::FromStr;
use std::sync::Arc; use std::sync::Arc;
use std::{env, fmt, fs}; use std::{env, fmt, fs};
use byte_unit::{Byte, ParseError, UnitType}; use byte_unit::{Byte, ByteError};
use clap::Parser; use clap::Parser;
use meilisearch_types::features::InstanceTogglableFeatures; use meilisearch_types::features::InstanceTogglableFeatures;
use meilisearch_types::milli::update::IndexerConfig; use meilisearch_types::milli::update::IndexerConfig;
use meilisearch_types::milli::ThreadPoolNoAbortBuilder; use meilisearch_types::milli::ThreadPoolNoAbortBuilder;
use rustls::server::{ServerSessionMemoryCache, WebPkiClientVerifier}; use rustls::server::{
AllowAnyAnonymousOrAuthenticatedClient, AllowAnyAuthenticatedClient, ServerSessionMemoryCache,
};
use rustls::RootCertStore; use rustls::RootCertStore;
use rustls_pemfile::{certs, rsa_private_keys}; use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use sysinfo::{MemoryRefreshKind, RefreshKind, System}; use sysinfo::{MemoryRefreshKind, RefreshKind, System};
use url::Url; use url::Url;
@@ -52,15 +54,13 @@ const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
const MEILI_EXPERIMENTAL_LOGS_MODE: &str = "MEILI_EXPERIMENTAL_LOGS_MODE"; const MEILI_EXPERIMENTAL_LOGS_MODE: &str = "MEILI_EXPERIMENTAL_LOGS_MODE";
const MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS: &str = "MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS"; const MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS: &str = "MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS";
const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE"; const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE";
const MEILI_EXPERIMENTAL_CONTAINS_FILTER: &str = "MEILI_EXPERIMENTAL_CONTAINS_FILTER";
const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS"; const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
const MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE: &str = "MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE"; const MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE: &str = "MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE";
const MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER: &str = "MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER";
const MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE: &str = "MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE";
const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str = const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
"MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE"; "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str = const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str =
"MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS"; "MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS";
const MEILI_EXPERIMENTAL_DISABLE_PREFIX_DB: &str = "MEILI_EXPERIMENTAL_DISABLE_PREFIXDB";
const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml"; const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
const DEFAULT_DB_PATH: &str = "./data.ms"; const DEFAULT_DB_PATH: &str = "./data.ms";
@@ -340,13 +340,6 @@ pub struct Opt {
#[serde(default)] #[serde(default)]
pub log_level: LogLevel, pub log_level: LogLevel,
/// Experimental contains filter feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/763>
///
/// Enables the experimental contains filter operator.
#[clap(long, env = MEILI_EXPERIMENTAL_CONTAINS_FILTER)]
#[serde(default)]
pub experimental_contains_filter: bool,
/// Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518> /// Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
/// ///
/// Enables the Prometheus metrics on the `GET /metrics` endpoint. /// Enables the Prometheus metrics on the `GET /metrics` endpoint.
@@ -363,22 +356,6 @@ pub struct Opt {
#[serde(default)] #[serde(default)]
pub experimental_search_queue_size: usize, pub experimental_search_queue_size: usize,
/// Experimental drop search after. For more information, see: <https://github.com/orgs/meilisearch/discussions/783>
///
/// Let you customize after how many seconds Meilisearch should consider a search request irrelevant and drop it.
/// The default value is 60.
#[clap(long, env = MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER, default_value_t = default_drop_search_after())]
#[serde(default = "default_drop_search_after")]
pub experimental_drop_search_after: NonZeroUsize,
/// Experimental number of searches per core. For more information, see: <https://github.com/orgs/meilisearch/discussions/784>
///
/// Lets you customize how many search requests can run on each core concurrently.
/// The default value is 4.
#[clap(long, env = MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE, default_value_t = default_nb_searches_per_core())]
#[serde(default = "default_nb_searches_per_core")]
pub experimental_nb_searches_per_core: NonZeroUsize,
/// Experimental logs mode feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/723> /// Experimental logs mode feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/723>
/// ///
/// Change the mode of the logs on the console. /// Change the mode of the logs on the console.
