Compare commits

..

5 Commits

Author SHA1 Message Date
Kerollmops
b126bf3aec Temporary use the charabia git repository to get the latest fixes 2023-09-19 10:15:17 +02:00
Kerollmops
e82ff56416 Enable by default the puffin server 2023-09-18 18:12:16 +02:00
Clément Renault
1b26dde438 Expose a new flag to limit the number of batched tasks 2023-09-18 18:11:12 +02:00
Tamo
3bb644b54d update the description of the cli argument 2023-09-18 18:10:46 +02:00
Clément Renault
34b9145db2 Fix the tests 2023-09-18 18:10:29 +02:00
62 changed files with 564 additions and 1175 deletions

View File

@@ -2,8 +2,8 @@ name: Create issue to upgrade dependencies
on:
schedule:
# Run the first of the month, every 6 month
- cron: '0 0 1 */6 *'
# Run the first of the month, every 3 month
- cron: '0 0 1 */3 *'
workflow_dispatch:
jobs:

View File

@@ -14,7 +14,6 @@ on:
env:
MEILI_MASTER_KEY: 'masterKey'
MEILI_NO_ANALYTICS: 'true'
DISABLE_COVERAGE: 'true'
jobs:
define-docker-image:
@@ -31,117 +30,6 @@ jobs:
if [[ $event == 'workflow_dispatch' ]]; then
echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
fi
- name: Docker image is ${{ steps.define-image.outputs.docker-image }}
run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
##########
## SDKs ##
##########
meilisearch-dotnet-tests:
needs: define-docker-image
name: .NET SDK tests
runs-on: ubuntu-latest
env:
MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-dotnet
- name: Setup .NET Core
uses: actions/setup-dotnet@v3
with:
dotnet-version: "6.0.x"
- name: Install dependencies
run: dotnet restore
- name: Build
run: dotnet build --configuration Release --no-restore
- name: Meilisearch (latest version) setup with Docker
run: docker compose up -d
- name: Run tests
run: dotnet test --no-restore --verbosity normal
meilisearch-dart-tests:
needs: define-docker-image
name: Dart SDK tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-dart
- uses: dart-lang/setup-dart@v1
with:
sdk: 3.1.1
- name: Install dependencies
run: dart pub get
- name: Run integration tests
run: dart test --concurrency=4
meilisearch-go-tests:
needs: define-docker-image
name: Go SDK tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- name: Set up Go
uses: actions/setup-go@v4
with:
go-version: stable
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-go
- name: Get dependencies
run: |
go get -v -t -d ./...
if [ -f Gopkg.toml ]; then
curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
dep ensure
fi
- name: Run integration tests
run: go test -v ./...
meilisearch-java-tests:
needs: define-docker-image
name: Java SDK tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-java
- name: Set up Java
uses: actions/setup-java@v3
with:
java-version: 8
distribution: 'zulu'
cache: gradle
- name: Grant execute permission for gradlew
run: chmod +x gradlew
- name: Build and run unit and integration tests
run: ./gradlew build integrationTest
meilisearch-js-tests:
needs: define-docker-image
@@ -178,6 +66,33 @@ jobs:
- name: Run Browser env
run: yarn test:env:browser
instant-meilisearch-tests:
needs: define-docker-image
name: instant-meilisearch tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/instant-meilisearch
- name: Setup node
uses: actions/setup-node@v3
with:
cache: yarn
- name: Install dependencies
run: yarn install
- name: Run tests
run: yarn test
- name: Build all the playgrounds and the packages
run: yarn build
meilisearch-php-tests:
needs: define-docker-image
name: PHP SDK tests
@@ -196,6 +111,8 @@ jobs:
repository: meilisearch/meilisearch-php
- name: Install PHP
uses: shivammathur/setup-php@v2
with:
coverage: none
- name: Validate composer.json and composer.lock
run: composer validate
- name: Install dependencies
@@ -232,6 +149,36 @@ jobs:
- name: Test with pytest
run: pipenv run pytest
meilisearch-go-tests:
needs: define-docker-image
name: Go SDK tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- name: Set up Go
uses: actions/setup-go@v4
with:
go-version: stable
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-go
- name: Get dependencies
run: |
go get -v -t -d ./...
if [ -f Gopkg.toml ]; then
curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
dep ensure
fi
- name: Run integration tests
run: go test -v ./...
meilisearch-ruby-tests:
needs: define-docker-image
name: Ruby SDK tests
@@ -277,110 +224,3 @@ jobs:
run: cargo build --verbose
- name: Run tests
run: cargo test --verbose
meilisearch-swift-tests:
needs: define-docker-image
name: Swift SDK tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-swift
- name: Run tests
run: swift test
########################
## FRONT-END PLUGINS ##
########################
meilisearch-js-plugins-tests:
needs: define-docker-image
name: meilisearch-js-plugins tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-js-plugins
- name: Setup node
uses: actions/setup-node@v3
with:
cache: yarn
- name: Install dependencies
run: yarn install
- name: Run tests
run: yarn test
- name: Build all the playgrounds and the packages
run: yarn build
########################
## BACK-END PLUGINS ###
########################
meilisearch-rails-tests:
needs: define-docker-image
name: meilisearch-rails tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-rails
- name: Set up Ruby 3
uses: ruby/setup-ruby@v1
with:
ruby-version: 3
bundler-cache: true
- name: Run tests
run: bundle exec rspec
meilisearch-symfony-tests:
needs: define-docker-image
name: meilisearch-symfony tests
runs-on: ubuntu-latest
services:
meilisearch:
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
env:
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
ports:
- '7700:7700'
steps:
- uses: actions/checkout@v3
with:
repository: meilisearch/meilisearch-symfony
- name: Install PHP
uses: shivammathur/setup-php@v2
with:
tools: composer:v2, flex
- name: Validate composer.json and composer.lock
run: composer validate
- name: Install dependencies
run: composer install --prefer-dist --no-progress --quiet
- name: Remove doctrine/annotations
run: composer remove --dev doctrine/annotations
- name: Run test suite
run: composer test:unit

View File

@@ -43,7 +43,7 @@ jobs:
toolchain: nightly
override: true
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.6.2
uses: Swatinem/rust-cache@v2.5.1
- name: Run cargo check without any default features
uses: actions-rs/cargo@v1
with:
@@ -65,7 +65,7 @@ jobs:
steps:
- uses: actions/checkout@v3
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.6.2
uses: Swatinem/rust-cache@v2.5.1
- name: Run cargo check without any default features
uses: actions-rs/cargo@v1
with:
@@ -123,10 +123,7 @@ jobs:
override: true
- name: Run cargo tree without default features and check lindera is not present
run: |
if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -vqz lindera; then
echo "lindera has been found in the sources and it shouldn't"
exit 1
fi
cargo tree -f '{p} {f}' -e normal --no-default-features | grep lindera -vqz
- name: Run cargo tree with default features and check lindera is pressent
run: |
cargo tree -f '{p} {f}' -e normal | grep lindera -qz
@@ -149,7 +146,7 @@ jobs:
toolchain: stable
override: true
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.6.2
uses: Swatinem/rust-cache@v2.5.1
- name: Run tests in debug
uses: actions-rs/cargo@v1
with:
@@ -168,7 +165,7 @@ jobs:
override: true
components: clippy
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.6.2
uses: Swatinem/rust-cache@v2.5.1
- name: Run cargo clippy
uses: actions-rs/cargo@v1
with:
@@ -187,7 +184,7 @@ jobs:
override: true
components: rustfmt
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.6.2
uses: Swatinem/rust-cache@v2.5.1
- name: Run cargo fmt
# Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
# Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate

63
Cargo.lock generated
View File

@@ -700,8 +700,7 @@ dependencies = [
[[package]]
name = "charabia"
version = "0.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "098219a776307414866165a03a9cc68c1578764fe3616fe979e1c280790ddd73"
source = "git+https://github.com/meilisearch/charabia?branch=main#5c3d09a7127dcf5e0e5d94d991c4d3d5ef4768cc"
dependencies = [
"aho-corasick",
"cow-utils",
@@ -2177,9 +2176,9 @@ dependencies = [
[[package]]
name = "lindera-cc-cedict-builder"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2d2e8f2ca97ddf952fe340642511b9c14b373cb2eef711d526bb8ef2ca0969b8"
checksum = "6f567a47e47b5420908424de2c6c5e424e3cafe588d0146bd128c0f3755758a3"
dependencies = [
"anyhow",
"bincode",
@@ -2196,9 +2195,9 @@ dependencies = [
[[package]]
name = "lindera-compress"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f72b460559bcbe8a9cee85ea4a5056133ed3abf373031191589236e656d65b59"
checksum = "49f3e553d55ebe9881fa5e5de588b0a153456e93564d17dfbef498912caf63a2"
dependencies = [
"anyhow",
"flate2",
@@ -2207,9 +2206,9 @@ dependencies = [
[[package]]
name = "lindera-core"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f586eb8a9393c32d5525e0e9336a3727bd1329674740097126f3b0bff8a1a1ea"
checksum = "a9a2440cc156a4a911a174ec68203543d1efb10df3a700a59b6bf581e453c726"
dependencies = [
"anyhow",
"bincode",
@@ -2224,9 +2223,9 @@ dependencies = [
[[package]]
name = "lindera-decompress"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1fb1facd8da698072fcc7338bd757730db53d59f313f44dd583fa03681dcc0e1"
checksum = "e077a410e61c962cb526f71b7effd62ffc607488a8f61869c937582d2ccb529b"
dependencies = [
"anyhow",
"flate2",
@@ -2235,9 +2234,9 @@ dependencies = [
[[package]]
name = "lindera-dictionary"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec7be7410b1da7017a8948986b87af67082f605e9a716f0989790d795d677f0c"
checksum = "d9f57491adf7b311a3ee87f5e4a36454df16a2ec73de4ef28b2106fac80bd782"
dependencies = [
"anyhow",
"bincode",
@@ -2255,9 +2254,9 @@ dependencies = [
[[package]]
name = "lindera-ipadic-builder"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "705d07f8a45d04fd95149f7ad41a26d1f9e56c9c00402be6f9dd05e3d88b99c6"
checksum = "a3476ec7748aebd2eb23d496ddfce5e7e0a5c031cffcd214451043e02d029f11"
dependencies = [
"anyhow",
"bincode",
@@ -2276,9 +2275,9 @@ dependencies = [
[[package]]
name = "lindera-ipadic-neologd-builder"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "633a93983ba13fba42328311a501091bd4a7aff0c94ae9eaa9d4733dd2b0468a"
checksum = "7b1c7576a02d5e4af2bf62de51790a01bc4b8bc0d0b6a6b86a46b157f5cb306d"
dependencies = [
"anyhow",
"bincode",
@@ -2297,9 +2296,9 @@ dependencies = [
[[package]]
name = "lindera-ko-dic"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a428e0d316b6c86f51bd919479692bc41ad840dba266ebc044663970f431ea18"
checksum = "b713ecd5b827d7d448c3c5eb3c6d5899ecaf22cd17087599996349a02c76828d"
dependencies = [
"bincode",
"byteorder",
@@ -2314,9 +2313,9 @@ dependencies = [
[[package]]
name = "lindera-ko-dic-builder"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2a5288704c6b8a069c0a1705c38758e836497698b50453373ab3d56c6f9a7ef8"
checksum = "3e545752f6487be87b572529ad594cb3b48d2ef20821516f598b2d152d23277b"
dependencies = [
"anyhow",
"bincode",
@@ -2334,9 +2333,9 @@ dependencies = [
[[package]]
name = "lindera-tokenizer"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "106ba439b2e87529d9bbedbb88d69f635baba1195c26502b308f55a85885fc81"
checksum = "24a2d4606a5a4da62ac4a3680ee884a75da7f0c892dc967fc9cb983ceba39a8f"
dependencies = [
"bincode",
"byteorder",
@@ -2349,9 +2348,9 @@ dependencies = [
[[package]]
name = "lindera-unidic"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3399b6dcfe1701333451d184ff3c677f433b320153427b146360c9e4bd8cb816"
checksum = "388b1bdf81794b5d5b8057ce0321c58ff4b90d676b637948ccc7863ae2f43d28"
dependencies = [
"bincode",
"byteorder",
@@ -2366,9 +2365,9 @@ dependencies = [
[[package]]
name = "lindera-unidic-builder"
version = "0.27.0"
version = "0.27.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b698227fdaeac32289173ab389b990d4eb00a40cbc9912020f69a0c491dabf55"
checksum = "cdfa3e29a22c047da57fadd960ff674b720de15a1e2fb35b5ed67f3408afb469"
dependencies = [
"anyhow",
"bincode",
@@ -3538,9 +3537,9 @@ dependencies = [
[[package]]
name = "rustls-webpki"
version = "0.100.2"
version = "0.100.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e98ff011474fa39949b7e5c0428f9b4937eda7da7848bbb947786b7be0b27dab"
checksum = "d6207cd5ed3d8dca7816f8f3725513a34609c0c765bf652b8c3cb4cfd87db46b"
dependencies = [
"ring",
"untrusted",
@@ -4248,7 +4247,7 @@ dependencies = [
"log",
"once_cell",
"rustls 0.21.6",
"rustls-webpki 0.100.2",
"rustls-webpki 0.100.1",
"url",
"webpki-roots 0.23.1",
]
@@ -4443,9 +4442,9 @@ dependencies = [
[[package]]
name = "webpki"
version = "0.22.1"
version = "0.22.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f0e74f82d49d545ad128049b7e88f6576df2da6b02e9ce565c6f533be576957e"
checksum = "f095d78192e208183081cc07bc5515ef55216397af48b873e5edcd72637fa1bd"
dependencies = [
"ring",
"untrusted",
@@ -4466,7 +4465,7 @@ version = "0.23.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b03058f88386e5ff5310d9111d53f48b17d732b401aeb83a8d5190f2ac459338"
dependencies = [
"rustls-webpki 0.100.2",
"rustls-webpki 0.100.1",
]
[[package]]

View File

@@ -539,7 +539,9 @@ impl IndexScheduler {
let index_tasks = self.index_tasks(rtxn, index_name)? & enqueued;
// If autobatching is disabled we only take one task at a time.
let tasks_limit = if self.autobatching_enabled { usize::MAX } else { 1 };
// Otherwise, we take only a maximum of tasks to create batches.
let tasks_limit =
if self.autobatching_enabled { self.maximum_number_of_batched_tasks } else { 1 };
let enqueued = index_tasks
.into_iter()

