Compare commits

..

60 Commits

Author SHA1 Message Date
Clément Renault
d96577d441 WIP 2024-02-13 13:51:51 +01:00
Clément Renault
e64ff1fa0c Always keep the new threads and new callsites 2024-02-08 16:44:28 +01:00
Clément Renault
173aad6090 Introduce a tracing tool to filter logs associated to high memory usage 2024-02-08 16:01:02 +01:00
Tamo
0b1bb42753 use debug instead of debug_span 2024-02-08 10:14:50 +01:00
Louis Dureuil
c668906047 Change error messages and fix tests 2024-02-08 09:43:39 +01:00
Louis Dureuil
392b98f3f8 Remove "with_line_numbers" 2024-02-08 09:43:21 +01:00
Tamo
aaab867476 Structures a bunch of logs 2024-02-07 17:57:30 +01:00
Louis Dureuil
3a0847771d Add panic hook to log panics 2024-02-07 17:29:40 +01:00
Louis Dureuil
474934e79f delete inner .gitignore 2024-02-07 16:42:30 +01:00
Louis Dureuil
5daa6be0e4 Write entries into database downgraded to trace level 2024-02-07 15:57:51 +01:00
Louis Dureuil
f57c7825c2 logs route: make memory profiling toggling usable 2024-02-07 15:57:51 +01:00
Louis Dureuil
cfb27adb3e Tracing trace: toggle the profiling of memory at runtime 2024-02-07 15:57:51 +01:00
Tamo
79cabb1e79 update the github discussion links 2024-02-07 15:56:47 +01:00
Tamo
7230ed4bb2 get rids of the log dependencies everywhere 2024-02-07 15:51:38 +01:00
Tamo
b5db926dbf add a profile_memory parameter disabled by default 2024-02-07 14:45:40 +01:00
Tamo
f839c8e61d move the /logs route to the /logs/stream route 2024-02-07 12:13:57 +01:00
Clément Renault
4f9539d91e Simplify MemoryStats fetching 2024-02-07 10:09:47 +01:00
Tamo
15579667d4 add back the actix-web logs 2024-02-07 09:20:18 +01:00
Louis Dureuil
32529d7442 logs route profile mode: don't barf bytes if the buffer is not empty 2024-02-06 18:24:02 +01:00
Clément Renault
6f3420f114 Replace the procfs by libproc 2024-02-06 18:22:01 +01:00
Louis Dureuil
86bad58c9a spanstats: change field names 2024-02-06 17:50:19 +01:00
Louis Dureuil
a874dbc841 tracing-trace: Spanstats deserializable + public fields 2024-02-06 17:50:19 +01:00
Clément Renault
6e772effcb Replace stats_alloc with procfs 2024-02-06 15:21:47 +01:00
Tamo
3331995976 get rids of log in milli and add logs for the bucket sort 2024-02-06 10:49:23 +01:00
Tamo
35d8546fc3 fix the auth 2024-02-05 14:14:13 +01:00
Tamo
53a0daf018 fix the tests and add tests on the experimental features 2024-02-05 14:05:24 +01:00
Tamo
1ab9d9bdf2 hide the route logs behind a feature flag 2024-02-05 13:31:46 +01:00
Tamo
e2b2c55c79 handle and tests errors 2024-02-05 11:52:05 +01:00
Tamo
40487194a7 add a test 2024-02-01 18:02:02 +01:00
Louis Dureuil
995d6ee81d meilisearch: logs route disconnects in profile mode 2024-01-31 17:54:01 +01:00
Louis Dureuil
ba838d1759 meilisearch: don't spawn a report everytime Meilisearch starts 2024-01-31 17:54:01 +01:00
Louis Dureuil
e3be095617 tracing-trace: introduce TraceWriter, trace now only exposes the channel 2024-01-31 17:54:01 +01:00
Louis Dureuil
ab9ecb28cc tracing-trace: implement Error on Error 2024-01-31 17:54:01 +01:00
Tamo
98e946cc6c get rids of env loggegr and fix the tests 2024-01-31 17:46:36 +01:00
Tamo
362ead123a stops profiling in a file by default 2024-01-31 17:21:27 +01:00
Louis Dureuil
9ca4db6ef0 Add cancel log route 2024-01-30 18:15:53 +01:00
Tamo
2f484b7382 start handling reloads with profiling 2024-01-30 16:31:42 +01:00
Tamo
a144ae10d2 start exposing the profiling layer 2024-01-30 14:19:46 +01:00
Louis Dureuil
8b3e0b3826 Add dummy log when calling tasks 2024-01-30 12:28:03 +01:00
Louis Dureuil
9507a20d8b Simplify stream implementation 2024-01-30 12:27:49 +01:00
Louis Dureuil
31df954aa5 better than before??? 2024-01-29 18:45:55 +01:00
Tamo
894c92cd5a make it compile and runtime error 2024-01-29 17:56:43 +01:00
Tamo
279c56a665 init commit 2024-01-29 13:36:10 +01:00
Tamo
9736424142 WIP: first draft at introducing a new log route 2024-01-25 18:09:50 +01:00
Tamo
2224548add nelson is not used anymore 2024-01-24 15:13:34 +01:00
Louis Dureuil
7f7b1b9269 use json lines 2024-01-24 11:16:41 +01:00
Louis Dureuil
75a17bd065 Add span stats processor 2024-01-24 09:50:51 +01:00
Louis Dureuil
20c75aa85c Use with tokio channel in Meilisearch 2024-01-23 16:53:05 +01:00
Louis Dureuil
07263bc0d7 Switch to tokio channel 2024-01-23 16:52:48 +01:00
Louis Dureuil
eb5c725931 Support Events in trace layer 2024-01-23 16:25:05 +01:00
Louis Dureuil
ef49ae7d6f Switch to a single view indicating current usage 2024-01-23 14:37:29 +01:00
Louis Dureuil
879aa786a5 Refactor memory handling and add markers 2024-01-23 14:37:29 +01:00
Clément Renault
33cbbfbe68 Remove the stats_alloc from the default features 2024-01-23 14:37:29 +01:00
Clément Renault
b72146eee4 Give the allocator to the tracer when necessary 2024-01-23 14:37:29 +01:00
Louis Dureuil
803f5a7936 Format the bytes as human readable bytes
Uses the same `byte_unit` version as `meilisearch`
2024-01-23 14:37:29 +01:00
Clément Renault
b177ed5696 Logging the memory usage over time 2024-01-23 14:37:29 +01:00
Louis Dureuil
789e5a9aff Add tracing to Meilisearch 2024-01-23 10:03:31 +01:00
Louis Dureuil
f48fc2e425 Add tracing to milli 2024-01-23 10:03:31 +01:00
Louis Dureuil
34a4a0520f Add tracing to index-scheduler 2024-01-23 10:03:26 +01:00
Louis Dureuil
117e43a9ec Add tracing-trace 2024-01-23 09:40:07 +01:00
340 changed files with 8273 additions and 30735 deletions