@@ -413,6 +390,11 @@ pub struct Opt {
#[serde(default = "default_limit_batched_tasks")] #[serde(default = "default_limit_batched_tasks")]
pub experimental_max_number_of_batched_tasks: usize, pub experimental_max_number_of_batched_tasks: usize,
/// Experimentally disable the prefix database, see: <https://github.com/orgs/meilisearch/discussions>
#[clap(long, env = MEILI_EXPERIMENTAL_DISABLE_PREFIX_DB)]
#[serde(default)]
pub experimental_disable_prefix_db: bool,
#[serde(flatten)] #[serde(flatten)]
#[clap(flatten)] #[clap(flatten)]
pub indexer_options: IndexerOpts, pub indexer_options: IndexerOpts,
@@ -507,15 +489,13 @@ impl Opt {
config_file_path: _, config_file_path: _,
#[cfg(feature = "analytics")] #[cfg(feature = "analytics")]
no_analytics, no_analytics,
experimental_contains_filter,
experimental_enable_metrics, experimental_enable_metrics,
experimental_search_queue_size, experimental_search_queue_size,
experimental_drop_search_after,
experimental_nb_searches_per_core,
experimental_logs_mode, experimental_logs_mode,
experimental_enable_logs_route, experimental_enable_logs_route,
experimental_replication_parameters, experimental_replication_parameters,
experimental_reduce_indexing_memory_usage, experimental_reduce_indexing_memory_usage,
experimental_disable_prefix_db,
} = self; } = self;
export_to_env_if_not_present(MEILI_DB_PATH, db_path); export_to_env_if_not_present(MEILI_DB_PATH, db_path);
export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr); export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -545,6 +525,10 @@ impl Opt {
MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS, MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
experimental_max_number_of_batched_tasks.to_string(), experimental_max_number_of_batched_tasks.to_string(),
); );
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_DISABLE_PREFIX_DB,
experimental_disable_prefix_db.to_string(),
);
if let Some(ssl_cert_path) = ssl_cert_path { if let Some(ssl_cert_path) = ssl_cert_path {
export_to_env_if_not_present(MEILI_SSL_CERT_PATH, ssl_cert_path); export_to_env_if_not_present(MEILI_SSL_CERT_PATH, ssl_cert_path);
} }
@@ -567,10 +551,6 @@ impl Opt {
export_to_env_if_not_present(MEILI_DUMP_DIR, dump_dir); export_to_env_if_not_present(MEILI_DUMP_DIR, dump_dir);
export_to_env_if_not_present(MEILI_LOG_LEVEL, log_level.to_string()); export_to_env_if_not_present(MEILI_LOG_LEVEL, log_level.to_string());
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_CONTAINS_FILTER,
experimental_contains_filter.to_string(),
);
export_to_env_if_not_present( export_to_env_if_not_present(
MEILI_EXPERIMENTAL_ENABLE_METRICS, MEILI_EXPERIMENTAL_ENABLE_METRICS,
experimental_enable_metrics.to_string(), experimental_enable_metrics.to_string(),
@@ -579,14 +559,6 @@ impl Opt {
MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE, MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE,
experimental_search_queue_size.to_string(), experimental_search_queue_size.to_string(),
); );
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER,
experimental_drop_search_after.to_string(),
);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE,
experimental_nb_searches_per_core.to_string(),
);
export_to_env_if_not_present( export_to_env_if_not_present(
MEILI_EXPERIMENTAL_LOGS_MODE, MEILI_EXPERIMENTAL_LOGS_MODE,
experimental_logs_mode.to_string(), experimental_logs_mode.to_string(),
@@ -608,21 +580,23 @@ impl Opt {
pub fn get_ssl_config(&self) -> anyhow::Result<Option<rustls::ServerConfig>> { 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) { if let (Some(cert_path), Some(key_path)) = (&self.ssl_cert_path, &self.ssl_key_path) {
let config = rustls::ServerConfig::builder(); let config = rustls::ServerConfig::builder().with_safe_defaults();
let config = match &self.ssl_auth_path { let config = match &self.ssl_auth_path {
Some(auth_path) => { Some(auth_path) => {
let roots = load_certs(auth_path.to_path_buf())?; let roots = load_certs(auth_path.to_path_buf())?;
let mut client_auth_roots = RootCertStore::empty(); let mut client_auth_roots = RootCertStore::empty();
for root in roots { for root in roots {
client_auth_roots.add(root).unwrap(); client_auth_roots.add(&root).unwrap();
} }
let mut client_verifier = if self.ssl_require_auth {
WebPkiClientVerifier::builder(client_auth_roots.into()); let verifier = AllowAnyAuthenticatedClient::new(client_auth_roots);
if !self.ssl_require_auth { config.with_client_cert_verifier(Arc::from(verifier))
client_verifier = client_verifier.allow_unauthenticated(); } else {
let verifier =
AllowAnyAnonymousOrAuthenticatedClient::new(client_auth_roots);
config.with_client_cert_verifier(Arc::from(verifier))
} }
config.with_client_cert_verifier(client_verifier.build()?)
