Compare commits

..

1 Commits

Author SHA1 Message Date
ManyTheFish
a8935d88ab Add test tryinmg to reproduce bug 2024-07-25 08:12:27 +02:00
116 changed files with 1456 additions and 9055 deletions

View File

@@ -18,7 +18,7 @@ jobs:
timeout-minutes: 180 # 3h
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -16,37 +16,6 @@ jobs:
runs-on: benchmarks
timeout-minutes: 180 # 3h
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
id: command
uses: xt0rted/slash-command-action@v2
@@ -66,7 +35,7 @@ jobs:
fetch-depth: 0 # fetch full history to be able to get main commit sha
ref: ${{ steps.comment-branch.outputs.head_ref }}
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -12,7 +12,7 @@ jobs:
timeout-minutes: 180 # 3h
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -18,7 +18,7 @@ jobs:
timeout-minutes: 4320 # 72h
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -13,38 +13,7 @@ jobs:
runs-on: benchmarks
timeout-minutes: 4320 # 72h
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
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -16,7 +16,7 @@ jobs:
timeout-minutes: 4320 # 72h
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -15,7 +15,7 @@ jobs:
runs-on: benchmarks
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -15,7 +15,7 @@ jobs:
runs-on: benchmarks
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -15,7 +15,7 @@ jobs:
runs-on: benchmarks
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -17,7 +17,7 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Install cargo-flaky
run: cargo install cargo-flaky
- name: Run cargo flaky in the dumps

View File

@@ -12,7 +12,7 @@ jobs:
timeout-minutes: 4320 # 72h
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal

View File

@@ -25,7 +25,7 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Install cargo-deb
run: cargo install cargo-deb
- uses: actions/checkout@v3

View File

@@ -45,7 +45,7 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Build
run: cargo build --release --locked
# No need to upload binaries for dry run (cron)
@@ -75,7 +75,7 @@ jobs:
asset_name: meilisearch-windows-amd64.exe
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Build
run: cargo build --release --locked
# No need to upload binaries for dry run (cron)
@@ -101,7 +101,7 @@ jobs:
- name: Checkout repository
uses: actions/checkout@v3
- name: Installing Rust toolchain
uses: dtolnay/rust-toolchain@1.79
uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
target: ${{ matrix.target }}
@@ -148,7 +148,7 @@ jobs:
add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
apt-get update -y && apt-get install -y docker-ce
- name: Installing Rust toolchain
uses: dtolnay/rust-toolchain@1.79
uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
target: ${{ matrix.target }}

View File

@@ -31,7 +31,7 @@ jobs:
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- name: Setup test with Rust stable
uses: dtolnay/rust-toolchain@1.79
uses: helix-editor/rust-toolchain@v1
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
- name: Run cargo check without any default features
@@ -56,7 +56,7 @@ jobs:
- uses: actions/checkout@v3
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Run cargo check without any default features
uses: actions-rs/cargo@v1
with:
@@ -81,7 +81,7 @@ jobs:
run: |
apt-get update
apt-get install --assume-yes build-essential curl
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Run cargo build with almost all features
run: |
cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
@@ -101,7 +101,7 @@ jobs:
run: |
apt-get update
apt-get install --assume-yes build-essential curl
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- 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 -qz lindera; then
@@ -125,7 +125,7 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
- name: Run tests in debug
@@ -139,7 +139,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
components: clippy
@@ -156,7 +156,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
toolchain: nightly-2024-07-09

View File

@@ -18,7 +18,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: dtolnay/rust-toolchain@1.79
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
- name: Install sd

151
Cargo.lock generated
View File

@@ -55,7 +55,7 @@ dependencies = [
"encoding_rs",
"flate2",
"futures-core",
"h2 0.3.26",
"h2",
"http 0.2.11",
"httparse",
"httpdate",
@@ -403,16 +403,6 @@ dependencies = [
"thiserror",
]
[[package]]
name = "assert-json-diff"
version = "2.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "47e4f2b81832e72834d7518d8487a0396a28cc408186a2e8854c0f98011faf12"
dependencies = [
"serde",
"serde_json",
]
[[package]]
name = "async-trait"
version = "0.1.81"
@@ -424,12 +414,6 @@ dependencies = [
"syn 2.0.60",
]
[[package]]
name = "atomic-waker"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
[[package]]
name = "autocfg"
version = "1.2.0"
@@ -471,7 +455,7 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
[[package]]
name = "benchmarks"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"anyhow",
"bytes",
@@ -652,7 +636,7 @@ dependencies = [
[[package]]
name = "build-info"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"anyhow",
"time",
@@ -933,17 +917,20 @@ dependencies = [
[[package]]
name = "charabia"
version = "0.9.1"
version = "0.8.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55ff52497324e7d168505a16949ae836c14595606fab94687238d2f6c8d4c798"
checksum = "9868a22f10dee80498a8a2b6c641d80bf28ea4495fcf71c2dc4836c2dd23958c"
dependencies = [
"aho-corasick",
"cow-utils",
"csv",
"deunicode",
"either",
"fst",
"irg-kvariants",
"jieba-rs",
"lindera",
"litemap",
"once_cell",
"pinyin",
"serde",
@@ -951,6 +938,7 @@ dependencies = [
"unicode-normalization",
"wana_kana",
"whatlang",
"zerovec",
]
[[package]]
@@ -1141,6 +1129,12 @@ version = "0.8.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e496a50fda8aacccc86d7529e2c1e0892dbd0f898a6b5645b5561b89c3210efa"
[[package]]
name = "cow-utils"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "79bb3adfaf5f75d24b01aee375f7555907840fa2800e5ec8fa3b9e2031830173"
[[package]]
name = "cpufeatures"
version = "0.2.12"
@@ -1383,24 +1377,6 @@ dependencies = [
"syn 2.0.60",
]
[[package]]
name = "deadpool"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fb84100978c1c7b37f09ed3ce3e5f843af02c2a2c431bae5b19230dad2c1b490"
dependencies = [
"async-trait",
"deadpool-runtime",
"num_cpus",
"tokio",
]
[[package]]
name = "deadpool-runtime"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "092966b41edc516079bdf31ec78a2e0588d1d0c08f78b91d8307215928642b2b"
[[package]]
name = "debugid"
version = "0.8.0"
@@ -1541,6 +1517,12 @@ dependencies = [
"syn 2.0.60",
]
[[package]]
name = "deunicode"
version = "1.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "339544cc9e2c4dc3fc7149fd630c5f22263a4fdf18a98afd0075784968b5cf00"
[[package]]
name = "digest"
version = "0.10.7"
@@ -1622,7 +1604,7 @@ dependencies = [
[[package]]
name = "dump"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"anyhow",
"big_s",
@@ -1834,7 +1816,7 @@ checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
[[package]]
name = "file-store"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"tempfile",
"thiserror",
@@ -1856,7 +1838,7 @@ dependencies = [
[[package]]
name = "filter-parser"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"insta",
"nom",
@@ -1876,7 +1858,7 @@ dependencies = [
[[package]]
name = "flatten-serde-json"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"criterion",
"serde_json",
@@ -2000,7 +1982,7 @@ dependencies = [
[[package]]
name = "fuzzers"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"arbitrary",
"clap",
@@ -2249,25 +2231,6 @@ dependencies = [
"tracing",
]
[[package]]
name = "h2"
version = "0.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa82e28a107a8cc405f0839610bdc9b15f1e25ec7d696aa5cf173edbcb1486ab"
dependencies = [
"atomic-waker",
"bytes",
"fnv",
"futures-core",
"futures-sink",
"http 1.1.0",
"indexmap",
"slab",
"tokio",
"tokio-util",
"tracing",
]
[[package]]
name = "half"
version = "1.8.2"
@@ -2478,11 +2441,9 @@ dependencies = [
"bytes",
"futures-channel",
"futures-util",
"h2 0.4.5",
"http 1.1.0",
"http-body",
"httparse",
"httpdate",
"itoa",
"pin-project-lite",
"smallvec",
@@ -2552,7 +2513,7 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
[[package]]
name = "index-scheduler"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"anyhow",
"arroy",
@@ -2746,7 +2707,7 @@ dependencies = [
[[package]]
name = "json-depth-checker"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"criterion",
"serde_json",
@@ -3262,6 +3223,12 @@ dependencies = [
"unicode-segmentation",
]
[[package]]
name = "litemap"
version = "0.7.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "643cb0b8d4fcc284004d5fd0d67ccf61dfffadb7f75e1e71bc420f4688a3a704"
[[package]]
name = "lmdb-master-sys"
version = "0.2.2"
@@ -3365,7 +3332,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
[[package]]
name = "meili-snap"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"insta",
"md5",
@@ -3374,7 +3341,7 @@ dependencies = [
[[package]]
name = "meilisearch"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"actix-cors",
"actix-http",
@@ -3456,14 +3423,13 @@ dependencies = [
"url",
"urlencoding",
"uuid",
"wiremock",
"yaup",
"zip 2.1.3",
]
[[package]]
name = "meilisearch-auth"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"base64 0.22.1",
"enum-iterator",
@@ -3482,7 +3448,7 @@ dependencies = [
[[package]]
name = "meilisearch-types"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"actix-web",
"anyhow",
@@ -3512,7 +3478,7 @@ dependencies = [
[[package]]
name = "meilitool"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"anyhow",
"clap",
@@ -3542,7 +3508,7 @@ dependencies = [
[[package]]
name = "milli"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"arroy",
"big_s",
@@ -3976,7 +3942,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
[[package]]
name = "permissive-json-pointer"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"big_s",
"serde_json",
@@ -6315,30 +6281,6 @@ dependencies = [
"windows-sys 0.48.0",
]
[[package]]
name = "wiremock"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec874e1eef0df2dcac546057fe5e29186f09c378181cd7b635b4b7bcc98e9d81"
dependencies = [
"assert-json-diff",
"async-trait",
"base64 0.21.7",
"deadpool",
"futures",
"http 1.1.0",
"http-body-util",
"hyper",
"hyper-util",
"log",
"once_cell",
"regex",
"serde",
"serde_json",
"tokio",
"url",
]
[[package]]
name = "wyz"
version = "0.5.1"
@@ -6361,7 +6303,7 @@ dependencies = [
[[package]]
name = "xtask"
version = "1.10.2"
version = "1.10.0"
dependencies = [
"anyhow",
"build-info",
@@ -6484,6 +6426,15 @@ dependencies = [
"syn 2.0.60",
]
[[package]]
name = "zerovec"
version = "0.10.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa2b893d79df23bfb12d5461018d408ea19dfafe76c2c7ef6d4eba614f8ff079"
dependencies = [
"zerofrom",
]
[[package]]
name = "zip"
version = "1.1.4"

View File

@@ -22,7 +22,7 @@ members = [
]
[workspace.package]
version = "1.10.2"
version = "1.10.0"
authors = [
"Quentin de Quelen <quentin@dequelen.me>",
"Clément Renault <clement@meilisearch.com>",

View File

@@ -286,7 +286,6 @@ pub(crate) mod test {
pagination: Setting::NotSet,
embedders: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
localized_attributes: Setting::NotSet,
_kind: std::marker::PhantomData,
};
settings.check()

View File

@@ -379,7 +379,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
v5::Setting::NotSet => v6::Setting::NotSet,
},
embedders: v6::Setting::NotSet,
localized_attributes: v6::Setting::NotSet,
search_cutoff_ms: v6::Setting::NotSet,
_kind: std::marker::PhantomData,
}