View File

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

View File

@@ -253,6 +253,9 @@ pub struct IndexSchedulerOptions {
/// Set to `true` iff the index scheduler is allowed to automatically
/// batch tasks together, to process multiple tasks at once.
pub autobatching_enabled: bool,
/// If the autobatcher is allowed to automatically batch tasks
/// it will only batch this defined number of tasks at once.
pub maximum_number_of_batched_tasks: usize,
/// The maximum number of tasks stored in the task queue before starting
/// to auto schedule task deletions.
pub max_number_of_tasks: usize,
@@ -310,6 +313,9 @@ pub struct IndexScheduler {
/// Whether auto-batching is enabled or not.
pub(crate) autobatching_enabled: bool,
/// The maximum number of tasks that will be batched together.
pub(crate) maximum_number_of_batched_tasks: usize,
/// The max number of tasks allowed before the scheduler starts to delete
/// the finished tasks automatically.
pub(crate) max_number_of_tasks: usize,
@@ -363,6 +369,7 @@ impl IndexScheduler {
index_mapper: self.index_mapper.clone(),
wake_up: self.wake_up.clone(),
autobatching_enabled: self.autobatching_enabled,
maximum_number_of_batched_tasks: self.maximum_number_of_batched_tasks,
max_number_of_tasks: self.max_number_of_tasks,
snapshots_path: self.snapshots_path.clone(),
dumps_path: self.dumps_path.clone(),
@@ -458,6 +465,7 @@ impl IndexScheduler {
// we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
wake_up: Arc::new(SignalEvent::auto(true)),
autobatching_enabled: options.autobatching_enabled,
maximum_number_of_batched_tasks: options.maximum_number_of_batched_tasks,
max_number_of_tasks: options.max_number_of_tasks,
dumps_path: options.dumps_path,
snapshots_path: options.snapshots_path,
@@ -1589,6 +1597,7 @@ mod tests {
index_count: 5,
indexer_config,
autobatching_enabled: true,
maximum_number_of_batched_tasks: usize::MAX,
max_number_of_tasks: 1_000_000,
instance_features: Default::default(),
};

View File

@@ -129,9 +129,6 @@ impl HeedAuthStore {
Action::DumpsAll => {
actions.insert(Action::DumpsCreate);
}
Action::SnapshotsAll => {
actions.insert(Action::SnapshotsCreate);
}
Action::TasksAll => {
actions.extend([Action::TasksGet, Action::TasksDelete, Action::TasksCancel]);
}

View File

@@ -257,12 +257,6 @@ pub enum Action {
#[serde(rename = "dumps.create")]
#[deserr(rename = "dumps.create")]
DumpsCreate,
#[serde(rename = "snapshots.*")]
#[deserr(rename = "snapshots.*")]
SnapshotsAll,
#[serde(rename = "snapshots.create")]
#[deserr(rename = "snapshots.create")]
SnapshotsCreate,
#[serde(rename = "version")]
#[deserr(rename = "version")]
Version,
@@ -315,7 +309,6 @@ impl Action {
METRICS_GET => Some(Self::MetricsGet),
DUMPS_ALL => Some(Self::DumpsAll),
DUMPS_CREATE => Some(Self::DumpsCreate),
SNAPSHOTS_CREATE => Some(Self::SnapshotsCreate),
VERSION => Some(Self::Version),
KEYS_CREATE => Some(Self::KeysAdd),
KEYS_GET => Some(Self::KeysGet),
@@ -360,7 +353,6 @@ pub mod actions {
pub const METRICS_GET: u8 = MetricsGet.repr();
pub const DUMPS_ALL: u8 = DumpsAll.repr();
pub const DUMPS_CREATE: u8 = DumpsCreate.repr();
pub const SNAPSHOTS_CREATE: u8 = SnapshotsCreate.repr();
pub const VERSION: u8 = Version.repr();
pub const KEYS_CREATE: u8 = KeysAdd.repr();
pub const KEYS_GET: u8 = KeysGet.repr();

View File

@@ -133,7 +133,7 @@ vergen = { version = "7.5.1", default-features = false, features = ["git"] }
zip = { version = "0.6.4", optional = true }
[features]
default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard", "profile-with-puffin"]
analytics = ["segment"]
profile-with-puffin = ["dep:puffin_http"]
mini-dashboard = [

View File

@@ -1,5 +1,6 @@
mod mock_analytics;
#[cfg(feature = "analytics")]
// if we are in release mode and the feature analytics was enabled
#[cfg(all(not(debug_assertions), feature = "analytics"))]
mod segment_analytics;
use std::fs;
@@ -16,25 +17,26 @@ use serde_json::Value;
use crate::routes::indexes::documents::UpdateDocumentsQuery;
use crate::routes::tasks::TasksFilterQuery;
// if the analytics feature is disabled
// if we are in debug mode OR the analytics feature is disabled
// the `SegmentAnalytics` point to the mock instead of the real analytics
#[cfg(not(feature = "analytics"))]
#[cfg(any(debug_assertions, not(feature = "analytics")))]
pub type SegmentAnalytics = mock_analytics::MockAnalytics;
#[cfg(not(feature = "analytics"))]
#[cfg(any(debug_assertions, not(feature = "analytics")))]
pub type SearchAggregator = mock_analytics::SearchAggregator;
#[cfg(not(feature = "analytics"))]
#[cfg(any(debug_assertions, not(feature = "analytics")))]
pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
#[cfg(not(feature = "analytics"))]
#[cfg(any(debug_assertions, not(feature = "analytics")))]
pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
// if the feature analytics is enabled we use the real analytics
#[cfg(feature = "analytics")]
// if we are in release mode and the feature analytics was enabled
// we use the real analytics
#[cfg(all(not(debug_assertions), feature = "analytics"))]
pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
pub type SearchAggregator = segment_analytics::SearchAggregator;
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
/// The Meilisearch config dir:

File diff suppressed because it is too large Load Diff

View File

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

View File

@@ -28,7 +28,7 @@ const MEILI_DB_PATH: &str = "MEILI_DB_PATH";
const MEILI_HTTP_ADDR: &str = "MEILI_HTTP_ADDR";
const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
const MEILI_ENV: &str = "MEILI_ENV";
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
const MEILI_SSL_CERT_PATH: &str = "MEILI_SSL_CERT_PATH";
@@ -51,6 +51,7 @@ const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
"MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
const MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS: &str = "MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS";
const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
const DEFAULT_DB_PATH: &str = "./data.ms";
@@ -159,7 +160,7 @@ pub struct Opt {
/// Meilisearch automatically collects data from all instances that do not opt out using this flag.
/// All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted
/// at any time.
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
#[serde(default)] // we can't send true
#[clap(long, env = MEILI_NO_ANALYTICS)]
pub no_analytics: bool,
@@ -301,6 +302,11 @@ pub struct Opt {
#[serde(default)]
pub experimental_reduce_indexing_memory_usage: bool,
/// Experimental limit to the number of tasks per batch
#[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS, default_value_t = default_limit_batched_tasks())]
#[serde(default = "default_limit_batched_tasks")]
pub experimental_limit_batched_tasks: usize,
#[serde(flatten)]
#[clap(flatten)]
pub indexer_options: IndexerOpts,
@@ -390,10 +396,11 @@ impl Opt {
ignore_missing_dump: _,
ignore_dump_if_db_exists: _,
config_file_path: _,
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
no_analytics,
experimental_enable_metrics: enable_metrics_route,
experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
experimental_reduce_indexing_memory_usage,
experimental_limit_batched_tasks,
} = self;
export_to_env_if_not_present(MEILI_DB_PATH, db_path);
export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -401,7 +408,7 @@ impl Opt {
export_to_env_if_not_present(MEILI_MASTER_KEY, master_key);
}
export_to_env_if_not_present(MEILI_ENV, env);
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
{
export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
}
@@ -437,7 +444,11 @@ impl Opt {
);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
reduce_indexing_memory_usage.to_string(),
experimental_reduce_indexing_memory_usage.to_string(),
);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS,
experimental_limit_batched_tasks.to_string(),
);
indexer_options.export_to_env();
}
@@ -739,6 +750,10 @@ fn default_dump_dir() -> PathBuf {
PathBuf::from(DEFAULT_DUMP_DIR)
}
fn default_limit_batched_tasks() -> usize {
usize::MAX
}
/// Indicates if a snapshot was scheduled, and if yes with which interval.
#[derive(Debug, Default, Copy, Clone, Deserialize, Serialize)]
pub enum ScheduleSnapshot {