} }
None => config.with_no_client_auth(), None => config.with_no_client_auth(),
}; };
@@ -631,7 +605,7 @@ impl Opt {
let privkey = load_private_key(key_path.to_path_buf())?; let privkey = load_private_key(key_path.to_path_buf())?;
let ocsp = load_ocsp(&self.ssl_ocsp_path)?; let ocsp = load_ocsp(&self.ssl_ocsp_path)?;
let mut config = config let mut config = config
.with_single_cert_with_ocsp(certs, privkey, ocsp) .with_single_cert_with_ocsp_and_sct(certs, privkey, ocsp, vec![])
.map_err(|_| anyhow::anyhow!("bad certificates/private key"))?; .map_err(|_| anyhow::anyhow!("bad certificates/private key"))?;
config.key_log = Arc::new(rustls::KeyLogFile::new()); config.key_log = Arc::new(rustls::KeyLogFile::new());
@@ -641,7 +615,7 @@ impl Opt {
} }
if self.ssl_tickets { if self.ssl_tickets {
config.ticketer = rustls::crypto::ring::Ticketer::new().unwrap(); config.ticketer = rustls::Ticketer::new().unwrap();
} }
Ok(Some(config)) Ok(Some(config))
@@ -654,7 +628,6 @@ impl Opt {
InstanceTogglableFeatures { InstanceTogglableFeatures {
metrics: self.experimental_enable_metrics, metrics: self.experimental_enable_metrics,
logs_route: self.experimental_enable_logs_route, logs_route: self.experimental_enable_logs_route,
contains_filter: self.experimental_contains_filter,
} }
} }
} }
@@ -712,7 +685,7 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
Ok(Self { Ok(Self {
log_every_n: Some(DEFAULT_LOG_EVERY_N), log_every_n: Some(DEFAULT_LOG_EVERY_N),
max_memory: other.max_indexing_memory.map(|b| b.as_u64() as usize), max_memory: other.max_indexing_memory.map(|b| b.get_bytes() as usize),
thread_pool: Some(thread_pool), thread_pool: Some(thread_pool),
max_positions_per_attributes: None, max_positions_per_attributes: None,
skip_index_budget: other.skip_index_budget, skip_index_budget: other.skip_index_budget,
@@ -726,25 +699,23 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
pub struct MaxMemory(Option<Byte>); pub struct MaxMemory(Option<Byte>);
impl FromStr for MaxMemory { impl FromStr for MaxMemory {
type Err = ParseError; type Err = ByteError;
fn from_str(s: &str) -> Result<MaxMemory, Self::Err> { fn from_str(s: &str) -> Result<MaxMemory, ByteError> {
Byte::from_str(s).map(Some).map(MaxMemory) Byte::from_str(s).map(Some).map(MaxMemory)
} }
} }
impl Default for MaxMemory { impl Default for MaxMemory {
fn default() -> MaxMemory { fn default() -> MaxMemory {
MaxMemory(total_memory_bytes().map(|bytes| bytes * 2 / 3).map(Byte::from_u64)) MaxMemory(total_memory_bytes().map(|bytes| bytes * 2 / 3).map(Byte::from_bytes))
} }
} }