View File

@@ -25,9 +25,8 @@ enum AutobatchKind {
primary_key: Option<String>,
},
DocumentEdition,
DocumentDeletion {
by_filter: bool,
},
DocumentDeletion,
DocumentDeletionByFilter,
DocumentClear,
Settings {
allow_index_creation: bool,
@@ -66,12 +65,10 @@ impl From<KindWithContent> for AutobatchKind {
..
} => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key },
KindWithContent::DocumentEdition { .. } => AutobatchKind::DocumentEdition,
KindWithContent::DocumentDeletion { .. } => {
AutobatchKind::DocumentDeletion { by_filter: false }
}
KindWithContent::DocumentDeletion { .. } => AutobatchKind::DocumentDeletion,
KindWithContent::DocumentClear { .. } => AutobatchKind::DocumentClear,
KindWithContent::DocumentDeletionByFilter { .. } => {
AutobatchKind::DocumentDeletion { by_filter: true }
AutobatchKind::DocumentDeletionByFilter
}
KindWithContent::SettingsUpdate { allow_index_creation, is_deletion, .. } => {
AutobatchKind::Settings {
@@ -108,7 +105,9 @@ pub enum BatchKind {
},
DocumentDeletion {
deletion_ids: Vec<TaskId>,
includes_by_filter: bool,
},
DocumentDeletionByFilter {
id: TaskId,
},
ClearAndSettings {
other: Vec<TaskId>,
@@ -206,13 +205,12 @@ impl BatchKind {
allow_index_creation,
),
K::DocumentEdition => (Break(BatchKind::DocumentEdition { id: task_id }), false),
K::DocumentDeletion { by_filter: includes_by_filter } => (
Continue(BatchKind::DocumentDeletion {
deletion_ids: vec![task_id],
includes_by_filter,
}),
false,
),
K::DocumentDeletion => {
(Continue(BatchKind::DocumentDeletion { deletion_ids: vec![task_id] }), false)
}
K::DocumentDeletionByFilter => {
(Break(BatchKind::DocumentDeletionByFilter { id: task_id }), false)
}
K::Settings { allow_index_creation } => (
Continue(BatchKind::Settings { allow_index_creation, settings_ids: vec![task_id] }),
allow_index_creation,
@@ -230,7 +228,7 @@ impl BatchKind {
match (self, kind) {
// 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::DocumentEdition | 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.
(this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
Break(this)
@@ -266,7 +264,7 @@ impl BatchKind {
// The index deletion can batch with everything but must stop after
(
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::Settings { allow_index_creation: _, settings_ids: mut ids },
K::IndexDeletion,
@@ -286,7 +284,7 @@ impl BatchKind {
(
BatchKind::DocumentClear { mut ids },
K::DocumentClear | K::DocumentDeletion { by_filter: _ },
K::DocumentClear | K::DocumentDeletion,
) => {
ids.push(id);
Continue(BatchKind::DocumentClear { ids })
@@ -330,7 +328,7 @@ impl BatchKind {
}
(
BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
K::DocumentDeletion { by_filter: false },
K::DocumentDeletion,
) => {
operation_ids.push(id);
@@ -341,13 +339,6 @@ impl BatchKind {
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
// this match branch MUST be AFTER the previous one
(
@@ -366,18 +357,13 @@ impl BatchKind {
operation_ids,
}),
(BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: _ }, K::DocumentClear) => {
(BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentClear) => {
deletion_ids.push(id);
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
(
BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false },
BatchKind::DocumentDeletion { mut deletion_ids },
K::DocumentImport { method, allow_index_creation, primary_key }
) if index_already_exists => {
deletion_ids.push(id);
@@ -391,7 +377,7 @@ impl BatchKind {
}
// 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 }
) if !allow_index_creation => {
deletion_ids.push(id);
@@ -410,9 +396,9 @@ impl BatchKind {
) => {
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);
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),
@@ -426,7 +412,7 @@ impl BatchKind {
}),
(
this @ BatchKind::Settings { .. },
K::DocumentImport { .. } | K::DocumentDeletion { .. },
K::DocumentImport { .. } | K::DocumentDeletion,
) => Break(this),
(
BatchKind::Settings { mut settings_ids, allow_index_creation },
@@ -457,7 +443,7 @@ impl BatchKind {
settings_ids,
allow_index_creation,
},
K::DocumentDeletion { .. },
K::DocumentDeletion,
) => {
other.push(id);
Continue(BatchKind::ClearAndSettings {
@@ -519,7 +505,7 @@ impl BatchKind {
// this MUST be AFTER the two previous branch
(
this @ BatchKind::SettingsAndDocumentOperation { .. },
K::DocumentDeletion { .. } | K::DocumentImport { .. },
K::DocumentDeletion | K::DocumentImport { .. },
) => Break(this),
(
BatchKind::SettingsAndDocumentOperation { mut settings_ids, method, allow_index_creation,primary_key, operation_ids },
@@ -539,7 +525,8 @@ impl BatchKind {
| BatchKind::IndexDeletion { .. }
| BatchKind::IndexUpdate { .. }
| BatchKind::IndexSwap { .. }
| BatchKind::DocumentEdition { .. },
| BatchKind::DocumentEdition { .. }
| BatchKind::DocumentDeletionByFilter { .. },
_,
) => {
unreachable!()
@@ -629,13 +616,6 @@ 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 {
KindWithContent::DocumentClear { index_uid: String::from("doggo") }
}
@@ -696,16 +676,10 @@ 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))");
// 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(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, 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(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, 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))");
debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
// we can autobatch one or multiple Settings together
debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
@@ -748,63 +722,25 @@ 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(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))"###);
// 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]
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(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(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_fil(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, 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_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
}
#[test]
@@ -871,7 +807,6 @@ 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(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_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(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
@@ -881,7 +816,6 @@ 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(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_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(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
@@ -893,7 +827,6 @@ 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(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_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, [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))");
@@ -903,7 +836,6 @@ 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(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_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, [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))");
@@ -969,10 +901,10 @@ 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))");
// 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(UpdateDocuments, 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, 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], 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] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
}
#[test]

View File

@@ -110,9 +110,9 @@ pub(crate) enum IndexOperation {
index_uid: String,
task: Task,
},
DocumentDeletion {
IndexDocumentDeletionByFilter {
index_uid: String,
tasks: Vec<Task>,
task: Task,
},
DocumentClear {
index_uid: String,
@@ -165,11 +165,11 @@ impl Batch {
Batch::IndexOperation { op, .. } => match op {
IndexOperation::DocumentOperation { tasks, .. }
| IndexOperation::Settings { tasks, .. }
| IndexOperation::DocumentDeletion { tasks, .. }
| IndexOperation::DocumentClear { tasks, .. } => {
RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
}
IndexOperation::DocumentEdition { task, .. } => {
IndexOperation::DocumentEdition { task, .. }
| IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
}
IndexOperation::SettingsAndDocumentOperation {
@@ -234,7 +234,7 @@ impl IndexOperation {
match self {
IndexOperation::DocumentOperation { index_uid, .. }
| IndexOperation::DocumentEdition { index_uid, .. }
| IndexOperation::DocumentDeletion { index_uid, .. }
| IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
| IndexOperation::DocumentClear { index_uid, .. }
| IndexOperation::Settings { index_uid, .. }
| IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -252,8 +252,8 @@ impl fmt::Display for IndexOperation {
IndexOperation::DocumentEdition { .. } => {
f.write_str("IndexOperation::DocumentEdition")
}
IndexOperation::DocumentDeletion { .. } => {
f.write_str("IndexOperation::DocumentDeletion")
IndexOperation::IndexDocumentDeletionByFilter { .. } => {
f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
}
IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"),
IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"),
@@ -289,6 +289,21 @@ impl IndexScheduler {
},
must_create_index,
})),
BatchKind::DocumentDeletionByFilter { id } => {
let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
match &task.kind {
KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
Ok(Some(Batch::IndexOperation {
op: IndexOperation::IndexDocumentDeletionByFilter {
index_uid: index_uid.clone(),
task,
},
must_create_index: false,
}))
}
_ => unreachable!(),
}
}
BatchKind::DocumentEdition { id } => {
let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
match &task.kind {
@@ -351,11 +366,30 @@ impl IndexScheduler {
must_create_index,
}))
}
BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: _ } => {
BatchKind::DocumentDeletion { 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 {
op: IndexOperation::DocumentDeletion { index_uid, tasks },
op: IndexOperation::DocumentOperation {
index_uid,
primary_key: None,
method: IndexDocumentsMethod::ReplaceDocuments,
documents_counts,
operations,
tasks,
},
must_create_index,
}))
}
@@ -1405,7 +1439,7 @@ impl IndexScheduler {
{
(original_filter, context, function)
} else {
// In the case of a `documentEdition` the details MUST be set
// In the case of a `documentDeleteByFilter` the details MUST be set
unreachable!();
};
@@ -1435,102 +1469,52 @@ impl IndexScheduler {
Ok(vec![task])
}
IndexOperation::DocumentDeletion { mut tasks, index_uid: _ } => {
let mut to_delete = RoaringBitmap::new();
let external_documents_ids = index.external_documents_ids();
IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
let filter =
if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
&task.kind
{
filter_expr
} else {
unreachable!()
};
let deleted_documents = delete_document_by_filter(
index_wtxn,
filter,
self.index_mapper.indexer_config(),
self.must_stop_processing.clone(),
index,
);
let original_filter = if let Some(Details::DocumentDeletionByFilter {
original_filter,
deleted_documents: _,
}) = task.details
{
original_filter
} else {
// In the case of a `documentDeleteByFilter` the details MUST be set
unreachable!();
};
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!(),
match deleted_documents {
Ok(deleted_documents) => {
task.status = Status::Succeeded;
task.details = Some(Details::DocumentDeletionByFilter {
original_filter,
deleted_documents: Some(deleted_documents),
});
}
Err(e) => {
task.status = Status::Failed;
task.details = Some(Details::DocumentDeletionByFilter {
original_filter,
deleted_documents: Some(0),
});
task.error = Some(e.into());
}
}
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)
Ok(vec![task])
}
IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
let indexer_config = self.index_mapper.indexer_config();
@@ -1734,6 +1718,46 @@ impl IndexScheduler {
}
}
fn delete_document_by_filter<'a>(
wtxn: &mut RwTxn<'a>,
filter: &serde_json::Value,
indexer_config: &IndexerConfig,
must_stop_processing: MustStopProcessing,
index: &'a Index,
) -> Result<u64> {
let filter = Filter::from_json(filter)?;
Ok(if let Some(filter) = filter {
let candidates = filter.evaluate(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(),
})?;
let config = IndexDocumentsConfig {
update_method: IndexDocumentsMethod::ReplaceDocuments,
..Default::default()
};
let mut builder = milli::update::IndexDocuments::new(
wtxn,
index,
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(&candidates)?;
builder = new_builder;
let _ = builder.execute()?;
count
} else {
0
})
}
fn edit_documents_by_function<'a>(
wtxn: &mut RwTxn<'a>,
filter: &Option<serde_json::Value>,

View File

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

View File

@@ -35,7 +35,6 @@ pub type TaskId = u32;
use std::collections::{BTreeMap, HashMap};
use std::io::{self, BufReader, Read};
use std::ops::{Bound, RangeBounds};
use std::panic::{catch_unwind, AssertUnwindSafe};
use std::path::{Path, PathBuf};
use std::sync::atomic::Ordering::{self, Relaxed};
use std::sync::atomic::{AtomicBool, AtomicU32};
@@ -613,24 +612,19 @@ impl IndexScheduler {
#[cfg(test)]
run.breakpoint(Breakpoint::Init);
run.wake_up.wait_timeout(std::time::Duration::from_secs(60));
run.wake_up.wait();
loop {
let ret = catch_unwind(AssertUnwindSafe(|| run.tick()));
match ret {
Ok(Ok(TickOutcome::TickAgain(_))) => (),
Ok(Ok(TickOutcome::WaitForSignal)) => run.wake_up.wait(),
Ok(Err(e)) => {
match run.tick() {
Ok(TickOutcome::TickAgain(_)) => (),
Ok(TickOutcome::WaitForSignal) => run.wake_up.wait(),
Err(e) => {
tracing::error!("{e}");
// Wait one second when an irrecoverable error occurs.
if !e.is_recoverable() {
std::thread::sleep(Duration::from_secs(1));
}
}
Err(_panic) => {
tracing::error!("Internal error: Unexpected panic in the `IndexScheduler::run` method.");
}
}
}
})
@@ -1764,7 +1758,6 @@ mod tests {
use crossbeam::channel::RecvTimeoutError;
use file_store::File;
use insta::assert_json_snapshot;
use maplit::btreeset;
use meili_snap::{json_string, snapshot};
use meilisearch_auth::AuthFilter;
use meilisearch_types::document_formats::DocumentFormatError;
@@ -2554,117 +2547,6 @@ mod tests {
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]
fn do_not_batch_task_of_different_indexes() {
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
@@ -3165,8 +3047,6 @@ mod tests {
api_key: Setting::Set(S("My super secret")),
url: Setting::Set(S("http://localhost:7777")),
dimensions: Setting::Set(4),
request: Setting::Set(serde_json::json!("{{text}}")),
response: Setting::Set(serde_json::json!("{{embedding}}")),
..Default::default()
};
embedders.insert(S("default"), Setting::Set(embedding_settings));
@@ -5126,8 +5006,6 @@ mod tests {
api_key: Setting::Set(S("My super secret")),
url: Setting::Set(S("http://localhost:7777")),
dimensions: Setting::Set(384),
request: Setting::Set(serde_json::json!("{{text}}")),
response: Setting::Set(serde_json::json!("{{embedding}}")),
..Default::default()
};
embedders.insert(S("A_fakerest"), Setting::Set(embedding_settings));

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

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:
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 }}
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:
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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 }}
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
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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 }}
----------------------------------------------------------------------
### Status:
@@ -42,3 +42,4 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
### File Store:
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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 }}
----------------------------------------------------------------------
### Status:
@@ -41,3 +41,4 @@ doggos: { number_of_documents: 0, field_distribution: {} }
00000000-0000-0000-0000-000000000000
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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:
enqueued [0,]
@@ -33,3 +33,4 @@ doggos [0,]
### File Store:
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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:
enqueued []
@@ -37,3 +37,4 @@ doggos: { number_of_documents: 0, field_distribution: {} }
### File Store:
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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:
enqueued [0,]
@@ -33,3 +33,4 @@ doggos [0,]
### File Store:
----------------------------------------------------------------------

View File

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
[]
----------------------------------------------------------------------
### 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:
enqueued []
@@ -37,3 +37,4 @@ doggos: { number_of_documents: 0, field_distribution: {} }
### File Store:
----------------------------------------------------------------------

View File

@@ -256,7 +256,6 @@ InvalidSearchCropLength , InvalidRequest , BAD_REQUEST ;
InvalidSearchCropMarker , InvalidRequest , BAD_REQUEST ;
InvalidSearchFacets , InvalidRequest , BAD_REQUEST ;
InvalidSearchSemanticRatio , InvalidRequest , BAD_REQUEST ;
InvalidSearchLocales , InvalidRequest , BAD_REQUEST ;
InvalidFacetSearchFacetName , InvalidRequest , BAD_REQUEST ;
InvalidSimilarId , InvalidRequest , BAD_REQUEST ;
InvalidSearchFilter , InvalidRequest , BAD_REQUEST ;
@@ -298,7 +297,6 @@ InvalidSettingsSeparatorTokens , InvalidRequest , BAD_REQUEST ;
InvalidSettingsDictionary , InvalidRequest , BAD_REQUEST ;
InvalidSettingsSynonyms , InvalidRequest , BAD_REQUEST ;
InvalidSettingsTypoTolerance , InvalidRequest , BAD_REQUEST ;
InvalidSettingsLocalizedAttributes , InvalidRequest , BAD_REQUEST ;
InvalidState , Internal , INTERNAL_SERVER_ERROR ;
InvalidStoreFile , Internal , INTERNAL_SERVER_ERROR ;
InvalidSwapDuplicateIndexFound , InvalidRequest , BAD_REQUEST ;