View File

@@ -1,2 +1,2 @@
[alias]
xtask = "run --release --package xtask --"
xtask = "run --package xtask --"

View File

@@ -2,13 +2,14 @@
name: New sprint issue
about: ⚠️ Should only be used by the engine team ⚠️
title: ''
labels: 'missing usage in PRD, impacts docs'
labels: ''
assignees: ''
---
Related product team resources: [PRD]() (_internal only_)
Related product discussion:
Related spec: WIP
## Motivation
@@ -20,7 +21,11 @@ Related product discussion:
## TODO
<!---If necessary, create a list with technical/product steps-->
<!---Feel free to adapt this list with more technical/product steps-->
- [ ] Release a prototype
- [ ] If prototype validated, merge changes into `main`
- [ ] Update the spec
### Reminders when modifying the Setting API

View File

@@ -1,28 +0,0 @@
name: Bench (manual)
on:
workflow_dispatch:
inputs:
workload:
description: 'The path to the workloads to execute (workloads/...)'
required: true
default: 'workloads/movies.json'
env:
WORKLOAD_NAME: ${{ github.event.inputs.workload }}
jobs:
benchmarks:
name: Run and upload benchmarks
runs-on: benchmarks
timeout-minutes: 180 # 3h
steps:
- uses: actions/checkout@v3
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
- name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
run: |
cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Manual [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- ${WORKLOAD_NAME}