impl fmt::Display for MaxMemory { impl fmt::Display for MaxMemory {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self.0 { match self.0 {
Some(memory) => { Some(memory) => write!(f, "{}", memory.get_appropriate_unit(true)),
write!(f, "{}", memory.get_appropriate_unit(UnitType::Binary))
}
None => f.write_str("unknown"), None => f.write_str("unknown"),
} }
} }
@@ -807,26 +778,21 @@ impl Deref for MaxThreads {
} }
} }
fn load_certs( fn load_certs(filename: PathBuf) -> anyhow::Result<Vec<rustls::Certificate>> {
filename: PathBuf,
) -> anyhow::Result<Vec<rustls::pki_types::CertificateDer<'static>>> {
let certfile = let certfile =
fs::File::open(filename).map_err(|_| anyhow::anyhow!("cannot open certificate file"))?; fs::File::open(filename).map_err(|_| anyhow::anyhow!("cannot open certificate file"))?;
let mut reader = BufReader::new(certfile); let mut reader = BufReader::new(certfile);
certs(&mut reader) certs(&mut reader)
.collect::<Result<Vec<_>, _>>() .map(|certs| certs.into_iter().map(rustls::Certificate).collect())
.map_err(|_| anyhow::anyhow!("cannot read certificate file")) .map_err(|_| anyhow::anyhow!("cannot read certificate file"))
} }
fn load_private_key( fn load_private_key(filename: PathBuf) -> anyhow::Result<rustls::PrivateKey> {
filename: PathBuf,
) -> anyhow::Result<rustls::pki_types::PrivateKeyDer<'static>> {
let rsa_keys = { let rsa_keys = {
let keyfile = fs::File::open(filename.clone()) let keyfile = fs::File::open(filename.clone())
.map_err(|_| anyhow::anyhow!("cannot open private key file"))?; .map_err(|_| anyhow::anyhow!("cannot open private key file"))?;
let mut reader = BufReader::new(keyfile); let mut reader = BufReader::new(keyfile);
rsa_private_keys(&mut reader) rsa_private_keys(&mut reader)
.collect::<Result<Vec<_>, _>>()
.map_err(|_| anyhow::anyhow!("file contains invalid rsa private key"))? .map_err(|_| anyhow::anyhow!("file contains invalid rsa private key"))?
}; };
@@ -834,21 +800,19 @@ fn load_private_key(
let keyfile = fs::File::open(filename) let keyfile = fs::File::open(filename)
.map_err(|_| anyhow::anyhow!("cannot open private key file"))?; .map_err(|_| anyhow::anyhow!("cannot open private key file"))?;
let mut reader = BufReader::new(keyfile); let mut reader = BufReader::new(keyfile);
rustls_pemfile::pkcs8_private_keys(&mut reader).collect::<Result<Vec<_>, _>>().map_err( pkcs8_private_keys(&mut reader).map_err(|_| {
|_| { anyhow::anyhow!(
anyhow::anyhow!( "file contains invalid pkcs8 private key (encrypted keys not supported)"
"file contains invalid pkcs8 private key (encrypted keys not supported)" )
) })?
},
)?