View File

@@ -7,7 +7,6 @@ pub mod features;
pub mod index_uid;
pub mod index_uid_pattern;
pub mod keys;
pub mod locales;
pub mod settings;
pub mod star_or;
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::error::deserr_codes::*;
use crate::facet_values_sort::FacetValuesSort;
use crate::locales::LocalizedAttributesRuleView;
/// The maximum number of results that the engine
/// 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")]
#[deserr(default, error = DeserrJsonError<InvalidSettingsSearchCutoffMs>)]
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)]
#[deserr(skip)]
@@ -265,7 +261,6 @@ impl Settings<Checked> {
pagination: Setting::Reset,
embedders: Setting::Reset,
search_cutoff_ms: Setting::Reset,
localized_attributes: Setting::Reset,
_kind: PhantomData,
}
}
@@ -289,8 +284,7 @@ impl Settings<Checked> {
pagination,
embedders,
search_cutoff_ms,
localized_attributes: localized_attributes_rules,
_kind,
..
} = self;
Settings {
@@ -311,7 +305,6 @@ impl Settings<Checked> {
pagination,
embedders,
search_cutoff_ms,
localized_attributes: localized_attributes_rules,
_kind: PhantomData,
}
}
@@ -359,7 +352,6 @@ impl Settings<Unchecked> {
pagination: self.pagination,
embedders: self.embedders,
search_cutoff_ms: self.search_cutoff_ms,
localized_attributes: self.localized_attributes,
_kind: PhantomData,
}
}
@@ -410,7 +402,6 @@ pub fn apply_settings_to_builder(
pagination,
embedders,
search_cutoff_ms,
localized_attributes: localized_attributes_rules,
_kind,
} = settings;
@@ -494,13 +485,6 @@ pub fn apply_settings_to_builder(
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 {
Setting::Set(ref value) => {
match value.enabled {
@@ -695,8 +679,6 @@ pub fn settings(
let search_cutoff_ms = index.search_cutoff(rtxn)?;
let localized_attributes_rules = index.localized_attributes_rules(rtxn)?;
let mut settings = Settings {
displayed_attributes: match displayed_attributes {
Some(attrs) => Setting::Set(attrs),
@@ -729,10 +711,6 @@ pub fn settings(
Some(cutoff) => Setting::Set(cutoff),
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,
};
@@ -924,7 +902,6 @@ pub(crate) mod test {
faceting: Setting::NotSet,
pagination: Setting::NotSet,
embedders: Setting::NotSet,
localized_attributes: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
_kind: PhantomData::<Unchecked>,
};
@@ -953,7 +930,6 @@ pub(crate) mod test {
faceting: Setting::NotSet,
pagination: Setting::NotSet,
embedders: Setting::NotSet,
localized_attributes: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
_kind: PhantomData::<Unchecked>,
};

View File

@@ -114,7 +114,6 @@ maplit = "1.0.2"
meili-snap = { path = "../meili-snap" }
temp-env = "0.3.6"
urlencoding = "2.1.3"
wiremock = "0.6.0"
yaup = "0.3.1"
[build-dependencies]

View File

@@ -1,4 +1,4 @@
use std::collections::{BTreeSet, BinaryHeap, HashMap, HashSet};
use std::collections::{BinaryHeap, HashMap, HashSet};
use std::fs;
use std::mem::take;
use std::path::{Path, PathBuf};
@@ -10,7 +10,6 @@ use actix_web::HttpRequest;
use byte_unit::Byte;
use index_scheduler::IndexScheduler;
use meilisearch_auth::{AuthController, AuthFilter};
use meilisearch_types::locales::Locale;
use meilisearch_types::InstanceUid;
use once_cell::sync::Lazy;
use regex::Regex;
@@ -654,9 +653,6 @@ pub struct SearchAggregator {
// every time a search is done, we increment the counter linked to the used settings
matching_strategy: HashMap<String, usize>,
// List of the unique Locales passed as parameter
locales: BTreeSet<Locale>,
// pagination
max_limit: usize,
max_offset: usize,
@@ -711,7 +707,6 @@ impl SearchAggregator {
attributes_to_search_on,
hybrid,
ranking_score_threshold,
locales,
} = query;
let mut ret = Self::default();
@@ -779,10 +774,6 @@ impl SearchAggregator {
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_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
@@ -868,7 +859,6 @@ impl SearchAggregator {
total_degraded,
total_used_negative_operator,
ranking_score_threshold,
ref mut locales,
} = other;
if self.timestamp.is_none() {
@@ -957,9 +947,6 @@ impl SearchAggregator {
self.show_ranking_score |= show_ranking_score;
self.show_ranking_score_details |= show_ranking_score_details;
self.ranking_score_threshold |= ranking_score_threshold;
// locales
self.locales.append(locales);
}
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -1004,7 +991,6 @@ impl SearchAggregator {
total_degraded,
total_used_negative_operator,
ranking_score_threshold,
locales,
} = self;
if total_received == 0 {
@@ -1074,7 +1060,6 @@ impl SearchAggregator {
"matching_strategy": {
"most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
},
"locales": locales,
"scoring": {
"show_ranking_score": show_ranking_score,
"show_ranking_score_details": show_ranking_score_details,
@@ -1165,7 +1150,6 @@ impl MultiSearchAggregator {
attributes_to_search_on: _,
hybrid: _,
ranking_score_threshold: _,
locales: _,
} = query;
index_uid.as_str()
@@ -1323,7 +1307,6 @@ impl FacetSearchAggregator {
attributes_to_search_on,
hybrid,
ranking_score_threshold,
locales,
} = query;
let mut ret = Self::default();
@@ -1339,8 +1322,7 @@ impl FacetSearchAggregator {
|| *matching_strategy != MatchingStrategy::default()
|| attributes_to_search_on.is_some()
|| hybrid.is_some()
|| ranking_score_threshold.is_some()
|| locales.is_some();
|| ranking_score_threshold.is_some();
ret
}

View File

@@ -13,10 +13,11 @@ pub mod search_queue;
use std::fs::File;
use std::io::{BufReader, BufWriter};
use std::num::NonZeroUsize;
use std::path::Path;
use std::str::FromStr;
use std::sync::Arc;
use std::thread;
use std::thread::{self, available_parallelism};
use std::time::Duration;
use actix_cors::Cors;
@@ -117,7 +118,6 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
pub fn create_app(
index_scheduler: Data<IndexScheduler>,
auth_controller: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: Opt,
logs: (LogRouteHandle, LogStderrHandle),
analytics: Arc<dyn Analytics>,
@@ -137,7 +137,6 @@ pub fn create_app(
s,
index_scheduler.clone(),
auth_controller.clone(),
search_queue.clone(),
&opt,
logs,
analytics.clone(),
@@ -470,16 +469,19 @@ pub fn configure_data(
config: &mut web::ServiceConfig,
index_scheduler: Data<IndexScheduler>,
auth: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: &Opt,
(logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
analytics: Arc<dyn Analytics>,
) {
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.as_u64() as usize;
config
.app_data(index_scheduler)
.app_data(auth)
.app_data(search_queue)
.app_data(web::Data::new(search_queue))
.app_data(web::Data::from(analytics))
.app_data(web::Data::new(logs_route))
.app_data(web::Data::new(logs_stderr))

View File

@@ -1,10 +1,8 @@
use std::env;
use std::io::{stderr, LineWriter, Write};
use std::num::NonZeroUsize;
use std::path::PathBuf;
use std::str::FromStr;
use std::sync::Arc;
use std::thread::available_parallelism;
use actix_web::http::KeepAlive;
use actix_web::web::Data;
@@ -13,7 +11,6 @@ use index_scheduler::IndexScheduler;
use is_terminal::IsTerminal;
use meilisearch::analytics::Analytics;
use meilisearch::option::LogMode;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{
analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
LogStderrType, Opt, SubscriberForSecondLayer,
@@ -75,19 +72,6 @@ fn on_panic(info: &std::panic::PanicInfo) {
#[actix_web::main]
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()?;
std::panic::set_hook(Box::new(on_panic));
@@ -151,17 +135,11 @@ async fn run_http(
let opt_clone = opt.clone();
let index_scheduler = Data::from(index_scheduler);
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()),
);
let search_queue = Data::new(search_queue);
let http_server = HttpServer::new(move || {
create_app(
index_scheduler.clone(),
auth_controller.clone(),
search_queue.clone(),
opt.clone(),
logs.clone(),
analytics.clone(),

View File

@@ -6,7 +6,6 @@ use meilisearch_types::deserr::DeserrJsonError;
use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::error::ResponseError;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::locales::Locale;
use serde_json::Value;
use tracing::debug;
@@ -49,8 +48,6 @@ pub struct FacetSearchQuery {
pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>,
#[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
pub locales: Option<Vec<Locale>>,
}
pub async fn search(
@@ -70,7 +67,6 @@ pub async fn search(
let facet_query = query.facet_query.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);
// Tenant token search_rules.
@@ -81,7 +77,7 @@ pub async fn search(
let index = index_scheduler.index(&index_uid)?;
let features = index_scheduler.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 || {
perform_facet_search(
&index,
@@ -90,12 +86,9 @@ pub async fn search(
facet_name,
search_kind,
index_scheduler.features(),
locales,
)
})
.await;
permit.drop().await;
let search_result = search_result?;
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
@@ -120,7 +113,6 @@ impl From<FacetSearchQuery> for SearchQuery {
attributes_to_search_on,
hybrid,
ranking_score_threshold,
locales,
} = value;
SearchQuery {
@@ -149,7 +141,6 @@ impl From<FacetSearchQuery> for SearchQuery {
attributes_to_search_on,
hybrid,
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::ResponseError;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::locales::Locale;
use meilisearch_types::milli;
use meilisearch_types::serde_cs::vec::CS;
use serde_json::Value;
@@ -90,8 +89,6 @@ pub struct SearchQueryGet {
pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchLocales>)]
pub locales: Option<CS<Locale>>,
}
#[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()),
hybrid,
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 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 || {
perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
})
.await;
permit.drop().await;
let search_result = search_result?;
.await?;
if let Ok(ref search_result) = 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 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 || {
perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
})
.await;
permit.drop().await;
let search_result = search_result?;
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
if search_result.degraded {

View File

@@ -474,28 +474,6 @@ make_setting_route!(
}
);
make_setting_route!(
"/localized-attributes",
put,
Vec<meilisearch_types::locales::LocalizedAttributesRuleView>,
meilisearch_types::deserr::DeserrJsonError<
meilisearch_types::error::deserr_codes::InvalidSettingsLocalizedAttributes,
>,
localized_attributes,
"localizedAttributes",
analytics,
|rules: &Option<Vec<meilisearch_types::locales::LocalizedAttributesRuleView>>, req: &HttpRequest| {
use serde_json::json;
analytics.publish(
"LocalizedAttributesRules Updated".to_string(),
json!({
"locales": rules.as_ref().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>())
}),
Some(req),
);
}
);
make_setting_route!(
"/ranking-rules",
put,
@@ -682,7 +660,6 @@ generate_configure!(
filterable_attributes,
sortable_attributes,
displayed_attributes,
localized_attributes,
searchable_attributes,
distinct_attribute,
proximity_precision,
@@ -809,7 +786,6 @@ pub async fn update_all(
},
"embedders": crate::routes::indexes::settings::embedder_analytics(new_settings.embedders.as_ref().set()),
"search_cutoff_ms": new_settings.search_cutoff_ms.as_ref().set(),
"locales": new_settings.localized_attributes.as_ref().set().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>()),
}),
Some(&req),
);

View File

@@ -39,7 +39,7 @@ pub async fn multi_search_with_post(
) -> Result<HttpResponse, ResponseError> {
// Since we don't want to process half of the search requests and then get a permit refused
// we're going to get one permit for the whole duration of the multi-search request.
let permit = search_queue.try_get_search_permit().await?;
let _permit = search_queue.try_get_search_permit().await?;
let federated_search = params.into_inner();
@@ -81,7 +81,6 @@ pub async fn multi_search_with_post(
perform_federated_search(&index_scheduler, queries, federation, features)
})
.await;
permit.drop().await;
if let Ok(Ok(_)) = search_result {
multi_aggregate.succeed();
@@ -144,7 +143,6 @@ pub async fn multi_search_with_post(
Ok(search_results)
}
.await;
permit.drop().await;
if search_results.is_ok() {
multi_aggregate.succeed();

View File

@@ -380,6 +380,9 @@ pub fn perform_federated_search(
let criteria = index.criteria(&rtxn)?;
// stuff we need for the hitmaker
let script_lang_map = index.script_language(&rtxn)?;
let dictionary = index.dictionary(&rtxn)?;
let dictionary: Option<Vec<_>> =
dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
@@ -491,7 +494,6 @@ pub fn perform_federated_search(
sort: query.sort,
show_ranking_score: query.show_ranking_score,
show_ranking_score_details: query.show_ranking_score_details,
locales: query.locales.map(|l| l.iter().copied().map(Into::into).collect()),
};
let milli::SearchResult {
@@ -507,7 +509,11 @@ pub fn perform_federated_search(
degraded |= query_degraded;
used_negative_operator |= query_used_negative_operator;
let tokenizer = HitMaker::tokenizer(dictionary.as_deref(), separators.as_deref());
let tokenizer = HitMaker::tokenizer(
&script_lang_map,
dictionary.as_deref(),
separators.as_deref(),
);
let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);