View File

@@ -24,7 +24,6 @@ pub mod features;
pub mod indexes;
mod metrics;
mod multi_search;
mod snapshot;
mod swap_indexes;
pub mod tasks;
@@ -33,7 +32,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
.service(web::resource("/health").route(web::get().to(get_health)))
.service(web::scope("/keys").configure(api_key::configure))
.service(web::scope("/dumps").configure(dump::configure))
.service(web::scope("/snapshots").configure(snapshot::configure))
.service(web::resource("/stats").route(web::get().to(get_stats)))
.service(web::resource("/version").route(web::get().to(get_version)))
.service(web::scope("/indexes").configure(indexes::configure))

View File

@@ -1,32 +0,0 @@
use actix_web::web::Data;
use actix_web::{web, HttpRequest, HttpResponse};
use index_scheduler::IndexScheduler;
use log::debug;
use meilisearch_types::error::ResponseError;
use meilisearch_types::tasks::KindWithContent;
use serde_json::json;
use crate::analytics::Analytics;
use crate::extractors::authentication::policies::*;
use crate::extractors::authentication::GuardedData;
use crate::extractors::sequential_extractor::SeqHandler;
use crate::routes::SummarizedTaskView;
pub fn configure(cfg: &mut web::ServiceConfig) {
cfg.service(web::resource("").route(web::post().to(SeqHandler(create_snapshot))));
}
pub async fn create_snapshot(
index_scheduler: GuardedData<ActionPolicy<{ actions::SNAPSHOTS_CREATE }>, Data<IndexScheduler>>,
req: HttpRequest,
analytics: web::Data<dyn Analytics>,
) -> Result<HttpResponse, ResponseError> {
analytics.publish("Snapshot Created".to_string(), json!({}), Some(&req));
let task = KindWithContent::SnapshotCreation;
let task: SummarizedTaskView =
tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
debug!("returns: {:?}", task);
Ok(HttpResponse::Accepted().json(task))
}

View File

@@ -1,7 +1,8 @@
use std::{thread, time};
use crate::common::{Server, Value};
use crate::json;
use serde_json::{json, Value};
use crate::common::Server;
#[actix_rt::test]
async fn add_valid_api_key() {
@@ -161,7 +162,7 @@ async fn add_valid_api_key_null_description() {
server.use_api_key("MASTER_KEY");
let content = json!({
"description": json!(null),
"description": Value::Null,
"indexes": ["products"],
"actions": ["documents.add"],
"expiresAt": "2050-11-13T00:00:00"
@@ -364,7 +365,7 @@ async fn error_add_api_key_invalid_index_uids() {
server.use_api_key("MASTER_KEY");
let content = json!({
"description": json!(null),
"description": Value::Null,
"indexes": ["invalid index # / \\name with spaces"],
"actions": [
"documents.add"
@@ -421,7 +422,7 @@ async fn error_add_api_key_invalid_parameters_actions() {
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]" }), @r###"
{
"message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
"message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
"code": "invalid_api_key_actions",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"
@@ -506,7 +507,7 @@ async fn error_add_api_key_invalid_parameters_uid() {
async fn error_add_api_key_parameters_uid_already_exist() {
let mut server = Server::new_auth().await;
server.use_api_key("MASTER_KEY");
let content: Value = json!({
let content = json!({
"uid": "4bc0887a-0e41-4f3b-935d-0c451dcee9c8",
"indexes": ["products"],
"actions": ["search"],
@@ -1145,7 +1146,7 @@ async fn patch_api_key_description() {
meili_snap::snapshot!(code, @"200 OK");
// Remove the description
let content = json!({ "description": null });
let content = json!({ "description": serde_json::Value::Null });
let (response, code) = server.patch_api_key(&uid, content).await;
meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]", ".uid" => "[ignored]", ".key" => "[ignored]" }), @r###"

View File

@@ -3,10 +3,10 @@ use std::collections::{HashMap, HashSet};
use ::time::format_description::well_known::Rfc3339;
use maplit::{hashmap, hashset};
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use time::{Duration, OffsetDateTime};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'static str>>> =
Lazy::new(|| {
@@ -54,7 +54,6 @@ pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'
("GET", "/indexes/products/stats") => hashset!{"stats.get", "stats.*", "*"},
("GET", "/stats") => hashset!{"stats.get", "stats.*", "*"},
("POST", "/dumps") => hashset!{"dumps.create", "dumps.*", "*"},
("POST", "/snapshots") => hashset!{"snapshots.create", "snapshots.*", "*"},
("GET", "/version") => hashset!{"version", "*"},
("GET", "/metrics") => hashset!{"metrics.get", "metrics.*", "*"},
("PATCH", "/keys/mykey/") => hashset!{"keys.update", "*"},

View File

@@ -1,8 +1,8 @@
use meili_snap::*;
use serde_json::json;
use uuid::Uuid;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn create_api_key_bad_description() {
@@ -90,7 +90,7 @@ async fn create_api_key_bad_actions() {
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
"message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
"code": "invalid_api_key_actions",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"

View File

@@ -7,9 +7,9 @@ mod tenant_token;
mod tenant_token_multi_search;
use actix_web::http::StatusCode;
use serde_json::{json, Value};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
impl Server {
pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {

View File

@@ -3,11 +3,11 @@ use std::collections::HashMap;
use ::time::format_description::well_known::Rfc3339;
use maplit::hashmap;
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use time::{Duration, OffsetDateTime};
use super::authorization::{ALL_ACTIONS, AUTHORIZATIONS};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
fn generate_tenant_token(
parent_uid: impl AsRef<str>,
@@ -233,31 +233,31 @@ async fn search_authorized_simple_token() {
},
hashmap! {
"searchRules" => json!({"*": {}}),
"exp" => json!(null)
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"*": null}),
"exp" => json!(null)
"searchRules" => json!({"*": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["*"]),
"exp" => json!(null)
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": {}}),
"exp" => json!(null)
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": null}),
"exp" => json!(null)
"searchRules" => json!({"sales": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sales"]),
"exp" => json!(null)
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sa*"]),
"exp" => json!(null)
"exp" => Value::Null
},
];
@@ -386,7 +386,7 @@ async fn error_search_token_forbidden_parent_key() {
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"*": null}),
"searchRules" => json!({"*": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -398,7 +398,7 @@ async fn error_search_token_forbidden_parent_key() {
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"sales": null}),
"searchRules" => json!({"sales": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -428,15 +428,15 @@ async fn error_search_forbidden_token() {
},
hashmap! {
"searchRules" => json!({"products": {}}),
"exp" => json!(null)
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"products": null}),
"exp" => json!(null)
"searchRules" => json!({"products": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["products"]),
"exp" => json!(null)
"exp" => Value::Null
},
// expired token
hashmap! {
@@ -444,7 +444,7 @@ async fn error_search_forbidden_token() {
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"*": null}),
"searchRules" => json!({"*": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -456,7 +456,7 @@ async fn error_search_forbidden_token() {
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"sales": null}),
"searchRules" => json!({"sales": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {

View File

@@ -3,11 +3,11 @@ use std::collections::HashMap;
use ::time::format_description::well_known::Rfc3339;
use maplit::hashmap;
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use time::{Duration, OffsetDateTime};
use super::authorization::ALL_ACTIONS;
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
fn generate_tenant_token(
parent_uid: impl AsRef<str>,
@@ -512,31 +512,31 @@ async fn single_search_authorized_simple_token() {
},
hashmap! {
"searchRules" => json!({"*": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"*": null}),
"exp" => json!(null),
"searchRules" => json!({"*": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["*"]),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": null}),
"exp" => json!(null),
"searchRules" => json!({"sales": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sales"]),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sa*"]),
"exp" => json!(null),
"exp" => Value::Null
},
];
@@ -564,31 +564,31 @@ async fn multi_search_authorized_simple_token() {
},
hashmap! {
"searchRules" => json!({"*": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"*": null}),
"exp" => json!(null),
"searchRules" => json!({"*": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["*"]),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": {}, "products": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": null, "products": null}),
"exp" => json!(null),
"searchRules" => json!({"sales": Value::Null, "products": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sales", "products"]),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sa*", "pro*"]),
"exp" => json!(null),
"exp" => Value::Null
},
];
@@ -823,7 +823,7 @@ async fn error_single_search_token_forbidden_parent_key() {
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"*": null}),
"searchRules" => json!({"*": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -835,7 +835,7 @@ async fn error_single_search_token_forbidden_parent_key() {
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"sales": null}),
"searchRules" => json!({"sales": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -864,7 +864,7 @@ async fn error_multi_search_token_forbidden_parent_key() {
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"*": null}),
"searchRules" => json!({"*": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -876,7 +876,7 @@ async fn error_multi_search_token_forbidden_parent_key() {
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"sales": null, "products": null}),
"searchRules" => json!({"sales": Value::Null, "products": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -919,15 +919,15 @@ async fn error_single_search_forbidden_token() {
},
hashmap! {
"searchRules" => json!({"products": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"products": null}),
"exp" => json!(null),
"searchRules" => json!({"products": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["products"]),
"exp" => json!(null),
"exp" => Value::Null
},
// expired token
hashmap! {
@@ -935,7 +935,7 @@ async fn error_single_search_forbidden_token() {
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"*": null}),
"searchRules" => json!({"*": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -947,7 +947,7 @@ async fn error_single_search_forbidden_token() {
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"sales": null}),
"searchRules" => json!({"sales": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -978,15 +978,15 @@ async fn error_multi_search_forbidden_token() {
},
hashmap! {
"searchRules" => json!({"products": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"products": null}),
"exp" => json!(null),
"searchRules" => json!({"products": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["products"]),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": {}}),
@@ -998,15 +998,15 @@ async fn error_multi_search_forbidden_token() {
},
hashmap! {
"searchRules" => json!({"sales": {}}),
"exp" => json!(null),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!({"sales": null}),
"exp" => json!(null),
"searchRules" => json!({"sales": Value::Null}),
"exp" => Value::Null
},
hashmap! {
"searchRules" => json!(["sales"]),
"exp" => json!(null),
"exp" => Value::Null
},
// expired token
hashmap! {
@@ -1014,7 +1014,7 @@ async fn error_multi_search_forbidden_token() {
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"*": null}),
"searchRules" => json!({"*": Value::Null}),
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
@@ -1026,7 +1026,7 @@ async fn error_multi_search_forbidden_token() {
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {
"searchRules" => json!({"sales": null, "products": {}}),
"searchRules" => json!({"sales": Value::Null, "products": {}}),
"exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
},
hashmap! {

View File

@@ -3,13 +3,12 @@ use std::panic::{catch_unwind, resume_unwind, UnwindSafe};
use std::time::Duration;
use actix_web::http::StatusCode;
use serde_json::{json, Value};
use tokio::time::sleep;
use urlencoding::encode as urlencode;
use super::encoder::Encoder;
use super::service::Service;
use super::Value;
use crate::json;
pub struct Index<'a> {
pub uid: String,
@@ -243,9 +242,7 @@ impl Index<'_> {
pub async fn delete_batch(&self, ids: Vec<u64>) -> (Value, StatusCode) {
let url = format!("/indexes/{}/documents/delete-batch", urlencode(self.uid.as_ref()));
self.service
.post_encoded(url, serde_json::to_value(&ids).unwrap().into(), self.encoder)
.await
self.service.post_encoded(url, serde_json::to_value(&ids).unwrap(), self.encoder).await
}
pub async fn delete_batch_raw(&self, body: Value) -> (Value, StatusCode) {

View File

@@ -3,83 +3,9 @@ pub mod index;
pub mod server;
pub mod service;
use std::fmt::{self, Display};
pub use index::{GetAllDocumentsOptions, GetDocumentOptions};
use meili_snap::json_string;
use serde::{Deserialize, Serialize};
pub use server::{default_settings, Server};
#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
pub struct Value(pub serde_json::Value);
impl Value {
pub fn uid(&self) -> u64 {
if let Some(uid) = self["uid"].as_u64() {
uid
} else if let Some(uid) = self["taskUid"].as_u64() {
uid
} else {
panic!("Didn't find any task id in: {self}");
}
}
}
impl From<serde_json::Value> for Value {
fn from(value: serde_json::Value) -> Self {
Value(value)
}
}
impl std::ops::Deref for Value {
type Target = serde_json::Value;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl PartialEq<serde_json::Value> for Value {
fn eq(&self, other: &serde_json::Value) -> bool {
&self.0 == other
}
}
impl PartialEq<Value> for serde_json::Value {
fn eq(&self, other: &Value) -> bool {
self == &other.0
}
}
impl PartialEq<&str> for Value {
fn eq(&self, other: &&str) -> bool {
self.0.eq(other)
}
}
impl Display for Value {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(
f,
"{}",
json_string!(self, { ".enqueuedAt" => "[date]", ".processedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]" })
)
}
}
impl From<Vec<Value>> for Value {
fn from(value: Vec<Value>) -> Self {
Self(value.into_iter().map(|value| value.0).collect::<serde_json::Value>())
}
}
#[macro_export]
macro_rules! json {
($($json:tt)+) => {
$crate::common::Value(serde_json::json!($($json)+))
};
}
/// Performs a search test on both post and get routes
#[macro_export]
macro_rules! test_post_get_search {

View File

@@ -11,14 +11,13 @@ use clap::Parser;
use meilisearch::option::{IndexerOpts, MaxMemory, Opt};
use meilisearch::{analytics, create_app, setup_meilisearch};
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use tempfile::TempDir;
use tokio::time::sleep;
use super::index::Index;
use super::service::Service;
use crate::common::encoder::Encoder;
use crate::common::Value;
use crate::json;
pub struct Server {
pub service: Service,
@@ -157,10 +156,6 @@ impl Server {
self.service.post("/dumps", json!(null)).await
}
pub async fn create_snapshot(&self) -> (Value, StatusCode) {
self.service.post("/snapshots", json!(null)).await
}
pub async fn index_swap(&self, value: Value) -> (Value, StatusCode) {
self.service.post("/swap-indexes", value).await
}
@@ -209,7 +204,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
db_path: dir.as_ref().join("db"),
dump_dir: dir.as_ref().join("dumps"),
env: "development".to_owned(),
#[cfg(feature = "analytics")]
#[cfg(all(not(debug_assertions), feature = "analytics"))]
no_analytics: true,
max_index_size: Byte::from_unit(100.0, ByteUnit::MiB).unwrap(),
max_task_db_size: Byte::from_unit(1.0, ByteUnit::GiB).unwrap(),