}; };
// prefer to load pkcs8 keys // prefer to load pkcs8 keys
if !pkcs8_keys.is_empty() { if !pkcs8_keys.is_empty() {
Ok(rustls::pki_types::PrivateKeyDer::Pkcs8(pkcs8_keys[0].clone_key())) Ok(rustls::PrivateKey(pkcs8_keys[0].clone()))
} else { } else {
assert!(!rsa_keys.is_empty()); assert!(!rsa_keys.is_empty());
Ok(rustls::pki_types::PrivateKeyDer::Pkcs1(rsa_keys[0].clone_key())) Ok(rustls::PrivateKey(rsa_keys[0].clone()))
} }
} }
@@ -891,11 +855,11 @@ fn default_env() -> String {
} }
fn default_max_index_size() -> Byte { fn default_max_index_size() -> Byte {
Byte::from_u64(INDEX_SIZE) Byte::from_bytes(INDEX_SIZE)
} }
fn default_max_task_db_size() -> Byte { fn default_max_task_db_size() -> Byte {
Byte::from_u64(TASK_DB_SIZE) Byte::from_bytes(TASK_DB_SIZE)
} }
fn default_http_payload_size_limit() -> Byte { fn default_http_payload_size_limit() -> Byte {
@@ -918,14 +882,6 @@ fn default_dump_dir() -> PathBuf {
PathBuf::from(DEFAULT_DUMP_DIR) PathBuf::from(DEFAULT_DUMP_DIR)
} }
fn default_drop_search_after() -> NonZeroUsize {
NonZeroUsize::new(60).unwrap()
}
fn default_nb_searches_per_core() -> NonZeroUsize {
NonZeroUsize::new(4).unwrap()
}
/// Indicates if a snapshot was scheduled, and if yes with which interval. /// Indicates if a snapshot was scheduled, and if yes with which interval.
#[derive(Debug, Default, Copy, Clone, Deserialize, Serialize)] #[derive(Debug, Default, Copy, Clone, Deserialize, Serialize)]
pub enum ScheduleSnapshot { pub enum ScheduleSnapshot {

View File

@@ -47,10 +47,6 @@ pub struct RuntimeTogglableFeatures {
pub metrics: Option<bool>, pub metrics: Option<bool>,
#[deserr(default)] #[deserr(default)]
pub logs_route: Option<bool>, pub logs_route: Option<bool>,
#[deserr(default)]
pub edit_documents_by_function: Option<bool>,
#[deserr(default)]
pub contains_filter: Option<bool>,
} }
async fn patch_features( async fn patch_features(
@@ -70,23 +66,13 @@ async fn patch_features(
vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store), vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
metrics: new_features.0.metrics.unwrap_or(old_features.metrics), metrics: new_features.0.metrics.unwrap_or(old_features.metrics),
logs_route: new_features.0.logs_route.unwrap_or(old_features.logs_route), logs_route: new_features.0.logs_route.unwrap_or(old_features.logs_route),
edit_documents_by_function: new_features
.0
.edit_documents_by_function
.unwrap_or(old_features.edit_documents_by_function),
contains_filter: new_features.0.contains_filter.unwrap_or(old_features.contains_filter),
}; };
// explicitly destructure for analytics rather than using the `Serialize` implementation, because // explicitly destructure for analytics rather than using the `Serialize` implementation, because
// the it renames to camelCase, which we don't want for analytics. // the it renames to camelCase, which we don't want for analytics.
// **Do not** ignore fields with `..` or `_` here, because we want to add them in the future. // **Do not** ignore fields with `..` or `_` here, because we want to add them in the future.
let meilisearch_types::features::RuntimeTogglableFeatures { let meilisearch_types::features::RuntimeTogglableFeatures { vector_store, metrics, logs_route } =
vector_store, new_features;
metrics,
logs_route,
edit_documents_by_function,
contains_filter,
} = new_features;
analytics.publish( analytics.publish(
"Experimental features Updated".to_string(), "Experimental features Updated".to_string(),
@@ -94,8 +80,6 @@ async fn patch_features(
"vector_store": vector_store, "vector_store": vector_store,
"metrics": metrics, "metrics": metrics,
"logs_route": logs_route, "logs_route": logs_route,
"edit_documents_by_function": edit_documents_by_function,
"contains_filter": contains_filter,
}), }),
Some(&req), Some(&req),
); );

View File

@@ -7,7 +7,7 @@ use bstr::ByteSlice as _;