View File

@@ -1,51 +0,0 @@
name: Bench (PR)
on:
issue_comment:
types: [created]
permissions:
issues: write
env:
GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
jobs:
run-benchmarks-on-comment:
if: startsWith(github.event.comment.body, '/bench')
name: Run and upload benchmarks
runs-on: benchmarks
timeout-minutes: 180 # 3h
steps:
- name: Check for Command
id: command
uses: xt0rted/slash-command-action@v2
with:
command: bench
reaction-type: "rocket"
repo-token: ${{ env.GH_TOKEN }}
- uses: xt0rted/pull-request-comment-branch@v2
id: comment-branch
with:
repo_token: ${{ env.GH_TOKEN }}
- uses: actions/checkout@v3
if: success()
with:
fetch-depth: 0 # fetch full history to be able to get main commit sha
ref: ${{ steps.comment-branch.outputs.head_ref }}
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
- name: Run benchmarks on PR ${{ github.event.issue.id }}
run: |
cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" \
--dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" \
--reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" \
-- ${{ steps.command.outputs.command-arguments }} > benchlinks.txt
- name: Send comment in PR
run: |
gh pr comment ${{github.event.issue.number}} --body-file benchlinks.txt

View File

@@ -1,23 +0,0 @@
name: Indexing bench (push)
on:
push:
branches:
- main
jobs:
benchmarks:
name: Run and upload benchmarks
runs-on: benchmarks
timeout-minutes: 180 # 3h
steps:
- uses: actions/checkout@v3
- uses: helix-editor/rust-toolchain@v1
with:
profile: minimal
# Run benchmarks
- name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}
run: |
cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Push on `main` [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- workloads/*.json

View File

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

View File

@@ -13,9 +13,11 @@ jobs:
runs-on: benchmarks
timeout-minutes: 4320 # 72h
steps:
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: stable
override: true
- name: Check for Command
id: command

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,6 +1,4 @@
name: Look for flaky tests
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
on:
workflow_dispatch:
schedule:
@@ -18,7 +16,10 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Install cargo-flaky
run: cargo install cargo-flaky
- name: Run cargo flaky in the dumps

View File

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

View File

@@ -110,44 +110,6 @@ jobs:
--milestone $MILESTONE_VERSION \
--assignee curquiza
create-update-version-issue:
needs: get-release-version
# Create the update-version issue even if the release is a patch release
if: github.event.action == 'created'
runs-on: ubuntu-latest
env:
ISSUE_TEMPLATE: issue-template.md
steps:
- uses: actions/checkout@v3
- name: Download the issue template
run: curl -s https://raw.githubusercontent.com/meilisearch/engine-team/main/issue-templates/update-version-issue.md > $ISSUE_TEMPLATE
- name: Create the issue
run: |
gh issue create \
--title "Update version in Cargo.toml for $MILESTONE_VERSION" \
--label 'maintenance' \
--body-file $ISSUE_TEMPLATE \
--milestone $MILESTONE_VERSION
create-update-openapi-issue:
needs: get-release-version
# Create the openAPI issue if the release is not only a patch release
if: github.event.action == 'created' && needs.get-release-version.outputs.is-patch == 'false'
runs-on: ubuntu-latest
env:
ISSUE_TEMPLATE: issue-template.md
steps:
- uses: actions/checkout@v3
- name: Download the issue template
run: curl -s https://raw.githubusercontent.com/meilisearch/engine-team/main/issue-templates/update-openapi-issue.md > $ISSUE_TEMPLATE
- name: Create the issue
run: |
gh issue create \
--title "Update Open API file for $MILESTONE_VERSION" \
--label 'maintenance' \
--body-file $ISSUE_TEMPLATE \
--milestone $MILESTONE_VERSION
# ----------------
# MILESTONE CLOSED
# ----------------

View File

@@ -15,8 +15,6 @@ jobs:
debian:
name: Publish debian packagge
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
runs-on: ubuntu-latest
needs: check-version
container:
@@ -27,7 +25,10 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Install cargo-deb
run: cargo install cargo-deb
- uses: actions/checkout@v3