View File

@@ -1,6 +1,6 @@
use core::fmt;
use std::cmp::min;
use std::collections::{BTreeMap, BTreeSet, HashSet};
use std::collections::{BTreeMap, BTreeSet, HashMap, HashSet};
use std::str::FromStr;
use std::sync::Arc;
use std::time::{Duration, Instant};
@@ -15,17 +15,16 @@ use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::error::{Code, ResponseError};
use meilisearch_types::heed::RoTxn;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::locales::Locale;
use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
use meilisearch_types::milli::vector::Embedder;
use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues, TimeBudget};
use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
use meilisearch_types::{milli, Document};
use milli::tokenizer::{Language, TokenizerBuilder};
use milli::tokenizer::TokenizerBuilder;
use milli::{
AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, LocalizedAttributesRule,
MatchBounds, MatcherBuilder, SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, MatchBounds, MatcherBuilder,
SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
};
use regex::Regex;
use serde::Serialize;
@@ -101,8 +100,6 @@ pub struct SearchQuery {
pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>,
#[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
pub locales: Option<Vec<Locale>>,
}
#[derive(Debug, Clone, Copy, PartialEq, Deserr)]
@@ -172,7 +169,6 @@ impl fmt::Debug for SearchQuery {
matching_strategy,
attributes_to_search_on,
ranking_score_threshold,
locales,
} = self;
let mut debug = f.debug_struct("SearchQuery");
@@ -254,10 +250,6 @@ impl fmt::Debug for SearchQuery {
debug.field("ranking_score_threshold", &ranking_score_threshold);
}
if let Some(locales) = locales {
debug.field("locales", &locales);
}
debug.finish()
}
}
@@ -433,8 +425,6 @@ pub struct SearchQueryWithIndex {
pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>,
#[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
pub locales: Option<Vec<Locale>>,
#[deserr(default)]
pub federation_options: Option<FederationOptions>,
@@ -487,7 +477,6 @@ impl SearchQueryWithIndex {
attributes_to_search_on,
hybrid,
ranking_score_threshold,
locales,
} = self;
(
index_uid,
@@ -517,7 +506,6 @@ impl SearchQueryWithIndex {
attributes_to_search_on,
hybrid,
ranking_score_threshold,
locales,
// do not use ..Default::default() here,
// rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
},
@@ -878,10 +866,6 @@ fn prepare_search<'t>(
search.sort_criteria(sort);
}
if let Some(ref locales) = query.locales {
search.locales(locales.iter().copied().map(Into::into).collect());
}
Ok((search, is_finite_pagination, max_total_hits, offset))
}
@@ -933,7 +917,6 @@ pub fn perform_search(
highlight_pre_tag,
highlight_post_tag,
crop_marker,
locales,
// already used in prepare_search
vector: _,
hybrid: _,
@@ -958,7 +941,6 @@ pub fn perform_search(
sort,
show_ranking_score,
show_ranking_score_details,
locales: locales.map(|l| l.iter().copied().map(Into::into).collect()),
};
let documents = make_hits(
@@ -1064,7 +1046,6 @@ struct AttributesFormat {
sort: Option<Vec<String>>,
show_ranking_score: bool,
show_ranking_score_details: bool,
locales: Option<Vec<Language>>,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -1112,16 +1093,19 @@ struct HitMaker<'a> {
show_ranking_score_details: bool,
sort: Option<Vec<String>>,
show_matches_position: bool,
locales: Option<Vec<Language>>,
}
impl<'a> HitMaker<'a> {
pub fn tokenizer<'b>(
script_lang_map: &'b HashMap<milli::tokenizer::Script, Vec<milli::tokenizer::Language>>,
dictionary: Option<&'b [&'b str]>,
separators: Option<&'b [&'b str]>,
) -> milli::tokenizer::Tokenizer<'b> {
let mut tokenizer_builder = TokenizerBuilder::default();
tokenizer_builder.create_char_map(true);
if !script_lang_map.is_empty() {
tokenizer_builder.allow_list(script_lang_map);
}
if let Some(separators) = separators {
tokenizer_builder.separators(separators);
@@ -1234,7 +1218,6 @@ impl<'a> HitMaker<'a> {
show_ranking_score_details: format.show_ranking_score_details,
show_matches_position: format.show_matches_position,
sort: format.sort,
locales: format.locales,
})
}
@@ -1290,9 +1273,6 @@ impl<'a> HitMaker<'a> {
document.insert("_vectors".into(), vectors.into());
}
let localized_attributes =
self.index.localized_attributes_rules(self.rtxn)?.unwrap_or_default();
let (matches_position, formatted) = format_fields(
&displayed_document,
&self.fields_ids_map,
@@ -1300,8 +1280,6 @@ impl<'a> HitMaker<'a> {
&self.formatted_options,
self.show_matches_position,
&self.displayed_ids,
self.locales.as_deref(),
&localized_attributes,
)?;
if let Some(sort) = self.sort.as_ref() {
@@ -1334,6 +1312,8 @@ fn make_hits<'a>(
) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
let mut documents = Vec::new();
let script_lang_map = index.script_language(rtxn)?;
let dictionary = index.dictionary(rtxn)?;
let dictionary: Option<Vec<_>> =
dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
@@ -1341,7 +1321,8 @@ fn make_hits<'a>(
let separators: Option<Vec<_>> =
separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
let tokenizer = HitMaker::tokenizer(dictionary.as_deref(), separators.as_deref());
let tokenizer =
HitMaker::tokenizer(&script_lang_map, dictionary.as_deref(), separators.as_deref());
let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
@@ -1360,7 +1341,6 @@ pub fn perform_facet_search(
facet_name: String,
search_kind: SearchKind,
features: RoFeatures,
locales: Option<Vec<Language>>,
) -> Result<FacetSearchResult, ResponseError> {
let before_search = Instant::now();
let rtxn = index.read_txn()?;
@@ -1369,20 +1349,6 @@ pub fn perform_facet_search(
None => TimeBudget::default(),
};
// In the faceted search context, we want to use the intersection between the locales provided by the user
// and the locales of the facet string.
// If the facet string is not localized, we **ignore** the locales provided by the user because the facet data has no locale.
// If the user does not provide locales, we use the locales of the facet string.
let localized_attributes = index.localized_attributes_rules(&rtxn)?.unwrap_or_default();
let localized_attributes_locales =
localized_attributes.into_iter().find(|attr| attr.match_str(&facet_name));
let locales = localized_attributes_locales.map(|attr| {
attr.locales
.into_iter()
.filter(|locale| locales.as_ref().map_or(true, |locales| locales.contains(locale)))
.collect()
});
let (search, _, _, _) =
prepare_search(index, &rtxn, &search_query, &search_kind, time_budget, features)?;
let mut facet_search = SearchForFacetValues::new(
@@ -1397,10 +1363,6 @@ pub fn perform_facet_search(
facet_search.max_values(max_facets as usize);
}
if let Some(locales) = locales {
facet_search.locales(locales);
}
Ok(FacetSearchResult {
facet_hits: facet_search.execute()?,
facet_query,
@@ -1481,7 +1443,6 @@ pub fn perform_similar(
sort: None,
show_ranking_score,
show_ranking_score_details,
locales: None,
};
let hits = make_hits(
@@ -1663,7 +1624,6 @@ fn make_document(
Ok(document)
}
#[allow(clippy::too_many_arguments)]
fn format_fields(
document: &Document,
field_ids_map: &FieldsIdsMap,
@@ -1671,8 +1631,6 @@ fn format_fields(
formatted_options: &BTreeMap<FieldId, FormatOptions>,
compute_matches: bool,
displayable_ids: &BTreeSet<FieldId>,
locales: Option<&[Language]>,
localized_attributes: &[LocalizedAttributesRule],
) -> Result<(Option<MatchesPosition>, Document), MeilisearchHttpError> {
let mut matches_position = compute_matches.then(BTreeMap::new);
let mut document = document.clone();
@@ -1705,22 +1663,7 @@ fn format_fields(
.reduce(|acc, option| acc.merge(option));
let mut infos = Vec::new();
// if no locales has been provided, we try to find the locales in the localized_attributes.
let locales = locales.or_else(|| {
localized_attributes
.iter()
.find(|rule| rule.match_str(key))
.map(LocalizedAttributesRule::locales)
});
*value = format_value(
std::mem::take(value),
builder,
format,
&mut infos,
compute_matches,
locales,
);
*value = format_value(std::mem::take(value), builder, format, &mut infos, compute_matches);
if let Some(matches) = matches_position.as_mut() {
if !infos.is_empty() {
@@ -1745,11 +1688,10 @@ fn format_value(
format_options: Option<FormatOptions>,
infos: &mut Vec<MatchBounds>,
compute_matches: bool,
locales: Option<&[Language]>,
) -> Value {
match value {
Value::String(old_string) => {
let mut matcher = builder.build(&old_string, locales);
let mut matcher = builder.build(&old_string);
if compute_matches {
let matches = matcher.matches();
infos.extend_from_slice(&matches[..]);
@@ -1776,7 +1718,6 @@ fn format_value(
}),
infos,
compute_matches,
locales,
)
})
.collect(),
@@ -1796,7 +1737,6 @@ fn format_value(
}),
infos,
compute_matches,
locales,
),
)
})
@@ -1805,7 +1745,7 @@ fn format_value(
Value::Number(number) => {
let s = number.to_string();
let mut matcher = builder.build(&s, locales);
let mut matcher = builder.build(&s);
if compute_matches {
let matches = matcher.matches();
infos.extend_from_slice(&matches[..]);

View File

@@ -18,7 +18,6 @@
//! And should drop the Permit only once you have freed all the RAM consumed by the method.
use std::num::NonZeroUsize;
use std::time::Duration;
use rand::rngs::StdRng;
use rand::{Rng, SeedableRng};
@@ -30,31 +29,16 @@ use crate::error::MeilisearchHttpError;
pub struct SearchQueue {
sender: mpsc::Sender<oneshot::Sender<Permit>>,
capacity: usize,
/// If we have waited longer than this to get a permit, we should abort the search request entirely.
/// The client probably already closed the connection, but we have no way to find out.
time_to_abort: Duration,
}
/// You should only run search requests while holding this permit.
/// Once it's dropped, a new search request will be able to process.
/// You should always try to drop the permit yourself calling the `drop` async method on it.
#[derive(Debug)]
pub struct Permit {
sender: mpsc::Sender<()>,
}
impl Permit {
/// Drop the permit giving back on permit to the search queue.
pub async fn drop(self) {
// if the channel is closed then the whole instance is down
let _ = self.sender.send(()).await;
}
}
impl Drop for Permit {
/// The implicit drop implementation can still be called in multiple cases:
/// - We forgot to call the explicit one somewhere => this should be fixed on our side asap
/// - The future is cancelled while running and the permit dropped with it
fn drop(&mut self) {
let sender = self.sender.clone();
// if the channel is closed then the whole instance is down
@@ -69,11 +53,7 @@ impl SearchQueue {
let (sender, receiver) = mpsc::channel(1);
tokio::task::spawn(Self::run(capacity, paralellism, receiver));
Self { sender, capacity, time_to_abort: Duration::from_secs(60) }
}
pub fn with_time_to_abort(self, time_to_abort: Duration) -> Self {
Self { time_to_abort, ..self }
Self { sender, capacity }
}
/// This function is the main loop, it's in charge on scheduling which search request should execute first and
@@ -139,23 +119,9 @@ impl SearchQueue {
/// Returns a search `Permit`.
/// It should be dropped as soon as you've freed all the RAM associated with the search request being processed.
pub async fn try_get_search_permit(&self) -> Result<Permit, MeilisearchHttpError> {
let now = std::time::Instant::now();
let (sender, receiver) = oneshot::channel();
self.sender.send(sender).await.map_err(|_| MeilisearchHttpError::SearchLimiterIsDown)?;
let permit = receiver
.await
.map_err(|_| MeilisearchHttpError::TooManySearchRequests(self.capacity))?;
// If we've been for more than one minute to get a search permit, it's better to simply
// abort the search request than spending time processing something were the client
// most certainly exited or got a timeout a long time ago.
// We may find a better solution in https://github.com/actix/actix-web/issues/3462.
if now.elapsed() > self.time_to_abort {
permit.drop().await;
Err(MeilisearchHttpError::TooManySearchRequests(self.capacity))
} else {
Ok(permit)
}
receiver.await.map_err(|_| MeilisearchHttpError::TooManySearchRequests(self.capacity))
}
/// Returns `Ok(())` if everything seems normal.