use deserr::actix_web::{AwebJson, AwebQueryParameter}; use deserr::actix_web::{AwebJson, AwebQueryParameter};
use deserr::Deserr; use deserr::Deserr;
use futures::StreamExt; use futures::StreamExt;
use index_scheduler::{IndexScheduler, RoFeatures, TaskId}; use index_scheduler::{IndexScheduler, TaskId};
use meilisearch_types::deserr::query_params::Param; use meilisearch_types::deserr::query_params::Param;
use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError}; use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
use meilisearch_types::document_formats::{read_csv, read_json, read_ndjson, PayloadType}; use meilisearch_types::document_formats::{read_csv, read_json, read_ndjson, PayloadType};
@@ -82,7 +82,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
web::resource("/delete-batch").route(web::post().to(SeqHandler(delete_documents_batch))), web::resource("/delete-batch").route(web::post().to(SeqHandler(delete_documents_batch))),
) )
.service(web::resource("/delete").route(web::post().to(SeqHandler(delete_documents_by_filter)))) .service(web::resource("/delete").route(web::post().to(SeqHandler(delete_documents_by_filter))))
.service(web::resource("/edit").route(web::post().to(SeqHandler(edit_documents_by_function))))
.service(web::resource("/fetch").route(web::post().to(SeqHandler(documents_by_query_post)))) .service(web::resource("/fetch").route(web::post().to(SeqHandler(documents_by_query_post))))
.service( .service(
web::resource("/{document_id}") web::resource("/{document_id}")
@@ -260,15 +259,8 @@ fn documents_by_query(
let retrieve_vectors = RetrieveVectors::new(retrieve_vectors, features)?; let retrieve_vectors = RetrieveVectors::new(retrieve_vectors, features)?;
let index = index_scheduler.index(&index_uid)?; let index = index_scheduler.index(&index_uid)?;
let (total, documents) = retrieve_documents( let (total, documents) =
&index, retrieve_documents(&index, offset, limit, filter, fields, retrieve_vectors)?;
offset,
limit,
filter,
fields,
retrieve_vectors,
index_scheduler.features(),
)?;
let ret = PaginationView::new(offset, limit, total as usize, documents); let ret = PaginationView::new(offset, limit, total as usize, documents);
@@ -312,11 +304,7 @@ pub async fn replace_documents(
debug!(parameters = ?params, "Replace documents"); debug!(parameters = ?params, "Replace documents");
let params = params.into_inner(); let params = params.into_inner();
analytics.add_documents( analytics.add_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
&params,
index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
&req,
);
let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid); let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
let uid = get_task_id(&req, &opt)?; let uid = get_task_id(&req, &opt)?;
@@ -353,11 +341,7 @@ pub async fn update_documents(
let params = params.into_inner(); let params = params.into_inner();
debug!(parameters = ?params, "Update documents"); debug!(parameters = ?params, "Update documents");
analytics.add_documents( analytics.update_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
&params,
index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
&req,
);
let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid); let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
let uid = get_task_id(&req, &opt)?; let uid = get_task_id(&req, &opt)?;
@@ -572,9 +556,11 @@ pub async fn delete_documents_by_filter(
analytics.delete_documents(DocumentDeletionKind::PerFilter, &req); analytics.delete_documents(DocumentDeletionKind::PerFilter, &req);
// we ensure the filter is well formed before enqueuing it // we ensure the filter is well formed before enqueuing it
crate::search::parse_filter(&filter, Code::InvalidDocumentFilter, index_scheduler.features())? || -> Result<_, ResponseError> {
.ok_or(MeilisearchHttpError::EmptyFilter)?; Ok(crate::search::parse_filter(&filter)?.ok_or(MeilisearchHttpError::EmptyFilter)?)