View File

@@ -35,8 +35,6 @@ jobs:
publish-linux:
name: Publish binary for Linux
runs-on: ubuntu-latest
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
needs: check-version
container:
# Use ubuntu-18.04 to compile with glibc 2.27
@@ -47,7 +45,10 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Build
run: cargo build --release --locked
# No need to upload binaries for dry run (cron)
@@ -77,7 +78,10 @@ jobs:
asset_name: meilisearch-windows-amd64.exe
steps:
- uses: actions/checkout@v3
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Build
run: cargo build --release --locked
# No need to upload binaries for dry run (cron)
@@ -103,10 +107,12 @@ jobs:
- name: Checkout repository
uses: actions/checkout@v3
- name: Installing Rust toolchain
uses: helix-editor/rust-toolchain@v1
uses: actions-rs/toolchain@v1
with:
toolchain: stable
profile: minimal
target: ${{ matrix.target }}
override: true
- name: Cargo build
uses: actions-rs/cargo@v1
with:
@@ -126,8 +132,6 @@ jobs:
name: Publish binary for aarch64
runs-on: ubuntu-latest
needs: check-version
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
container:
# Use ubuntu-18.04 to compile with glibc 2.27
image: ubuntu:18.04
@@ -150,10 +154,12 @@ jobs:
add-apt-repository "deb [arch=$(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: helix-editor/rust-toolchain@v1
uses: actions-rs/toolchain@v1
with:
toolchain: stable
profile: minimal
target: ${{ matrix.target }}
override: true
- name: Configure target aarch64 GNU
## Environment variable is not passed using env:
## LD gold won't work with MUSL

View File

@@ -80,11 +80,10 @@ jobs:
type=ref,event=tag
type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
- name: Build and push
uses: docker/build-push-action@v6
uses: docker/build-push-action@v5
with:
push: true
platforms: linux/amd64,linux/arm64
@@ -98,7 +97,7 @@ jobs:
- name: Send CI information to Cloud team
# Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event)
if: github.event_name == 'push'
uses: peter-evans/repository-dispatch@v3
uses: peter-evans/repository-dispatch@v2
with:
token: ${{ secrets.MEILI_BOT_GH_PAT }}
repository: meilisearch/meilisearch-cloud

View File

@@ -21,8 +21,6 @@ jobs:
test-linux:
name: Tests on ubuntu-18.04
runs-on: ubuntu-latest
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
container:
# Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
image: ubuntu:18.04
@@ -33,7 +31,17 @@ jobs:
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- name: Setup test with Rust stable
uses: helix-editor/rust-toolchain@v1
if: github.event_name != 'schedule'
uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Setup test with Rust nightly
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
uses: actions-rs/toolchain@v1
with:
toolchain: nightly
override: true
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
- name: Run cargo check without any default features
@@ -58,7 +66,10 @@ jobs:
- uses: actions/checkout@v3
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Run cargo check without any default features
uses: actions-rs/cargo@v1
with:
@@ -73,8 +84,6 @@ jobs:
test-all-features:
name: Tests almost all features
runs-on: ubuntu-latest
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
container:
# Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
image: ubuntu:18.04
@@ -85,7 +94,10 @@ jobs:
run: |
apt-get update
apt-get install --assume-yes build-essential curl
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Run cargo build with almost all features
run: |
cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
@@ -95,8 +107,6 @@ jobs:
test-disabled-tokenization:
name: Test disabled tokenization
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
runs-on: ubuntu-latest
container:
image: ubuntu:18.04
@@ -107,10 +117,13 @@ jobs:
run: |
apt-get update
apt-get install --assume-yes build-essential curl
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Run cargo tree without default features and check lindera is not present
run: |
if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -vqz lindera; then
echo "lindera has been found in the sources and it shouldn't"
exit 1
fi
@@ -121,8 +134,6 @@ jobs:
# We run tests in debug also, to make sure that the debug_assertions are hit
test-debug:
name: Run tests in debug
env:
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
runs-on: ubuntu-latest
container:
# Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
@@ -133,7 +144,10 @@ jobs:
run: |
apt-get update && apt-get install -y curl
apt-get install build-essential -y
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
toolchain: stable
override: true
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
- name: Run tests in debug
@@ -147,9 +161,11 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: 1.75.0
override: true
components: clippy
- name: Cache dependencies
uses: Swatinem/rust-cache@v2.7.1
@@ -164,10 +180,10 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: helix-editor/rust-toolchain@v1
- uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: nightly-2024-07-09
toolchain: nightly
override: true
components: rustfmt
- name: Cache dependencies

View File

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

2
.gitignore vendored
View File

@@ -9,8 +9,6 @@
/data.ms
/snapshots
/dumps
/bench
/_xtask_benchmark.ms
# Snapshots
## ... large