View File

@@ -80,15 +80,7 @@ impl Display for Value {
write!(
f,
"{}",
json_string!(self, {
".uid" => "[uid]",
".enqueuedAt" => "[date]",
".startedAt" => "[date]",
".finishedAt" => "[date]",
".duration" => "[duration]",
".processingTimeMs" => "[duration]",
".details.embedders.*.url" => "[url]"
})
json_string!(self, { ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]", ".processingTimeMs" => "[duration]" })
)
}
}

View File

@@ -1,9 +1,6 @@
#![allow(dead_code)]
use std::num::NonZeroUsize;
use std::path::Path;
use std::str::FromStr as _;
use std::sync::Arc;
use std::time::Duration;
use actix_http::body::MessageBody;
@@ -11,8 +8,7 @@ use actix_web::dev::ServiceResponse;
use actix_web::http::StatusCode;
use byte_unit::{Byte, Unit};
use clap::Parser;
use meilisearch::option::{IndexerOpts, MaxMemory, MaxThreads, Opt};
use meilisearch::search_queue::SearchQueue;
use meilisearch::option::{IndexerOpts, MaxMemory, Opt};
use meilisearch::{analytics, create_app, setup_meilisearch, SubscriberForSecondLayer};
use once_cell::sync::Lazy;
use tempfile::TempDir;
@@ -35,12 +31,6 @@ pub struct Server {
pub static TEST_TEMP_DIR: Lazy<TempDir> = Lazy::new(|| TempDir::new().unwrap());
impl Server {
fn new_search_queue(options: &Opt) -> Arc<SearchQueue> {
let search_queue =
SearchQueue::new(options.experimental_search_queue_size, NonZeroUsize::new(1).unwrap());
Arc::new(search_queue)
}
pub async fn new() -> Self {
let dir = TempDir::new().unwrap();
@@ -53,13 +43,7 @@ impl Server {
let options = default_settings(dir.path());
let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
let service = Service {
index_scheduler,
auth,
search_queue: Self::new_search_queue(&options),
options,
api_key: None,
};
let service = Service { index_scheduler, auth, options, api_key: None };
Server { service, _dir: Some(dir) }
}
@@ -74,13 +58,7 @@ impl Server {
options.master_key = Some("MASTER_KEY".to_string());
let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
let service = Service {
index_scheduler,
auth,
search_queue: Self::new_search_queue(&options),
options,
api_key: None,
};
let service = Service { index_scheduler, auth, options, api_key: None };
Server { service, _dir: Some(dir) }
}
@@ -93,13 +71,7 @@ impl Server {
pub async fn new_with_options(options: Opt) -> Result<Self, anyhow::Error> {
let (index_scheduler, auth) = setup_meilisearch(&options)?;
let service = Service {
index_scheduler,
auth,
search_queue: Self::new_search_queue(&options),
options,
api_key: None,
};
let service = Service { index_scheduler, auth, options, api_key: None };
Ok(Server { service, _dir: None })
}
@@ -127,7 +99,6 @@ impl Server {
actix_web::test::init_service(create_app(
self.service.index_scheduler.clone().into(),
self.service.auth.clone().into(),
self.service.search_queue.clone().into(),
self.service.options.clone(),
(route_layer_handle, stderr_layer_handle),
analytics::MockAnalytics::new(&self.service.options),
@@ -268,7 +239,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
// memory has to be unlimited because several meilisearch are running in test context.
max_indexing_memory: MaxMemory::unlimited(),
skip_index_budget: true,
max_indexing_threads: MaxThreads::from_str("1").unwrap(),
..Parser::parse_from(None as Option<&str>)
},
experimental_enable_metrics: false,
..Parser::parse_from(None as Option<&str>)

View File

@@ -5,7 +5,6 @@ use actix_web::http::StatusCode;
use actix_web::test;
use actix_web::test::TestRequest;
use index_scheduler::IndexScheduler;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
use meilisearch_auth::AuthController;
use tracing::level_filters::LevelFilter;
@@ -17,7 +16,6 @@ use crate::common::Value;
pub struct Service {
pub index_scheduler: Arc<IndexScheduler>,
pub auth: Arc<AuthController>,
pub search_queue: Arc<SearchQueue>,
pub options: Opt,
pub api_key: Option<String>,
}
@@ -125,7 +123,6 @@ impl Service {
let app = test::init_service(create_app(
self.index_scheduler.clone().into(),
self.auth.clone().into(),
self.search_queue.clone().into(),
self.options.clone(),
(route_layer_handle, stderr_layer_handle),
analytics::MockAnalytics::new(&self.options),

View File

@@ -1110,7 +1110,7 @@ async fn document_addition_with_huge_int_primary_key() {
snapshot!(response,
@r###"
{
"uid": "[uid]",
"uid": 0,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -1402,7 +1402,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
snapshot!(response,
@r###"
{
"uid": "[uid]",
"uid": 1,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -1436,7 +1436,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
snapshot!(response,
@r###"
{
"uid": "[uid]",
"uid": 2,
"indexUid": "test",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -1485,7 +1485,7 @@ async fn error_document_field_limit_reached_in_one_nested_document() {
snapshot!(response,
@r###"
{
"uid": "[uid]",
"uid": 1,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -1528,7 +1528,7 @@ async fn error_document_field_limit_reached_over_multiple_documents_with_nested_
snapshot!(response,
@r###"
{
"uid": "[uid]",
"uid": 1,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -1563,7 +1563,7 @@ async fn error_document_field_limit_reached_over_multiple_documents_with_nested_
snapshot!(response,
@r###"
{
"uid": "[uid]",
"uid": 2,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -2209,7 +2209,7 @@ async fn add_invalid_geo_and_then_settings() {
let ret = index.wait_task(ret.uid()).await;
snapshot!(ret, @r###"
{
"uid": "[uid]",
"uid": 1,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -2231,7 +2231,7 @@ async fn add_invalid_geo_and_then_settings() {
let ret = index.wait_task(ret.uid()).await;
snapshot!(ret, @r###"
{
"uid": "[uid]",
"uid": 2,
"indexUid": "test",
"status": "failed",
"type": "settingsUpdate",

View File

@@ -78,8 +78,7 @@ async fn import_dump_v1_movie_raw() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -241,8 +240,7 @@ async fn import_dump_v1_movie_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -390,8 +388,7 @@ async fn import_dump_v1_rubygems_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -525,8 +522,7 @@ async fn import_dump_v2_movie_raw() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -672,8 +668,7 @@ async fn import_dump_v2_movie_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -818,8 +813,7 @@ async fn import_dump_v2_rubygems_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -953,8 +947,7 @@ async fn import_dump_v3_movie_raw() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -1100,8 +1093,7 @@ async fn import_dump_v3_movie_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -1246,8 +1238,7 @@ async fn import_dump_v3_rubygems_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -1381,8 +1372,7 @@ async fn import_dump_v4_movie_raw() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -1528,8 +1518,7 @@ async fn import_dump_v4_movie_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -1674,8 +1663,7 @@ async fn import_dump_v4_rubygems_with_settings() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###
);
@@ -1921,8 +1909,7 @@ async fn import_dump_v6_containing_experimental_features() {
"pagination": {
"maxTotalHits": 1000
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###);
@@ -2100,8 +2087,7 @@ async fn generate_and_import_dump_containing_vectors() {
"documentTemplate": "{{doc.doggo}}"
}
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###);

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/dumps/mod.rs
---
{
"uid": "[uid]",
"uid": 0,
"indexUid": "pets",
"status": "succeeded",
"type": "settingsUpdate",

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/dumps/mod.rs
---
{
"uid": "[uid]",
"uid": 1,
"indexUid": "pets",
"status": "succeeded",
"type": "documentAdditionOrUpdate",

View File

@@ -44,7 +44,6 @@ async fn basic_test_log_stream_route() {
let app = actix_web::test::init_service(create_app(
server.service.index_scheduler.clone().into(),
server.service.auth.clone().into(),
server.service.search_queue.clone().into(),
server.service.options.clone(),
(route_layer_handle, stderr_layer_handle),
analytics::MockAnalytics::new(&server.service.options),

View File

@@ -497,7 +497,7 @@ async fn query_combination() {
snapshot!(code, @"400 Bad Request");
snapshot!(response, @r###"
{
"message": "Error while generating embeddings: user error: attempt to embed the following text in a configuration where embeddings must be user provided:\n - `Captain`",
"message": "Error while generating embeddings: user error: attempt to embed the following text in a configuration where embeddings must be user provided: \"Captain\"",
"code": "vector_embedding_error",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"

File diff suppressed because it is too large Load Diff

View File

@@ -7,8 +7,6 @@ mod facet_search;
mod formatted;
mod geo;
mod hybrid;
#[cfg(not(feature = "chinese-pinyin"))]
mod locales;
mod matching_strategy;
mod multi;
mod pagination;
@@ -266,6 +264,85 @@ async fn simple_search() {
})
.await;
}
#[actix_rt::test]
async fn filter_should_not_return_documents_with_missing_filterable_value() {
let server = Server::new().await;
let index = server.index("test");
let documents = NESTED_DOCUMENTS.clone();
let (_, code) = index
.update_settings(json!({"filterableAttributes": ["custom_propertie.999.options"]}))
.await;
meili_snap::snapshot!(code, @"202 Accepted");
index
.add_documents(
json!([
{
"id": 951,
"custom_propertie": {
"999": {
"type": "multi",
"options": [
{
"slug": "group_1",
"age": 6,
},
{
"slug": "group_2",
"age": 8,
},
]
}
},
}]),
None,
)
.await;
index.wait_task(1).await;
index
.search(
json!({"filter": "custom_propertie.999.options.slug IN ['group_2']"}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
},
)
.await;
index
.add_documents(
json!([
{
"id": 951,
"custom_propertie": {
"999": {
"type": "multi",
"options": [
{
"slug": "group_1",
"age": 6,
},
]
}
},
}]),
None,
)
.await;
index.wait_task(2).await;
index
.search(
json!({"filter": "custom_propertie.999.options.slug IN ['group_2']"}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
},
)
.await;
}
#[actix_rt::test]
async fn phrase_search_with_stop_word() {
@@ -393,7 +470,6 @@ async fn negative_special_cases_search() {
}
#[cfg(feature = "default")]
#[cfg(not(feature = "chinese-pinyin"))]
#[actix_rt::test]
async fn test_kanji_language_detection() {
let server = Server::new().await;

View File

@@ -37,43 +37,6 @@ async fn search_queue_register() {
.unwrap();
}
#[actix_rt::test]
async fn search_queue_register_with_explicit_drop() {
let queue = SearchQueue::new(4, NonZeroUsize::new(2).unwrap());
// First, use all the cores
let permit1 = queue.try_get_search_permit().await.unwrap();
let _permit2 = queue.try_get_search_permit().await.unwrap();
// If we free one spot we should be able to register one new search
permit1.drop().await;
let permit3 = queue.try_get_search_permit().await.unwrap();
// And again
permit3.drop().await;
let _permit4 = queue.try_get_search_permit().await.unwrap();
}
#[actix_rt::test]
async fn search_queue_register_with_time_to_abort() {
let queue = Arc::new(
SearchQueue::new(1, NonZeroUsize::new(1).unwrap())
.with_time_to_abort(Duration::from_secs(1)),
);
// First, use all the cores
let permit1 = queue.try_get_search_permit().await.unwrap();
let q = queue.clone();
let permit2 = tokio::task::spawn(async move { q.try_get_search_permit().await });
tokio::time::sleep(Duration::from_secs(1)).await;
permit1.drop().await;
let ret = permit2.await.unwrap();
snapshot!(ret.unwrap_err(), @"Too many search requests running at the same time: 1. Retry after 10s.");
}
#[actix_rt::test]
async fn wait_till_cores_are_available() {
let queue = Arc::new(SearchQueue::new(4, NonZeroUsize::new(1).unwrap()));

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/search/distinct.rs
---
{
"uid": "[uid]",
"uid": 1,
"indexUid": "tamo",
"status": "succeeded",
"type": "settingsUpdate",

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/search/errors.rs
---
{
"uid": "[uid]",
"uid": 0,
"indexUid": "tamo",
"status": "succeeded",
"type": "indexCreation",

View File

@@ -9,7 +9,6 @@ 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("localized_attributes", json!(null));
map.insert("filterable_attributes", json!([]));
map.insert("distinct_attribute", json!(null));
map.insert(
@@ -56,7 +55,7 @@ async fn get_settings() {
let (response, code) = index.settings().await;
assert_eq!(code, 200);
let settings = response.as_object().unwrap();
assert_eq!(settings.keys().len(), 17);
assert_eq!(settings.keys().len(), 16);
assert_eq!(settings["displayedAttributes"], json!(["*"]));
assert_eq!(settings["searchableAttributes"], json!(["*"]));
assert_eq!(settings["filterableAttributes"], json!([]));
@@ -117,8 +116,6 @@ async fn secrets_are_hidden_in_settings() {
"url": "https://localhost:7777",
"apiKey": "My super secret value you will never guess",
"dimensions": 4,
"request": "{{text}}",
"response": "{{embedding}}"
}
}
}))
@@ -192,13 +189,20 @@ async fn secrets_are_hidden_in_settings() {
"dimensions": 4,
"documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
"url": "https://localhost:7777",
"request": "{{text}}",
"response": "{{embedding}}",
"headers": {}
"query": null,
"inputField": [
"input"
],
"pathToEmbeddings": [
"data"
],
"embeddingObject": [
"embedding"
],
"inputType": "text"
}
},
"searchCutoffMs": null,
"localizedAttributes": null
"searchCutoffMs": null
}
"###);
@@ -211,9 +215,7 @@ async fn secrets_are_hidden_in_settings() {
"source": "rest",
"apiKey": "My suXXXXXX...",
"dimensions": 4,
"url": "https://localhost:7777",
"request": "{{text}}",
"response": "{{embedding}}"
"url": "https://localhost:7777"
}
}
}
@@ -410,7 +412,6 @@ macro_rules! test_setting_routes {
test_setting_routes!(
filterable_attributes put,
displayed_attributes put,
localized_attributes put,
searchable_attributes put,
distinct_attribute put,
stop_words put,