View File

@@ -7,9 +7,9 @@ use actix_web::test::TestRequest;
use index_scheduler::IndexScheduler;
use meilisearch::{analytics, create_app, Opt};
use meilisearch_auth::AuthController;
use serde_json::Value;
use crate::common::encoder::Encoder;
use crate::common::Value;
pub struct Service {
pub index_scheduler: Arc<IndexScheduler>,

View File

@@ -3,8 +3,9 @@
mod common;
use actix_web::test;
use serde_json::{json, Value};
use crate::common::{Server, Value};
use crate::common::Server;
enum HttpVerb {
Put,

View File

@@ -1,11 +1,11 @@
use actix_web::test;
use meili_snap::{json_string, snapshot};
use serde_json::{json, Value};
use time::format_description::well_known::Rfc3339;
use time::OffsetDateTime;
use crate::common::encoder::Encoder;
use crate::common::{GetAllDocumentsOptions, Server, Value};
use crate::json;
use crate::common::{GetAllDocumentsOptions, Server};
/// This is the basic usage of our API and every other tests uses the content-type application/json
#[actix_rt::test]

View File

@@ -1,7 +1,7 @@
use meili_snap::{json_string, snapshot};
use serde_json::json;
use crate::common::{GetAllDocumentsOptions, Server};
use crate::json;
#[actix_rt::test]
async fn delete_one_document_unexisting_index() {

View File

@@ -1,8 +1,8 @@
use meili_snap::*;
use serde_json::json;
use urlencoding::encode;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn get_all_documents_bad_offset() {

View File

@@ -1,11 +1,11 @@
use actix_web::test;
use http::header::ACCEPT_ENCODING;
use meili_snap::*;
use serde_json::{json, Value};
use urlencoding::encode as urlencode;
use crate::common::encoder::Encoder;
use crate::common::{GetAllDocumentsOptions, GetDocumentOptions, Server, Value};
use crate::json;
use crate::common::{GetAllDocumentsOptions, GetDocumentOptions, Server};
// TODO: partial test since we are testing error, amd error is not yet fully implemented in
// transplant
@@ -40,7 +40,7 @@ async fn get_document() {
let server = Server::new().await;
let index = server.index("test");
index.create(None).await;
let documents = json!([
let documents = serde_json::json!([
{
"id": 0,
"nested": { "content": "foobar" },
@@ -53,7 +53,7 @@ async fn get_document() {
assert_eq!(code, 200);
assert_eq!(
response,
json!({
serde_json::json!({
"id": 0,
"nested": { "content": "foobar" },
})
@@ -64,7 +64,7 @@ async fn get_document() {
assert_eq!(code, 200);
assert_eq!(
response,
json!({
serde_json::json!({
"id": 0,
})
);
@@ -75,7 +75,7 @@ async fn get_document() {
assert_eq!(code, 200);
assert_eq!(
response,
json!({
serde_json::json!({
"nested": { "content": "foobar" },
})
);
@@ -122,7 +122,7 @@ async fn get_all_documents_no_options() {
assert_eq!(code, 200);
let arr = response["results"].as_array().unwrap();
assert_eq!(arr.len(), 20);
let first = json!({
let first = serde_json::json!({
"id":0,
"isActive":false,
"balance":"$2,668.55",

View File

@@ -1,8 +1,7 @@
use meili_snap::snapshot;
use serde_json::json;
use crate::common::encoder::Encoder;
use crate::common::{GetAllDocumentsOptions, Server};
use crate::json;
#[actix_rt::test]
async fn error_document_update_create_index_bad_uid() {
@@ -85,13 +84,7 @@ async fn update_document() {
let (response, code) = index.get_document(1, None).await;
assert_eq!(code, 200);
snapshot!(response, @r###"
{
"doc_id": 1,
"content": "foo",
"other": "bar"
}
"###);
assert_eq!(response.to_string(), r##"{"doc_id":1,"content":"foo","other":"bar"}"##);
}
#[actix_rt::test]
@@ -129,13 +122,7 @@ async fn update_document_gzip_encoded() {
let (response, code) = index.get_document(1, None).await;
assert_eq!(code, 200);
snapshot!(response, @r###"
{
"doc_id": 1,
"content": "foo",
"other": "bar"
}
"###);
assert_eq!(response.to_string(), r##"{"doc_id":1,"content":"foo","other":"bar"}"##);
}
#[actix_rt::test]

View File

@@ -2,10 +2,10 @@ mod data;
use meili_snap::{json_string, snapshot};
use meilisearch::Opt;
use serde_json::json;
use self::data::GetDump;
use crate::common::{default_settings, GetAllDocumentsOptions, Server};
use crate::json;
// all the following test are ignored on windows. See #2364
#[actix_rt::test]

View File

@@ -1,5 +1,6 @@
use serde_json::json;
use crate::common::Server;
use crate::json;
/// Feature name to test against.
/// This will have to be changed by a different one when that feature is stabilized.

View File

@@ -2,10 +2,10 @@ use actix_web::http::header::ContentType;
use actix_web::test;
use http::header::ACCEPT_ENCODING;
use meili_snap::{json_string, snapshot};
use serde_json::{json, Value};
use crate::common::encoder::Encoder;
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
#[actix_rt::test]
async fn create_index_no_primary_key() {
@@ -21,7 +21,7 @@ async fn create_index_no_primary_key() {
assert_eq!(response["status"], "succeeded");
assert_eq!(response["type"], "indexCreation");
assert_eq!(response["details"]["primaryKey"], json!(null));
assert_eq!(response["details"]["primaryKey"], Value::Null);
}
#[actix_rt::test]
@@ -38,7 +38,7 @@ async fn create_index_with_gzip_encoded_request() {
assert_eq!(response["status"], "succeeded");
assert_eq!(response["type"], "indexCreation");
assert_eq!(response["details"]["primaryKey"], json!(null));
assert_eq!(response["details"]["primaryKey"], Value::Null);
}
#[actix_rt::test]
@@ -86,7 +86,7 @@ async fn create_index_with_zlib_encoded_request() {
assert_eq!(response["status"], "succeeded");
assert_eq!(response["type"], "indexCreation");
assert_eq!(response["details"]["primaryKey"], json!(null));
assert_eq!(response["details"]["primaryKey"], Value::Null);
}
#[actix_rt::test]
@@ -103,7 +103,7 @@ async fn create_index_with_brotli_encoded_request() {
assert_eq!(response["status"], "succeeded");
assert_eq!(response["type"], "indexCreation");
assert_eq!(response["details"]["primaryKey"], json!(null));
assert_eq!(response["details"]["primaryKey"], Value::Null);
}
#[actix_rt::test]
@@ -136,7 +136,7 @@ async fn create_index_with_invalid_primary_key() {
let (response, code) = index.get().await;
assert_eq!(code, 200);
assert_eq!(response["primaryKey"], json!(null));
assert_eq!(response["primaryKey"], Value::Null);
}
#[actix_rt::test]

View File

@@ -1,5 +1,6 @@
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn create_and_delete_index() {

View File

@@ -1,7 +1,7 @@
use meili_snap::*;
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn get_indexes_bad_offset() {

View File

@@ -1,5 +1,6 @@
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn stats() {

View File

@@ -1,9 +1,9 @@
use serde_json::json;
use time::format_description::well_known::Rfc3339;
use time::OffsetDateTime;
use crate::common::encoder::Encoder;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn update_primary_key() {