}()
// and whatever was the error, the error code should always be an InvalidDocumentFilter
.map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter }; let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
let uid = get_task_id(&req, &opt)?; let uid = get_task_id(&req, &opt)?;
@@ -588,83 +574,6 @@ pub async fn delete_documents_by_filter(
Ok(HttpResponse::Accepted().json(task)) Ok(HttpResponse::Accepted().json(task))
} }
#[derive(Debug, Deserr)]
#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
pub struct DocumentEditionByFunction {
#[deserr(default, error = DeserrJsonError<InvalidDocumentFilter>)]
pub filter: Option<Value>,
#[deserr(default, error = DeserrJsonError<InvalidDocumentEditionContext>)]
pub context: Option<Value>,
#[deserr(error = DeserrJsonError<InvalidDocumentEditionFunctionFilter>, missing_field_error = DeserrJsonError::missing_document_edition_function)]
pub function: String,
}
pub async fn edit_documents_by_function(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ALL }>, Data<IndexScheduler>>,
index_uid: web::Path<String>,
params: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
req: HttpRequest,
opt: web::Data<Opt>,
analytics: web::Data<dyn Analytics>,
) -> Result<HttpResponse, ResponseError> {
debug!(parameters = ?params, "Edit documents by function");
index_scheduler
.features()
.check_edit_documents_by_function("Using the documents edit route")?;
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let index_uid = index_uid.into_inner();
let params = params.into_inner();
analytics.update_documents_by_function(
&params,
index_scheduler.index(&index_uid).is_err(),
&req,
);
let DocumentEditionByFunction { filter, context, function } = params;
let engine = milli::rhai::Engine::new();
if let Err(e) = engine.compile(&function) {
return Err(ResponseError::from_msg(e.to_string(), Code::BadRequest));
}
if let Some(ref filter) = filter {
// we ensure the filter is well formed before enqueuing it
crate::search::parse_filter(
filter,
Code::InvalidDocumentFilter,
index_scheduler.features(),
)?
.ok_or(MeilisearchHttpError::EmptyFilter)?;
}
let task = KindWithContent::DocumentEdition {
index_uid,
filter_expr: filter,
context: match context {
Some(Value::Object(m)) => Some(m),
None => None,
_ => {
return Err(ResponseError::from_msg(
"The context must be an object".to_string(),
Code::InvalidDocumentEditionContext,
))
}
},
function,
};
let uid = get_task_id(&req, &opt)?;
let dry_run = is_dry_run(&req, &opt)?;
let task: SummarizedTaskView =
tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
.await??
.into();
debug!(returns = ?task, "Edit documents by function");
Ok(HttpResponse::Accepted().json(task))
}
pub async fn clear_all_documents( pub async fn clear_all_documents(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>, index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
index_uid: web::Path<String>, index_uid: web::Path<String>,
@@ -706,8 +615,6 @@ fn some_documents<'a, 't: 'a>(
document.remove("_vectors"); document.remove("_vectors");
} }
RetrieveVectors::Retrieve => { RetrieveVectors::Retrieve => {
// Clippy is simply wrong
#[allow(clippy::manual_unwrap_or_default)]
let mut vectors = match document.remove("_vectors") { let mut vectors = match document.remove("_vectors") {
Some(Value::Object(map)) => map, Some(Value::Object(map)) => map,
_ => Default::default(), _ => Default::default(),
@@ -742,12 +649,12 @@ fn retrieve_documents<S: AsRef<str>>(
filter: Option<Value>, filter: Option<Value>,
attributes_to_retrieve: Option<Vec<S>>, attributes_to_retrieve: Option<Vec<S>>,
retrieve_vectors: RetrieveVectors, retrieve_vectors: RetrieveVectors,
features: RoFeatures,
) -> Result<(u64, Vec<Document>), ResponseError> { ) -> Result<(u64, Vec<Document>), ResponseError> {
let rtxn = index.read_txn()?; let rtxn = index.read_txn()?;
let filter = &filter; let filter = &filter;
let filter = if let Some(filter) = filter { let filter = if let Some(filter) = filter {
parse_filter(filter, Code::InvalidDocumentFilter, features)? parse_filter(filter)
.map_err(|err| ResponseError::from_msg(err.to_string(), Code::InvalidDocumentFilter))?