View File

@@ -1,371 +0,0 @@
# Benchmarks
Currently this repository hosts two kinds of benchmarks:
1. The older "milli benchmarks", that use [criterion](https://github.com/bheisler/criterion.rs) and live in the "benchmarks" directory.
2. The newer "bench" that are workload-based and so split between the [`workloads`](./workloads/) directory and the [`xtask::bench`](./xtask/src/bench/) module.
This document describes the newer "bench" benchmarks. For more details on the "milli benchmarks", see [benchmarks/README.md](./benchmarks/README.md).
## Design philosophy for the benchmarks
The newer "bench" benchmarks are **integration** benchmarks, in the sense that they spawn an actual Meilisearch server and measure its performance end-to-end, including HTTP request overhead.
Since this is prone to fluctuating, the benchmarks regain a bit of precision by measuring the runtime of the individual spans using the [logging machinery](./CONTRIBUTING.md#logging) of Meilisearch.
A span roughly translates to a function call. The benchmark runner collects all the spans by name using the [logs route](https://github.com/orgs/meilisearch/discussions/721) and sums their runtime. The processed results are then sent to the [benchmark dashboard](https://bench.meilisearch.dev), which is in charge of storing and presenting the data.
## Running the benchmarks
Benchmarks can run locally or in CI.
### Locally
#### With a local benchmark dashboard
The benchmarks dashboard lives in its [own repository](https://github.com/meilisearch/benchboard). We provide binaries for Ubuntu/Debian, but you can build from source for other platforms (MacOS should work as it was developed under that platform).
Run the `benchboard` binary to create a fresh database of results. By default it will serve the results and the API to gather results on `http://localhost:9001`.
From the Meilisearch repository, you can then run benchmarks with:
```sh
cargo xtask bench -- workloads/my_workload_1.json ..
```
This command will build and run Meilisearch locally on port 7700, so make sure that this port is available.
To run benchmarks on a different commit, just use the usual git command to get back to the desired commit.
#### Without a local benchmark dashboard
To work with the raw results, you can also skip using a local benchmark dashboard.
Run:
```sh
cargo xtask bench --no-dashboard -- workloads/my_workload_1.json workloads/my_workload_2.json ..
```
For processing the results, look at [Looking at benchmark results/Without dashboard](#without-dashboard).
### In CI
We have dedicated runners to run workloads on CI. Currently, there are three ways of running the CI:
1. Automatically, on every push to `main`.
2. Manually, by clicking the [`Run workflow`](https://github.com/meilisearch/meilisearch/actions/workflows/bench-manual.yml) button and specifying the target reference (tag, commit or branch) as well as one or multiple workloads to run. The workloads must exist in the Meilisearch repository (conventionally, in the [`workloads`](./workloads/) directory) on the target reference. Globbing (e.g., `workloads/*.json`) works.
3. Manually on a PR, by posting a comment containing a `/bench` command, followed by one or multiple workloads to run. Globbing works. The workloads must exist in the Meilisearch repository in the branch of the PR.
```
/bench workloads/movies*.json /hackernews_1M.json
```
## Looking at benchmark results
### On the dashboard
Results are available on the global dashboard used by CI at <https://bench.meilisearch.dev> or on your [local dashboard](#with-a-local-benchmark-dashboard).
The dashboard homepage presents three sections:
1. The latest invocations (a call to `cargo xtask bench`, either local or by CI) with their reason (generally set to some helpful link in CI) and their status.
2. The latest workloads ran on `main`.
3. The latest workloads ran on other references.
By default, the workload shows the total runtime delta with the latest applicable commit on `main`. The latest applicable commit is the latest commit for workload invocations that do not originate on `main`, and the latest previous commit for workload invocations that originate on `main`.
You can explicitly request a detailed comparison by span with the `main` branch, the branch or origin, or any previous commit, by clicking the links at the bottom of the workload invocation.
In the detailed comparison view, the spans are sorted by improvements, regressions, stable (no statistically significant change) and unstable (the span runtime is comparable to its standard deviation).
You can click on the name of any span to get a box plot comparing the target commit with multiple commits of the selected branch.