View File

@@ -1,8 +1,8 @@
use meili_snap::*;
use serde_json::json;
use super::DOCUMENTS;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn search_unexisting_index() {

View File

@@ -1,8 +1,8 @@
use meili_snap::snapshot;
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([

View File

@@ -1,8 +1,8 @@
use insta::{allow_duplicates, assert_json_snapshot};
use serde_json::json;
use super::*;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn formatted_contain_wildcard() {

View File

@@ -1,8 +1,8 @@
use meili_snap::{json_string, snapshot};
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([

View File

@@ -10,9 +10,9 @@ mod pagination;
mod restrict_searchable;
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([

View File

@@ -1,8 +1,8 @@
use meili_snap::{json_string, snapshot};
use serde_json::json;
use super::{DOCUMENTS, NESTED_DOCUMENTS};
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn search_empty_list() {

View File

@@ -1,5 +1,6 @@
use serde_json::json;
use crate::common::Server;
use crate::json;
use crate::search::DOCUMENTS;
#[actix_rt::test]

View File

@@ -1,9 +1,9 @@
use meili_snap::{json_string, snapshot};
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use crate::common::index::Index;
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
let index = server.index("test");

View File

@@ -1,5 +1,6 @@
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn set_and_reset_distinct_attribute() {

View File

@@ -1,7 +1,7 @@
use meili_snap::*;
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn settings_bad_displayed_attributes() {

View File

@@ -1,16 +1,16 @@
use std::collections::HashMap;
use once_cell::sync::Lazy;
use serde_json::{json, Value};
use crate::common::{Server, Value};
use crate::json;
use crate::common::Server;
static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|| {
let mut map = HashMap::new();
map.insert("displayed_attributes", json!(["*"]));
map.insert("searchable_attributes", json!(["*"]));
map.insert("filterable_attributes", json!([]));
map.insert("distinct_attribute", json!(null));
map.insert("distinct_attribute", json!(Value::Null));
map.insert(
"ranking_rules",
json!(["words", "typo", "proximity", "attribute", "sort", "exactness"]),
@@ -229,7 +229,7 @@ macro_rules! test_setting_routes {
.chars()
.map(|c| if c == '_' { '-' } else { c })
.collect::<String>());
let (response, code) = server.service.$write_method(url, serde_json::Value::Null.into()).await;
let (response, code) = server.service.$write_method(url, serde_json::Value::Null).await;
assert_eq!(code, 202, "{}", response);
server.index("").wait_task(0).await;
let (response, code) = server.index("test").get().await;

View File

@@ -1,7 +1,7 @@
use meili_snap::{json_string, snapshot};
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn set_and_reset() {

View File

@@ -1,13 +1,11 @@
use std::time::Duration;
use actix_rt::time::sleep;
use meili_snap::{json_string, snapshot};
use meilisearch::option::ScheduleSnapshot;
use meilisearch::Opt;
use crate::common::server::default_settings;
use crate::common::{GetAllDocumentsOptions, Server};
use crate::json;
macro_rules! verify_snapshot {
(
@@ -46,7 +44,7 @@ async fn perform_snapshot() {
let index = server.index("test");
index
.update_settings(json! ({
.update_settings(serde_json::json! ({
"searchableAttributes": [],
}))
.await;
@@ -92,95 +90,3 @@ async fn perform_snapshot() {
server.index("test1").settings(),
);
}
#[actix_rt::test]
async fn perform_on_demand_snapshot() {
let temp = tempfile::tempdir().unwrap();
let snapshot_dir = tempfile::tempdir().unwrap();
let options =
Opt { snapshot_dir: snapshot_dir.path().to_owned(), ..default_settings(temp.path()) };
let server = Server::new_with_options(options).await.unwrap();
let index = server.index("catto");
index
.update_settings(json! ({
"searchableAttributes": [],
}))
.await;
index.load_test_set().await;
server.index("doggo").create(Some("bone")).await;
index.wait_task(2).await;
server.index("doggo").create(Some("bone")).await;
index.wait_task(2).await;
let (task, code) = server.create_snapshot().await;
snapshot!(code, @"202 Accepted");
snapshot!(json_string!(task, { ".enqueuedAt" => "[date]" }), @r###"
{
"taskUid": 4,
"indexUid": null,
"status": "enqueued",
"type": "snapshotCreation",
"enqueuedAt": "[date]"
}
"###);
let task = index.wait_task(task.uid()).await;
snapshot!(json_string!(task, { ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]" }), @r###"
{
"uid": 4,
"indexUid": null,
"status": "succeeded",
"type": "snapshotCreation",
"canceledBy": null,
"error": null,
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
let temp = tempfile::tempdir().unwrap();
let snapshots: Vec<String> = std::fs::read_dir(&snapshot_dir)
.unwrap()
.map(|entry| entry.unwrap().path().file_name().unwrap().to_str().unwrap().to_string())
.collect();
meili_snap::snapshot!(format!("{snapshots:?}"), @r###"["db.snapshot"]"###);
let snapshot_path = snapshot_dir.path().to_owned().join("db.snapshot");
#[cfg_attr(windows, allow(unused))]
let snapshot_meta = std::fs::metadata(&snapshot_path).unwrap();
#[cfg(unix)]
{
use std::os::unix::fs::PermissionsExt;
let mode = snapshot_meta.permissions().mode();
// rwxrwxrwx
meili_snap::snapshot!(format!("{:b}", mode), @"1000000100100100");
}
let options = Opt { import_snapshot: Some(snapshot_path), ..default_settings(temp.path()) };
let snapshot_server = Server::new_with_options(options).await.unwrap();
verify_snapshot!(server, snapshot_server, |server| =>
server.list_indexes(None, None),
// for some reason the db sizes differ. this may be due to the compaction options we have
// set when performing the snapshot
//server.stats(),
// The original instance contains the snapshotCreation task, while the snapshotted-instance does not. For this reason we need to compare the task queue **after** the task 4
server.tasks_filter("?from=2"),
server.index("catto").get_all_documents(GetAllDocumentsOptions::default()),
server.index("catto").settings(),
server.index("doggo").get_all_documents(GetAllDocumentsOptions::default()),
server.index("doggo").settings(),
);
}

View File

@@ -1,8 +1,8 @@
use serde_json::json;
use time::format_description::well_known::Rfc3339;
use time::OffsetDateTime;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn get_settings_unexisting_index() {

View File

@@ -1,7 +1,7 @@
use meili_snap::*;
use serde_json::json;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn swap_indexes_bad_format() {

View File

@@ -1,9 +1,9 @@
mod errors;
use meili_snap::{json_string, snapshot};
use serde_json::json;
use crate::common::{GetAllDocumentsOptions, Server};
use crate::json;
#[actix_rt::test]
async fn swap_indexes() {

View File

@@ -1,11 +1,11 @@
mod errors;
use meili_snap::insta::assert_json_snapshot;
use serde_json::json;
use time::format_description::well_known::Rfc3339;
use time::OffsetDateTime;
use crate::common::Server;
use crate::json;
#[actix_rt::test]
async fn error_get_unexisting_task_status() {
@@ -33,7 +33,7 @@ async fn get_task_status() {
index.create(None).await;
index
.add_documents(
json!([{
serde_json::json!([{
"id": 1,
"content": "foobar",
}]),