View File

@@ -744,7 +744,7 @@ async fn test_summarized_index_deletion() {
snapshot!(task,
@r###"
{
"uid": "[uid]",
"uid": 0,
"indexUid": "test",
"status": "failed",
"type": "indexDeletion",
@@ -774,7 +774,7 @@ async fn test_summarized_index_deletion() {
snapshot!(task,
@r###"
{
"uid": "[uid]",
"uid": 1,
"indexUid": "test",
"status": "succeeded",
"type": "documentAdditionOrUpdate",
@@ -796,7 +796,7 @@ async fn test_summarized_index_deletion() {
snapshot!(task,
@r###"
{
"uid": "[uid]",
"uid": 2,
"indexUid": "test",
"status": "succeeded",
"type": "indexDeletion",
@@ -818,7 +818,7 @@ async fn test_summarized_index_deletion() {
snapshot!(task,
@r###"
{
"uid": "[uid]",
"uid": 3,
"indexUid": "test",
"status": "failed",
"type": "indexDeletion",

View File

@@ -1,5 +1,3 @@
mod openai;
mod rest;
mod settings;
use meili_snap::{json_string, snapshot};
@@ -8,22 +6,6 @@ use crate::common::index::Index;
use crate::common::{GetAllDocumentsOptions, Server};
use crate::json;
async fn get_server_vector() -> Server {
let server = Server::new().await;
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false,
"editDocumentsByFunction": false,
"containsFilter": false
}
"###);
server
}
#[actix_rt::test]
async fn add_remove_user_provided() {
let server = Server::new().await;
@@ -235,7 +217,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 2,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -264,7 +246,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 3,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -294,7 +276,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 4,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -323,7 +305,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 5,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -352,7 +334,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 6,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -381,7 +363,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 7,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -422,7 +404,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 10,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -450,7 +432,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 11,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -478,7 +460,7 @@ async fn user_provided_embeddings_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 12,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -504,27 +486,26 @@ async fn user_provided_embeddings_error() {
#[actix_rt::test]
async fn user_provided_vectors_error() {
let server = Server::new().await;
let index = generate_default_user_provided_documents(&server).await;
// First case, we forget to specify `_vectors`
let documents = json!([{"id": 40, "name": "kefir"}, {"id": 41, "name": "intel"}, {"id": 42, "name": "max"}, {"id": 43, "name": "venus"}, {"id": 44, "name": "eva"}]);
let documents = json!({"id": 42, "name": "kefir"});
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 2,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
"canceledBy": null,
"details": {
"receivedDocuments": 5,
"receivedDocuments": 1,
"indexedDocuments": 0
},
"error": {
"message": "While embedding documents for embedder `manual`: no vectors provided for document \"40\" and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
"message": "While embedding documents for embedder `manual`: user error: attempt to embed the following text in a configuration where embeddings must be user provided: \" id: 42\\n name: kefir\\n _vectors: \\n _vectors.manual: \\n _vectors.manual.regenerate: \\n _vectors.manual.embeddings: \\n\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
"code": "vector_embedding_error",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -543,7 +524,7 @@ async fn user_provided_vectors_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 3,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -553,7 +534,7 @@ async fn user_provided_vectors_error() {
"indexedDocuments": 0
},
"error": {
"message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
"message": "While embedding documents for embedder `manual`: user error: attempt to embed the following text in a configuration where embeddings must be user provided: \" id: 42\\n name: kefir\\n _vectors: \\n _vectors.manual: \\n _vectors.manual.regenerate: \\n _vectors.manual.embeddings: \\n _vector: manaul000\\n _vector.manaul: \\n\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
"code": "vector_embedding_error",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -572,7 +553,7 @@ async fn user_provided_vectors_error() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r###"
{
"uid": "[uid]",
"uid": 4,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
@@ -582,7 +563,7 @@ async fn user_provided_vectors_error() {
"indexedDocuments": 0
},
"error": {
"message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
"message": "While embedding documents for embedder `manual`: user error: attempt to embed the following text in a configuration where embeddings must be user provided: \" id: 42\\n name: kefir\\n _vectors: manaul000\\n _vectors.manual: \\n _vectors.manual.regenerate: \\n _vectors.manual.embeddings: \\n _vectors.manaul: \\n\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
"code": "vector_embedding_error",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -43,7 +43,7 @@ async fn update_embedder() {
let ret = server.wait_task(response.uid()).await;
snapshot!(ret, @r###"
{
"uid": "[uid]",
"uid": 1,
"indexUid": "doggo",
"status": "succeeded",
"type": "settingsUpdate",

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/vector/mod.rs
---
{
"uid": "[uid]",
"uid": 1,
"indexUid": "doggo",
"status": "succeeded",
"type": "documentAdditionOrUpdate",

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/vector/mod.rs
---
{
"uid": "[uid]",
"uid": 2,
"indexUid": "doggo",
"status": "succeeded",
"type": "documentAdditionOrUpdate",

View File

@@ -2,7 +2,7 @@
source: meilisearch/tests/vector/mod.rs
---
{
"uid": "[uid]",
"uid": 0,
"indexUid": "doggo",
"status": "succeeded",
"type": "settingsUpdate",

View File

@@ -17,7 +17,7 @@ bincode = "1.3.3"
bstr = "1.9.1"
bytemuck = { version = "1.16.1", features = ["extern_crate_alloc"] }
byteorder = "1.5.0"
charabia = { version = "0.9.1", default-features = false }
charabia = { version = "0.8.12", default-features = false }
concat-arrays = "0.1.2"
crossbeam-channel = "0.5.13"
deserr = "0.6.2"
@@ -106,7 +106,6 @@ all-tokenizations = [
"charabia/greek",
"charabia/khmer",
"charabia/vietnamese",
"charabia/swedish-recomposition",
]
# Use POSIX semaphores instead of SysV semaphores in LMDB

View File

@@ -68,7 +68,6 @@ fn main() -> Result<(), Box<dyn Error>> {
logger,
TimeBudget::max(),
None,
None,
)?;
if let Some((logger, dir)) = detailed_logger {
logger.finish(&mut ctx, Path::new(dir))?;

View File

@@ -7,6 +7,7 @@ mod fst_set_codec;
mod obkv_codec;
mod roaring_bitmap;
mod roaring_bitmap_length;
mod script_language_codec;
mod str_beu32_codec;
mod str_ref;
mod str_str_u8_codec;
@@ -25,6 +26,7 @@ pub use self::roaring_bitmap::{BoRoaringBitmapCodec, CboRoaringBitmapCodec, Roar
pub use self::roaring_bitmap_length::{
BoRoaringBitmapLenCodec, CboRoaringBitmapLenCodec, RoaringBitmapLenCodec,
};
pub use self::script_language_codec::ScriptLanguageCodec;
pub use self::str_beu32_codec::{StrBEU16Codec, StrBEU32Codec};
pub use self::str_str_u8_codec::{U8StrStrCodec, UncheckedU8StrStrCodec};

View File

@@ -0,0 +1,39 @@
use std::borrow::Cow;
use std::ffi::CStr;
use std::str;
use charabia::{Language, Script};
use heed::BoxedError;
pub struct ScriptLanguageCodec;
impl<'a> heed::BytesDecode<'a> for ScriptLanguageCodec {
type DItem = (Script, Language);
fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
let cstr = CStr::from_bytes_until_nul(bytes)?;
let script = cstr.to_str()?;
let script_name = Script::from_name(script);
// skip '\0' byte between the two strings.
let lan = str::from_utf8(&bytes[script.len() + 1..])?;
let lan_name = Language::from_name(lan);
Ok((script_name, lan_name))
}
}
impl<'a> heed::BytesEncode<'a> for ScriptLanguageCodec {
type EItem = (Script, Language);
fn bytes_encode((script, lan): &Self::EItem) -> Result<Cow<'a, [u8]>, BoxedError> {
let script_name = script.name().as_bytes();
let lan_name = lan.name().as_bytes();
let mut bytes = Vec::with_capacity(script_name.len() + lan_name.len() + 1);
bytes.extend_from_slice(script_name);
bytes.push(0);
bytes.extend_from_slice(lan_name);
Ok(Cow::Owned(bytes))
}
}

View File

@@ -4,11 +4,13 @@ use std::convert::TryInto;
use std::fs::File;
use std::path::Path;
use charabia::{Language, Script};
use heed::types::*;
use heed::{CompactionOption, Database, RoTxn, RwTxn, Unspecified};
use roaring::RoaringBitmap;
use rstar::RTree;
use serde::{Deserialize, Serialize};
use time::OffsetDateTime;
use crate::documents::PrimaryKey;
use crate::error::{InternalError, UserError};
@@ -17,7 +19,9 @@ use crate::heed_codec::facet::{
FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
FieldIdCodec, OrderedF64Codec,
};
use crate::heed_codec::{BEU16StrCodec, FstSetCodec, StrBEU16Codec, StrRefCodec};
use crate::heed_codec::{
BEU16StrCodec, FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec,
};
use crate::order_by_map::OrderByMap;
use crate::proximity::ProximityPrecision;
use crate::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME;
@@ -25,8 +29,8 @@ use crate::vector::{Embedding, EmbeddingConfig};
use crate::{
default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
FacetDistribution, FieldDistribution, FieldId, FieldIdMapMissingEntry, FieldIdWordCountCodec,
FieldidsWeightsMap, GeoPoint, LocalizedAttributesRule, ObkvCodec, Result, RoaringBitmapCodec,
RoaringBitmapLenCodec, Search, U8StrStrCodec, Weight, BEU16, BEU32, BEU64,
FieldidsWeightsMap, GeoPoint, ObkvCodec, Result, RoaringBitmapCodec, RoaringBitmapLenCodec,
Search, U8StrStrCodec, Weight, BEU16, BEU32, BEU64,
};
pub const DEFAULT_MIN_WORD_LEN_ONE_TYPO: u8 = 5;
@@ -69,7 +73,6 @@ pub mod main_key {
pub const PROXIMITY_PRECISION: &str = "proximity-precision";
pub const EMBEDDING_CONFIGS: &str = "embedding_configs";
pub const SEARCH_CUTOFF: &str = "search_cutoff";
pub const LOCALIZED_ATTRIBUTES_RULES: &str = "localized_attributes_rules";
}
pub mod db_name {
@@ -98,6 +101,7 @@ pub mod db_name {
pub const VECTOR_EMBEDDER_CATEGORY_ID: &str = "vector-embedder-category-id";
pub const VECTOR_ARROY: &str = "vector-arroy";
pub const DOCUMENTS: &str = "documents";
pub const SCRIPT_LANGUAGE_DOCIDS: &str = "script_language_docids";
}
#[derive(Clone)]
@@ -138,6 +142,9 @@ pub struct Index {
/// Maps the word prefix and a field id with all the docids where the prefix appears inside the field
pub word_prefix_fid_docids: Database<StrBEU16Codec, CboRoaringBitmapCodec>,
/// Maps the script and language with all the docids that corresponds to it.
pub script_language_docids: Database<ScriptLanguageCodec, RoaringBitmapCodec>,
/// Maps the facet field id and the docids for which this field exists
pub facet_id_exists_docids: Database<FieldIdCodec, CboRoaringBitmapCodec>,
/// Maps the facet field id and the docids for which this field is set as null
@@ -172,8 +179,8 @@ impl Index {
pub fn new_with_creation_dates<P: AsRef<Path>>(
mut options: heed::EnvOpenOptions,
path: P,
created_at: time::OffsetDateTime,
updated_at: time::OffsetDateTime,
created_at: OffsetDateTime,
updated_at: OffsetDateTime,
) -> Result<Index> {
use db_name::*;
@@ -191,6 +198,8 @@ impl Index {
env.create_database(&mut wtxn, Some(EXACT_WORD_PREFIX_DOCIDS))?;
let word_pair_proximity_docids =
env.create_database(&mut wtxn, Some(WORD_PAIR_PROXIMITY_DOCIDS))?;
let script_language_docids =
env.create_database(&mut wtxn, Some(SCRIPT_LANGUAGE_DOCIDS))?;
let word_position_docids = env.create_database(&mut wtxn, Some(WORD_POSITION_DOCIDS))?;
let word_fid_docids = env.create_database(&mut wtxn, Some(WORD_FIELD_ID_DOCIDS))?;
let field_id_word_count_docids =
@@ -234,6 +243,7 @@ impl Index {
word_prefix_docids,
exact_word_prefix_docids,
word_pair_proximity_docids,
script_language_docids,
word_position_docids,
word_fid_docids,
word_prefix_position_docids,
@@ -255,22 +265,22 @@ impl Index {
}
pub fn new<P: AsRef<Path>>(options: heed::EnvOpenOptions, path: P) -> Result<Index> {
let now = time::OffsetDateTime::now_utc();
let now = OffsetDateTime::now_utc();
Self::new_with_creation_dates(options, path, now, now)
}
fn set_creation_dates(
env: &heed::Env,
main: Database<Unspecified, Unspecified>,
created_at: time::OffsetDateTime,
updated_at: time::OffsetDateTime,
created_at: OffsetDateTime,
updated_at: OffsetDateTime,
) -> heed::Result<()> {
let mut txn = env.write_txn()?;
// The db was just created, we update its metadata with the relevant information.
let main = main.remap_types::<Str, SerdeJson<OffsetDateTime>>();
if main.get(&txn, main_key::CREATED_AT_KEY)?.is_none() {
main.put(&mut txn, main_key::UPDATED_AT_KEY, &OffsetDateTime(updated_at))?;
main.put(&mut txn, main_key::CREATED_AT_KEY, &OffsetDateTime(created_at))?;
main.put(&mut txn, main_key::UPDATED_AT_KEY, &updated_at)?;
main.put(&mut txn, main_key::CREATED_AT_KEY, &created_at)?;
txn.commit()?;
}
Ok(())
@@ -370,7 +380,7 @@ impl Index {
wtxn: &mut RwTxn<'_>,
primary_key: &str,
) -> heed::Result<()> {
self.set_updated_at(wtxn, &time::OffsetDateTime::now_utc())?;
self.set_updated_at(wtxn, &OffsetDateTime::now_utc())?;
self.main.remap_types::<Str, Str>().put(wtxn, main_key::PRIMARY_KEY_KEY, primary_key)
}
@@ -1322,7 +1332,7 @@ impl Index {
}
/// Returns the index creation time.
pub fn created_at(&self, rtxn: &RoTxn<'_>) -> Result<time::OffsetDateTime> {
pub fn created_at(&self, rtxn: &RoTxn<'_>) -> Result<OffsetDateTime> {
Ok(self
.main
.remap_types::<Str, SerdeJson<OffsetDateTime>>()
@@ -1330,12 +1340,11 @@ impl Index {
.ok_or(InternalError::DatabaseMissingEntry {
db_name: db_name::MAIN,
key: Some(main_key::CREATED_AT_KEY),
})?
.0)
})?)
}
/// Returns the index last updated time.
pub fn updated_at(&self, rtxn: &RoTxn<'_>) -> Result<time::OffsetDateTime> {
pub fn updated_at(&self, rtxn: &RoTxn<'_>) -> Result<OffsetDateTime> {
Ok(self
.main
.remap_types::<Str, SerdeJson<OffsetDateTime>>()
@@ -1343,19 +1352,18 @@ impl Index {
.ok_or(InternalError::DatabaseMissingEntry {
db_name: db_name::MAIN,
key: Some(main_key::UPDATED_AT_KEY),
})?
.0)
})?)
}
pub(crate) fn set_updated_at(
&self,
wtxn: &mut RwTxn<'_>,
time: &time::OffsetDateTime,
time: &OffsetDateTime,
) -> heed::Result<()> {
self.main.remap_types::<Str, SerdeJson<OffsetDateTime>>().put(
wtxn,
main_key::UPDATED_AT_KEY,
&OffsetDateTime(*time),
time,
)
}
@@ -1554,32 +1562,46 @@ impl Index {
self.main.remap_key_type::<Str>().delete(txn, main_key::PROXIMITY_PRECISION)
}
pub fn localized_attributes_rules(
/* script language docids */
/// Retrieve all the documents ids that correspond with (Script, Language) key, `None` if it is any.
pub fn script_language_documents_ids(
&self,
rtxn: &RoTxn<'_>,
) -> heed::Result<Option<Vec<LocalizedAttributesRule>>> {
self.main
.remap_types::<Str, SerdeJson<Vec<LocalizedAttributesRule>>>()
.get(rtxn, main_key::LOCALIZED_ATTRIBUTES_RULES)
key: &(Script, Language),
) -> heed::Result<Option<RoaringBitmap>> {
self.script_language_docids.get(rtxn, key)
}
pub(crate) fn put_localized_attributes_rules(
pub fn script_language(
&self,
txn: &mut RwTxn<'_>,
val: Vec<LocalizedAttributesRule>,
) -> heed::Result<()> {
self.main.remap_types::<Str, SerdeJson<Vec<LocalizedAttributesRule>>>().put(
txn,
main_key::LOCALIZED_ATTRIBUTES_RULES,
&val,
)
}
rtxn: &RoTxn<'_>,
) -> heed::Result<HashMap<Script, Vec<Language>>> {
let mut script_language: HashMap<Script, Vec<Language>> = HashMap::new();
let mut script_language_doc_count: Vec<(Script, Language, u64)> = Vec::new();
let mut total = 0;
for sl in self.script_language_docids.iter(rtxn)? {
let ((script, language), docids) = sl?;
pub(crate) fn delete_localized_attributes_rules(
&self,
txn: &mut RwTxn<'_>,
) -> heed::Result<bool> {
self.main.remap_key_type::<Str>().delete(txn, main_key::LOCALIZED_ATTRIBUTES_RULES)
// keep only Languages that contains at least 1 document.
let remaining_documents_count = docids.len();
total += remaining_documents_count;
if remaining_documents_count > 0 {
script_language_doc_count.push((script, language, remaining_documents_count));
}
}
let threshold = total / 20; // 5% (arbitrary)
for (script, language, count) in script_language_doc_count {
if count > threshold {
if let Some(languages) = script_language.get_mut(&script) {
(*languages).push(language);
} else {
script_language.insert(script, vec![language]);
}
}
}
Ok(script_language)
}
/// Put the embedding configs:
@@ -1682,10 +1704,6 @@ pub struct IndexEmbeddingConfig {
pub user_provided: RoaringBitmap,
}
#[derive(Serialize, Deserialize)]
#[serde(transparent)]
struct OffsetDateTime(#[serde(with = "time::serde::rfc3339")] time::OffsetDateTime);
#[cfg(test)]
pub(crate) mod tests {
use std::collections::HashSet;