} else { } else {
None None
}; };

View File

@@ -6,7 +6,6 @@ use meilisearch_types::deserr::DeserrJsonError;
use meilisearch_types::error::deserr_codes::*; use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::error::ResponseError; use meilisearch_types::error::ResponseError;
use meilisearch_types::index_uid::IndexUid; use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::locales::Locale;
use serde_json::Value; use serde_json::Value;
use tracing::debug; use tracing::debug;
@@ -49,8 +48,6 @@ pub struct FacetSearchQuery {
pub attributes_to_search_on: Option<Vec<String>>, pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)] #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>, pub ranking_score_threshold: Option<RankingScoreThreshold>,
#[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
pub locales: Option<Vec<Locale>>,
} }
pub async fn search( pub async fn search(
@@ -70,7 +67,6 @@ pub async fn search(
let facet_query = query.facet_query.clone(); let facet_query = query.facet_query.clone();
let facet_name = query.facet_name.clone(); let facet_name = query.facet_name.clone();
let locales = query.locales.clone().map(|l| l.into_iter().map(Into::into).collect());
let mut search_query = SearchQuery::from(query); let mut search_query = SearchQuery::from(query);
// Tenant token search_rules. // Tenant token search_rules.
@@ -81,21 +77,11 @@ pub async fn search(
let index = index_scheduler.index(&index_uid)?; let index = index_scheduler.index(&index_uid)?;
let features = index_scheduler.features(); let features = index_scheduler.features();
let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?; let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
let permit = search_queue.try_get_search_permit().await?; let _permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || { let search_result = tokio::task::spawn_blocking(move || {
perform_facet_search( perform_facet_search(&index, search_query, facet_query, facet_name, search_kind)
&index,
search_query,
facet_query,
facet_name,
search_kind,
index_scheduler.features(),
locales,
)
}) })
.await; .await?;
permit.drop().await;
let search_result = search_result?;
if let Ok(ref search_result) = search_result { if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result); aggregate.succeed(search_result);
@@ -120,7 +106,6 @@ impl From<FacetSearchQuery> for SearchQuery {
attributes_to_search_on, attributes_to_search_on,
hybrid, hybrid,
ranking_score_threshold, ranking_score_threshold,
locales,
} = value; } = value;
SearchQuery { SearchQuery {
@@ -149,7 +134,6 @@ impl From<FacetSearchQuery> for SearchQuery {
attributes_to_search_on, attributes_to_search_on,
hybrid, hybrid,
ranking_score_threshold, ranking_score_threshold,
locales,
} }
} }
} }

View File

@@ -7,7 +7,6 @@ use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
use meilisearch_types::error::deserr_codes::*; use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::error::ResponseError; use meilisearch_types::error::ResponseError;
use meilisearch_types::index_uid::IndexUid; use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::locales::Locale;
use meilisearch_types::milli; use meilisearch_types::milli;
use meilisearch_types::serde_cs::vec::CS; use meilisearch_types::serde_cs::vec::CS;
use serde_json::Value; use serde_json::Value;
@@ -90,8 +89,6 @@ pub struct SearchQueryGet {
pub hybrid_semantic_ratio: Option<SemanticRatioGet>, pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)] #[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
pub ranking_score_threshold: Option<RankingScoreThresholdGet>, pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchLocales>)]
pub locales: Option<CS<Locale>>,
} }
#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)] #[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
@@ -178,7 +175,6 @@ impl From<SearchQueryGet> for SearchQuery {
attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()), attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
hybrid, hybrid,
ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0), ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
locales: other.locales.map(|o| o.into_iter().collect()),
} }
} }
} }
@@ -233,13 +229,11 @@ pub async fn search_with_url_query(
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?; let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?; let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
let permit = search_queue.try_get_search_permit().await?; let _permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || { let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features()) perform_search(&index, query, search_kind, retrieve_vector)
}) })
.await; .await?;
permit.drop().await;
let search_result = search_result?;
if let Ok(ref search_result) = search_result { if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result); aggregate.succeed(search_result);
} }
@@ -278,13 +272,11 @@ pub async fn search_with_post(
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?; let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?; let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
let permit = search_queue.try_get_search_permit().await?; let _permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || { let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features()) perform_search(&index, query, search_kind, retrieve_vectors)
}) })
.await; .await?;
permit.drop().await;
let search_result = search_result?;
if let Ok(ref search_result) = search_result { if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result); aggregate.succeed(search_result);
if search_result.degraded { if search_result.degraded {

Some files were not shown because too many files have changed in this diff Show More