View File

@@ -17,7 +17,8 @@ bincode = "1.3.3"
bstr = "1.4.0"
bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
byteorder = "1.4.3"
charabia = { version = "0.8.3", default-features = false }
# charabia = { version = "0.8.3", default-features = false }
charabia = { git = "https://github.com/meilisearch/charabia", branch = "main", default-features = false }
concat-arrays = "0.1.2"
crossbeam-channel = "0.5.8"
deserr = { version = "0.6.0", features = ["actix-web"]}

View File

@@ -12,8 +12,7 @@ use super::Word;
use crate::heed_codec::{BytesDecodeOwned, StrBEU16Codec};
use crate::update::{merge_cbo_roaring_bitmaps, MergeFn};
use crate::{
CboRoaringBitmapCodec, CboRoaringBitmapLenCodec, Result, RoaringBitmapCodec,
RoaringBitmapLenCodec, SearchContext,
CboRoaringBitmapCodec, CboRoaringBitmapLenCodec, Result, RoaringBitmapCodec, SearchContext,
};
/// A cache storing pointers to values in the LMDB databases.
@@ -260,7 +259,6 @@ impl<'ctx> SearchContext<'ctx> {
word2: Interned<String>,
proximity: u8,
) -> Result<Option<RoaringBitmap>> {
unreachable!();
DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
self.txn,
(proximity, word1, word2),
@@ -280,7 +278,6 @@ impl<'ctx> SearchContext<'ctx> {
word2: Interned<String>,
proximity: u8,
) -> Result<Option<u64>> {
unreachable!();
DatabaseCache::get_value::<_, _, CboRoaringBitmapLenCodec>(
self.txn,
(proximity, word1, word2),
@@ -294,23 +291,12 @@ impl<'ctx> SearchContext<'ctx> {
)
}
pub fn get_db_word_docids_len(&mut self, word: Interned<String>) -> Result<Option<u64>> {
DatabaseCache::get_value::<_, _, RoaringBitmapLenCodec>(
self.txn,
word,
self.word_interner.get(word).as_str(),
&mut self.db_cache.word_docids,
self.index.word_docids.remap_data_type::<ByteSlice>(),
)
}
pub fn get_db_word_prefix_pair_proximity_docids(
&mut self,
word1: Interned<String>,
prefix2: Interned<String>,
proximity: u8,
) -> Result<Option<RoaringBitmap>> {
unreachable!();
DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
self.txn,
(proximity, word1, prefix2),
@@ -329,7 +315,6 @@ impl<'ctx> SearchContext<'ctx> {
right: Interned<String>,
proximity: u8,
) -> Result<Option<RoaringBitmap>> {
unreachable!();
DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
self.txn,
(proximity, left_prefix, right),

View File

@@ -295,11 +295,11 @@ fn get_ranking_rules_for_query_graph_search<'ctx>(
ranking_rules.push(Box::new(Typo::new(None)));
}
crate::Criterion::Proximity => {
// if proximity {
continue;
// }
// proximity = true;
// ranking_rules.push(Box::new(Proximity::new(None)));
if proximity {
continue;
}
proximity = true;
ranking_rules.push(Box::new(Proximity::new(None)));
}
crate::Criterion::Attribute => {
if attribute {

View File

@@ -265,11 +265,11 @@ pub fn partially_initialized_term_from_word(
}
fn find_split_words(ctx: &mut SearchContext, word: &str) -> Result<Option<Interned<Phrase>>> {
// if let Some((l, r)) = split_best_frequency(ctx, word)? {
// Ok(Some(ctx.phrase_interner.insert(Phrase { words: vec![Some(l), Some(r)] })))
// } else {
Ok(None)
// }
if let Some((l, r)) = split_best_frequency(ctx, word)? {
Ok(Some(ctx.phrase_interner.insert(Phrase { words: vec![Some(l), Some(r)] })))
} else {
Ok(None)
}
}
impl Interned<QueryTerm> {
@@ -416,20 +416,11 @@ fn split_best_frequency(
let left = ctx.word_interner.insert(left.to_owned());
let right = ctx.word_interner.insert(right.to_owned());
if let (Some(l_freq), Some(r_freq)) =
(ctx.get_db_word_docids_len(left)?, ctx.get_db_word_docids_len(right)?)
{
let frequency = l_freq.min(r_freq);
if let Some(frequency) = ctx.get_db_word_pair_proximity_docids_len(left, right, 1)? {
if best.map_or(true, |(old, _, _)| frequency > old) {
best = Some((frequency, left, right));
}
}
// if let Some(frequency) = ctx.get_db_word_pair_proximity_docids_len(left, right, 1)? {
// if best.map_or(true, |(old, _, _)| frequency > old) {
// best = Some((frequency, left, right));
// }
// }
}
Ok(best.map(|(_, left, right)| (left, right)))

View File

@@ -82,41 +82,41 @@ pub fn located_query_terms_from_tokens(
position = position.wrapping_add(7);
}
// phrase = 'phrase: {
// let phrase = phrase.take();
phrase = 'phrase: {
let phrase = phrase.take();
// // If we have a hard separator inside a phrase, we immediately start a new phrase
// let phrase = if separator_kind == SeparatorKind::Hard {
// if let Some(phrase) = phrase {
// if let Some(located_query_term) = phrase.build(ctx) {
// located_terms.push(located_query_term)
// }
// Some(PhraseBuilder::empty())
// } else {
// None
// }
// } else {
// phrase
// };
// If we have a hard separator inside a phrase, we immediately start a new phrase
let phrase = if separator_kind == SeparatorKind::Hard {
if let Some(phrase) = phrase {
if let Some(located_query_term) = phrase.build(ctx) {
located_terms.push(located_query_term)
}
Some(PhraseBuilder::empty())
} else {
None
}
} else {
phrase
};
// // We close and start a new phrase depending on the number of double quotes
// let mut quote_count = token.lemma().chars().filter(|&s| s == '"').count();
// if quote_count == 0 {
// break 'phrase phrase;
// }
// We close and start a new phrase depending on the number of double quotes
let mut quote_count = token.lemma().chars().filter(|&s| s == '"').count();
if quote_count == 0 {
break 'phrase phrase;
}
// // Consume the closing quote and the phrase
// if let Some(phrase) = phrase {
// // Per the check above, quote_count > 0
// quote_count -= 1;
// if let Some(located_query_term) = phrase.build(ctx) {
// located_terms.push(located_query_term)
// }
// }
// Consume the closing quote and the phrase
if let Some(phrase) = phrase {
// Per the check above, quote_count > 0
quote_count -= 1;
if let Some(located_query_term) = phrase.build(ctx) {
located_terms.push(located_query_term)
}
}
// // Start new phrase if the token ends with an opening quote
// (quote_count % 2 == 1).then_some(PhraseBuilder::empty())
// };
// Start new phrase if the token ends with an opening quote
(quote_count % 2 == 1).then_some(PhraseBuilder::empty())
};
}
_ => (),
}

View File

@@ -152,15 +152,15 @@ pub(crate) fn data_from_obkv_documents(
});
}
// spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
// docid_word_positions_chunks.clone(),
// indexer,
// lmdb_writer_sx.clone(),
// extract_word_pair_proximity_docids,
// merge_cbo_roaring_bitmaps,
// TypedChunk::WordPairProximityDocids,
// "word-pair-proximity-docids",
// );
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_word_positions_chunks.clone(),
indexer,
lmdb_writer_sx.clone(),
extract_word_pair_proximity_docids,
merge_cbo_roaring_bitmaps,
TypedChunk::WordPairProximityDocids,
"word-pair-proximity-docids",
);
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_word_positions_chunks.clone(),