View File

@@ -16,7 +16,6 @@ pub mod facet;
mod fields_ids_map;
pub mod heed_codec;
pub mod index;
mod localized_attributes_rules;
pub mod order_by_map;
pub mod prompt;
pub mod proximity;
@@ -63,8 +62,6 @@ pub use self::heed_codec::{
UncheckedU8StrStrCodec,
};
pub use self::index::Index;
pub use self::localized_attributes_rules::LocalizedAttributesRule;
use self::localized_attributes_rules::LocalizedFieldIds;
pub use self::search::facet::{FacetValueHit, SearchForFacetValues};
pub use self::search::similar::Similar;
pub use self::search::{

View File

@@ -1,129 +0,0 @@
use std::collections::HashMap;
use charabia::Language;
use serde::{Deserialize, Serialize};
use crate::fields_ids_map::FieldsIdsMap;
use crate::FieldId;
/// A rule that defines which locales are supported for a given attribute.
///
/// The rule is a list of attribute patterns and a list of locales.
/// The attribute patterns are matched against the attribute name.
/// The pattern `*` matches any attribute name.
/// The pattern `attribute_name*` matches any attribute name that starts with `attribute_name`.
/// The pattern `*attribute_name` matches any attribute name that ends with `attribute_name`.
/// The pattern `*attribute_name*` matches any attribute name that contains `attribute_name`.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct LocalizedAttributesRule {
pub attribute_patterns: Vec<String>,
pub locales: Vec<Language>,
}
impl LocalizedAttributesRule {
pub fn new(attribute_patterns: Vec<String>, locales: Vec<Language>) -> Self {
Self { attribute_patterns, locales }
}
pub fn match_str(&self, str: &str) -> bool {
self.attribute_patterns.iter().any(|pattern| match_pattern(pattern.as_str(), str))
}
pub fn locales(&self) -> &[Language] {
&self.locales
}
}
fn match_pattern(pattern: &str, str: &str) -> bool {
if pattern == "*" {
true
} else if pattern.starts_with('*') && pattern.ends_with('*') {
str.contains(&pattern[1..pattern.len() - 1])
} else if let Some(pattern) = pattern.strip_prefix('*') {
str.ends_with(pattern)
} else if let Some(pattern) = pattern.strip_suffix('*') {
str.starts_with(pattern)
} else {
pattern == str
}
}
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct LocalizedFieldIds {
field_id_to_locales: HashMap<FieldId, Vec<Language>>,
}
impl LocalizedFieldIds {
pub fn new<I: Iterator<Item = FieldId>>(
rules: &Option<Vec<LocalizedAttributesRule>>,
fields_ids_map: &FieldsIdsMap,
fields_ids: I,
) -> Self {
let mut field_id_to_locales = HashMap::new();
if let Some(rules) = rules {
let fields = fields_ids.filter_map(|field_id| {
fields_ids_map.name(field_id).map(|field_name| (field_id, field_name))
});
for (field_id, field_name) in fields {
let mut locales = Vec::new();
for rule in rules {
if rule.match_str(field_name) {
locales.extend(rule.locales.iter());
// Take the first rule that matches
break;
}
}
if !locales.is_empty() {
locales.sort();
locales.dedup();
field_id_to_locales.insert(field_id, locales);
}
}
}
Self { field_id_to_locales }
}
pub fn locales(&self, fields_id: FieldId) -> Option<&[Language]> {
self.field_id_to_locales.get(&fields_id).map(Vec::as_slice)
}
pub fn all_locales(&self) -> Vec<Language> {
let mut locales = Vec::new();
for field_locales in self.field_id_to_locales.values() {
if !field_locales.is_empty() {
locales.extend(field_locales);
} else {
// If a field has no locales, we consider it as not localized
return Vec::new();
}
}
locales.sort();
locales.dedup();
locales
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_match_pattern() {
assert!(match_pattern("*", "test"));
assert!(match_pattern("test*", "test"));
assert!(match_pattern("test*", "testa"));
assert!(match_pattern("*test", "test"));
assert!(match_pattern("*test", "atest"));
assert!(match_pattern("*test*", "test"));
assert!(match_pattern("*test*", "atesta"));
assert!(match_pattern("*test*", "atest"));
assert!(match_pattern("*test*", "testa"));
assert!(!match_pattern("test*test", "test"));
assert!(!match_pattern("*test", "testa"));
assert!(!match_pattern("test*", "atest"));
}
}

View File

@@ -3,7 +3,7 @@ use std::collections::BinaryHeap;
use std::ops::ControlFlow;
use charabia::normalizer::NormalizerOption;
use charabia::{Language, Normalize, StrDetection, Token};
use charabia::Normalize;
use fst::automaton::{Automaton, Str};
use fst::{IntoStreamer, Streamer};
use roaring::RoaringBitmap;
@@ -23,7 +23,6 @@ pub struct SearchForFacetValues<'a> {
search_query: Search<'a>,
max_values: usize,
is_hybrid: bool,
locales: Option<Vec<Language>>,
}
impl<'a> SearchForFacetValues<'a> {
@@ -38,7 +37,6 @@ impl<'a> SearchForFacetValues<'a> {
search_query,
max_values: DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET,
is_hybrid,
locales: None,
}
}
@@ -52,11 +50,6 @@ impl<'a> SearchForFacetValues<'a> {
self
}
pub fn locales(&mut self, locales: Vec<Language>) -> &mut Self {
self.locales = Some(locales);
self
}
fn one_original_value_of(
&self,
field_id: FieldId,
@@ -116,7 +109,8 @@ impl<'a> SearchForFacetValues<'a> {
match self.query.as_ref() {
Some(query) => {
let query = normalize_facet_string(query, self.locales.as_deref());
let options = NormalizerOption { lossy: true, ..Default::default() };
let query = query.normalize(&options);
let query = query.as_ref();
let authorize_typos = self.search_query.index.authorize_typos(rtxn)?;
@@ -336,23 +330,3 @@ impl ValuesCollection {
}
}
}
fn normalize_facet_string(facet_string: &str, locales: Option<&[Language]>) -> String {
let options = NormalizerOption { lossy: true, ..Default::default() };
let mut detection = StrDetection::new(facet_string, locales);
// Detect the language of the facet string only if several locales are explicitly provided.
let language = match locales {
Some(&[language]) => Some(language),
Some(multiple_locales) if multiple_locales.len() > 1 => detection.language(),
_ => None,
};
let token = Token {
lemma: std::borrow::Cow::Borrowed(facet_string),
script: detection.script(),
language,
..Default::default()
};
token.normalize(&options).lemma.into_owned()
}

View File

@@ -174,7 +174,6 @@ impl<'a> Search<'a> {
semantic: self.semantic.clone(),
time_budget: self.time_budget.clone(),
ranking_score_threshold: self.ranking_score_threshold,
locales: self.locales.clone(),
};
let semantic = search.semantic.take();

View File

@@ -1,7 +1,6 @@
use std::fmt;
use std::sync::Arc;
use charabia::Language;
use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
use once_cell::sync::Lazy;
use roaring::bitmap::RoaringBitmap;
@@ -53,7 +52,6 @@ pub struct Search<'a> {
semantic: Option<SemanticSearch>,
time_budget: TimeBudget,
ranking_score_threshold: Option<f64>,
locales: Option<Vec<Language>>,
}
impl<'a> Search<'a> {
@@ -74,7 +72,6 @@ impl<'a> Search<'a> {
rtxn,
index,
semantic: None,
locales: None,
time_budget: TimeBudget::max(),
ranking_score_threshold: None,
}
@@ -163,11 +160,6 @@ impl<'a> Search<'a> {
self
}
pub fn locales(&mut self, locales: Vec<Language>) -> &mut Search<'a> {
self.locales = Some(locales);
self
}
pub fn execute_for_candidates(&self, has_vector_search: bool) -> Result<RoaringBitmap> {
if has_vector_search {
let ctx = SearchContext::new(self.index, self.rtxn)?;
@@ -240,7 +232,6 @@ impl<'a> Search<'a> {
&mut DefaultSearchLogger,
self.time_budget.clone(),
self.ranking_score_threshold,
self.locales.as_ref(),
)?,
};
@@ -281,7 +272,6 @@ impl fmt::Debug for Search<'_> {
semantic,
time_budget,
ranking_score_threshold,
locales,
} = self;
f.debug_struct("Search")
.field("query", query)
@@ -302,7 +292,6 @@ impl fmt::Debug for Search<'_> {
)
.field("time_budget", time_budget)
.field("ranking_score_threshold", ranking_score_threshold)
.field("locales", locales)
.finish()
}
}
@@ -360,7 +349,6 @@ mod test {
use super::*;
#[cfg(feature = "japanese")]
#[cfg(not(feature = "chinese-pinyin"))]
#[test]
fn test_kanji_language_detection() {
use crate::index::tests::TempIndex;

View File

@@ -110,18 +110,18 @@ impl<'ctx> DatabaseCache<'ctx> {
.map_err(Into::into)
}
fn get_value_from_keys<'v, K1, KC>(
fn get_value_from_keys<'v, K1, KC, DC>(
txn: &'ctx RoTxn<'_>,
cache_key: K1,
db_keys: &'v [KC::EItem],
cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
db: Database<KC, Bytes>,
universe: Option<&RoaringBitmap>,
merger: MergeFn,
) -> Result<Option<RoaringBitmap>>
) -> Result<Option<DC::DItem>>
where
K1: Copy + Eq + Hash,
KC: BytesEncode<'v>,
DC: BytesDecodeOwned,
KC::EItem: Sized,
{
if let Entry::Vacant(entry) = cache.entry(cache_key) {
@@ -146,22 +146,16 @@ impl<'ctx> DatabaseCache<'ctx> {
entry.insert(bitmap_ptr);
}
let bitmap_bytes = match cache.get(&cache_key).unwrap() {
Some(Cow::Borrowed(bytes)) => bytes,
Some(Cow::Owned(bytes)) => bytes.as_slice(),
None => return Ok(None),
};
match (bitmap_bytes, universe) {
(bytes, Some(universe)) => {
CboRoaringBitmapCodec::intersection_with_serialized(bytes, universe)
.map(Some)
.map_err(Into::into)
}
(bytes, None) => CboRoaringBitmapCodec::bytes_decode_owned(bytes)
match cache.get(&cache_key).unwrap() {
Some(Cow::Borrowed(bytes)) => DC::bytes_decode_owned(bytes)
.map(Some)
.map_err(heed::Error::Decoding)
.map_err(Into::into),
Some(Cow::Owned(bytes)) => DC::bytes_decode_owned(bytes)
.map(Some)
.map_err(heed::Error::Decoding)
.map_err(Into::into),
None => Ok(None),
}
}
}
@@ -213,13 +207,12 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> =
restricted_fids.tolerant.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _>(
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
self.txn,
word,
&keys[..],
&mut self.db_cache.word_docids,
self.index.word_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps,
)
}
@@ -245,13 +238,12 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> =
restricted_fids.exact.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _>(
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
self.txn,
word,
&keys[..],
&mut self.db_cache.exact_word_docids,
self.index.word_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps,
)
}
@@ -302,13 +294,12 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> =
restricted_fids.tolerant.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _>(
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
self.txn,
prefix,
&keys[..],
&mut self.db_cache.word_prefix_docids,
self.index.word_prefix_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps,
)
}
@@ -334,13 +325,12 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> =
restricted_fids.exact.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _>(
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
self.txn,
prefix,
&keys[..],
&mut self.db_cache.exact_word_prefix_docids,
self.index.word_prefix_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps,
)
}

View File

@@ -1,6 +1,6 @@
use std::borrow::Cow;
use charabia::{Language, SeparatorKind, Token, Tokenizer};
use charabia::{SeparatorKind, Token, Tokenizer};
pub use matching_words::MatchingWords;
use matching_words::{MatchType, PartialMatch, WordId};
use serde::Serialize;
@@ -46,11 +46,7 @@ impl<'m> MatcherBuilder<'m> {
self
}
pub fn build<'t, 'lang>(
&self,
text: &'t str,
locales: Option<&'lang [Language]>,
) -> Matcher<'t, 'm, '_, 'lang> {
pub fn build<'t>(&self, text: &'t str) -> Matcher<'t, 'm, '_> {
let crop_marker = match &self.crop_marker {
Some(marker) => marker.as_str(),
None => DEFAULT_CROP_MARKER,
@@ -72,7 +68,6 @@ impl<'m> MatcherBuilder<'m> {
highlight_prefix,
highlight_suffix,
matches: None,
locales,
}
}
}
@@ -112,18 +107,17 @@ pub struct MatchBounds {
/// Structure used to analyze a string, compute words that match,
/// and format the source string, returning a highlighted and cropped sub-string.
pub struct Matcher<'t, 'tokenizer, 'b, 'lang> {
pub struct Matcher<'t, 'tokenizer, 'b> {
text: &'t str,
matching_words: &'b MatchingWords,
tokenizer: &'b Tokenizer<'tokenizer>,
locales: Option<&'lang [Language]>,
crop_marker: &'b str,
highlight_prefix: &'b str,
highlight_suffix: &'b str,
matches: Option<(Vec<Token<'t>>, Vec<Match>)>,
}
impl<'t, 'tokenizer> Matcher<'t, 'tokenizer, '_, '_> {
impl<'t, 'tokenizer> Matcher<'t, 'tokenizer, '_> {
/// Iterates over tokens and save any of them that matches the query.
fn compute_matches(&mut self) -> &mut Self {
/// some words are counted as matches only if they are close together and in the good order,
@@ -179,8 +173,7 @@ impl<'t, 'tokenizer> Matcher<'t, 'tokenizer, '_, '_> {
false
}
let tokens: Vec<_> =
self.tokenizer.tokenize_with_allow_list(self.text, self.locales).collect();
let tokens: Vec<_> = self.tokenizer.tokenize(self.text).collect();
let mut matches = Vec::new();
let mut words_positions = tokens
@@ -537,7 +530,6 @@ mod tests {
&mut crate::DefaultSearchLogger,
TimeBudget::max(),
None,
None,
)
.unwrap();
@@ -561,19 +553,19 @@ mod tests {
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop and no highlight should return complete text.
assert_eq!(&matcher.format(format_options), &text);
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop and no highlight should return complete text.
assert_eq!(&matcher.format(format_options), &text);
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop and no highlight should return complete text.
assert_eq!(&matcher.format(format_options), &text);
}
@@ -588,23 +580,23 @@ mod tests {
// empty text.
let text = "";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
assert_eq!(&matcher.format(format_options), "");
// text containing only separators.
let text = ":-)";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
assert_eq!(&matcher.format(format_options), ":-)");
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop should return complete text, because there is no matches.
assert_eq!(&matcher.format(format_options), &text);
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -613,7 +605,7 @@ mod tests {
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -630,7 +622,7 @@ mod tests {
// Text containing prefix match.
let text = "Ŵôřlḑôle";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -639,7 +631,7 @@ mod tests {
// Text containing unicode match.
let text = "Ŵôřlḑ";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -651,7 +643,7 @@ mod tests {
// Text containing unicode match.
let text = "Westfália";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -669,7 +661,7 @@ mod tests {
// empty text.
let text = "";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@""
@@ -677,7 +669,7 @@ mod tests {
// text containing only separators.
let text = ":-)";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@":-)"
@@ -685,7 +677,7 @@ mod tests {
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no highlight should return 10 first words with a marker at the end.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -694,7 +686,7 @@ mod tests {
// Text without any match starting by a separator.
let text = "(A quick brown fox can not jump 32 feet, right? Brr, it is cold!)";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no highlight should return 10 first words with a marker at the end.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -703,7 +695,7 @@ mod tests {
// Test phrase propagation
let text = "Natalie risk her future. Split The World is a book written by Emily Henry. I never read it.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// should crop the phrase instead of croping around the match.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -712,7 +704,7 @@ mod tests {
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no highlight should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -721,7 +713,7 @@ mod tests {
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// no highlight should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -730,7 +722,7 @@ mod tests {
// Text containing a match unordered and a match ordered.
let text = "The world split void void void void void void void void void split the world void void";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -739,7 +731,7 @@ mod tests {
// Text containing matches with different density.
let text = "split void the void void world void void void void void void void void void void split the world void void";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -748,7 +740,7 @@ mod tests {
// Text containing matches with same word.
let text = "split split split split split split void void void void void void void void void void split the world void void";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -766,7 +758,7 @@ mod tests {
// empty text.
let text = "";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@""
@@ -774,7 +766,7 @@ mod tests {
// text containing only separators.
let text = ":-)";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@":-)"
@@ -782,7 +774,7 @@ mod tests {
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// both should return 10 first words with a marker at the end.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -791,7 +783,7 @@ mod tests {
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// both should return 10 last words with a marker at the start and highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -800,7 +792,7 @@ mod tests {
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// both should return 10 last words with a marker at the start and highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -809,7 +801,7 @@ mod tests {
// Text containing a match unordered and a match ordered.
let text = "The world split void void void void void void void void void split the world void void";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -832,7 +824,7 @@ mod tests {
let text = "The groundbreaking invention had the power to split the world between those who embraced progress and those who resisted change!";
let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "\"the world\"");
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// should return 10 words with a marker at the start as well the end, and the highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -840,7 +832,7 @@ mod tests {
);
let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "those \"and those\"");
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// should highlight "those" and the phrase "and those".
insta::assert_snapshot!(
matcher.format(format_options),
@@ -859,7 +851,7 @@ mod tests {
// set a smaller crop size
let format_options = FormatOptions { highlight: false, crop: Some(2) };
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// because crop size < query size, partially format matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -868,7 +860,7 @@ mod tests {
// set a smaller crop size
let format_options = FormatOptions { highlight: false, crop: Some(1) };
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// because crop size < query size, partially format matches.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -877,7 +869,7 @@ mod tests {
// set crop size to 0
let format_options = FormatOptions { highlight: false, crop: Some(0) };
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
// because crop size is 0, crop is ignored.
insta::assert_snapshot!(
matcher.format(format_options),
@@ -897,7 +889,7 @@ mod tests {
let format_options = FormatOptions { highlight: true, crop: None };
let text = "the do or die can't be he do and or isn't he";
let mut matcher = builder.build(text, None);
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@"_the_ _do_ _or_ die can't be he do and or isn'_t_ _he_"

View File

@@ -24,7 +24,7 @@ mod tests;
use std::collections::HashSet;
use bucket_sort::{bucket_sort, BucketSortOutput};
use charabia::{Language, TokenizerBuilder};
use charabia::TokenizerBuilder;
use db_cache::DatabaseCache;
use exact_attribute::ExactAttribute;
use graph_based_ranking_rule::{Exactness, Fid, Position, Proximity, Typo};
@@ -49,7 +49,6 @@ pub use self::geo_sort::Strategy as GeoSortStrategy;
use self::graph_based_ranking_rule::Words;
use self::interner::Interned;
use self::vector_sort::VectorSort;
use crate::localized_attributes_rules::LocalizedFieldIds;
use crate::score_details::{ScoreDetails, ScoringStrategy};
use crate::search::new::distinct::apply_distinct_rule;
use crate::vector::Embedder;
@@ -640,7 +639,6 @@ pub fn execute_search(
query_graph_logger: &mut dyn SearchLogger<QueryGraph>,
time_budget: TimeBudget,
ranking_score_threshold: Option<f64>,
locales: Option<&Vec<Language>>,
) -> Result<PartialSearchResult> {
check_sort_criteria(ctx, sort_criteria.as_ref())?;
@@ -672,44 +670,10 @@ pub fn execute_search(
tokbuilder.words_dict(dictionary);
}
let db_locales;
match locales {
Some(locales) => {
if !locales.is_empty() {
tokbuilder.allow_list(locales);
}
}
None => {
// If no locales are specified, we use the locales specified in the localized attributes rules
let localized_attributes_rules = ctx.index.localized_attributes_rules(ctx.txn)?;
let fields_ids_map = ctx.index.fields_ids_map(ctx.txn)?;
let searchable_fields = ctx.index.searchable_fields_ids(ctx.txn)?;
let localized_fields = match &ctx.restricted_fids {
// if AttributeToSearchOn is set, use the restricted list of ids
Some(restricted_fids) => {
let iter = restricted_fids
.exact
.iter()
.chain(restricted_fids.tolerant.iter())
.map(|(fid, _)| *fid);
LocalizedFieldIds::new(&localized_attributes_rules, &fields_ids_map, iter)
}
// Otherwise use the full list of ids coming from the index searchable fields
None => LocalizedFieldIds::new(
&localized_attributes_rules,
&fields_ids_map,
searchable_fields.into_iter(),
),
};
db_locales = localized_fields.all_locales();
if !db_locales.is_empty() {
tokbuilder.allow_list(&db_locales);
}
}
};
let script_lang_map = ctx.index.script_language(ctx.txn)?;
if !script_lang_map.is_empty() {
tokbuilder.allow_list(&script_lang_map);
}
let tokenizer = tokbuilder.build();
drop(entered);

View File

@@ -24,7 +24,7 @@ pub struct ExtractedTokens {
#[tracing::instrument(level = "trace", skip_all, target = "search::query")]
pub fn located_query_terms_from_tokens(
ctx: &mut SearchContext<'_>,
query: NormalizedTokenIter<'_, '_, '_, '_>,
query: NormalizedTokenIter<'_, '_>,
words_limit: Option<usize>,
) -> Result<ExtractedTokens> {
let nbr_typos = number_of_typos_allowed(ctx)?;

View File

@@ -6,7 +6,6 @@ pub mod exactness;
pub mod geo_sort;
pub mod integration;
#[cfg(feature = "all-tokenizations")]
#[cfg(not(feature = "chinese-pinyin"))]
pub mod language;
pub mod ngram_split_words;
pub mod proximity;

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