### Without dashboard
After the workloads are done running, the reports will live in the Meilisearch repository, in the `bench/reports` directory (by default).
You can then convert these reports into other formats.
- To [Firefox profiler](https://profiler.firefox.com) format. Run:
```sh
cd bench/reports
cargo run --release --bin trace-to-firefox -- my_workload_1-0-trace.json
```
You can then upload the resulting `firefox-my_workload_1-0-trace.json` file to the online profiler.
## Designing benchmark workloads
Benchmark workloads conventionally live in the `workloads` directory of the Meilisearch repository.
They are JSON files with the following structure (comments are not actually supported, to make your own, remove them or copy some existing workload file):
```jsonc
{
// Name of the workload. Must be unique to the workload, as it will be used to group results on the dashboard.
"name": "hackernews.ndjson_1M,no-threads",
// Number of consecutive runs of the commands that should be performed.
// Each run uses a fresh instance of Meilisearch and a fresh database.
// Each run produces its own report file.
"run_count": 3,
// List of arguments to add to the Meilisearch command line.
"extra_cli_args": ["--max-indexing-threads=1"],
// An expression that can be parsed as a comma-separated list of targets and levels
// as described in [tracing_subscriber's documentation](https://docs.rs/tracing-subscriber/latest/tracing_subscriber/filter/targets/struct.Targets.html#examples).
// The expression is used to filter the spans that are measured for profiling purposes.
// Optional, defaults to "indexing::=trace" (for indexing workloads), common other values is
// "search::=trace"
"target": "indexing::=trace",
// List of named assets that can be used in the commands.
"assets": {
// name of the asset.
// Must be unique at the workload level.
// For better results, the same asset (same sha256) should have the same name accross workloads.
// Having multiple assets with the same name and distinct hashes is supported accross workloads,
// but will lead to superfluous downloads.
//
// Assets are stored in the `bench/assets/` directory by default.
"hackernews-100_000.ndjson": {
// If the assets exists in the local filesystem (Meilisearch repository or for your local workloads)
// Its file path can be specified here.
// `null` if the asset should be downloaded from a remote location.
"local_location": null,
// URL of the remote location where the asset can be downloaded.
// Use the `--assets-key` of the runner to pass an API key in the `Authorization: Bearer` header of the download requests.
// `null` if the asset should be imported from a local location.
// if both local and remote locations are specified, then the local one is tried first, then the remote one
// if the file is locally missing or its hash differs.
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-100_000.ndjson",
// SHA256 of the asset.
// Optional, the `sha256` of the asset will be displayed during a run of the workload if it is missing.
// If present, the hash of the asset in the `bench/assets/` directory will be compared against this hash before
// running the workload. If the hashes differ, the asset will be downloaded anew.
"sha256": "60ecd23485d560edbd90d9ca31f0e6dba1455422f2a44e402600fbb5f7f1b213",
// Optional, one of "Auto", "Json", "NdJson" or "Raw".
// If missing, assumed to be "Auto".
// If "Auto", the format will be determined from the extension in the asset name.
"format": "NdJson"
},
"hackernews-200_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-200_000.ndjson",
"sha256": "785b0271fdb47cba574fab617d5d332276b835c05dd86e4a95251cf7892a1685"
},
"hackernews-300_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-300_000.ndjson",
"sha256": "de73c7154652eddfaf69cdc3b2f824d5c452f095f40a20a1c97bb1b5c4d80ab2"
},
"hackernews-400_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-400_000.ndjson",
"sha256": "c1b00a24689110f366447e434c201c086d6f456d54ed1c4995894102794d8fe7"
},
"hackernews-500_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-500_000.ndjson",
"sha256": "ae98f9dbef8193d750e3e2dbb6a91648941a1edca5f6e82c143e7996f4840083"
},
"hackernews-600_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-600_000.ndjson",
"sha256": "b495fdc72c4a944801f786400f22076ab99186bee9699f67cbab2f21f5b74dbe"
},
"hackernews-700_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-700_000.ndjson",
"sha256": "4b2c63974f3dabaa4954e3d4598b48324d03c522321ac05b0d583f36cb78a28b"
},
"hackernews-800_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-800_000.ndjson",
"sha256": "cb7b6afe0e6caa1be111be256821bc63b0771b2a0e1fad95af7aaeeffd7ba546"
},
"hackernews-900_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-900_000.ndjson",
"sha256": "e1154ddcd398f1c867758a93db5bcb21a07b9e55530c188a2917fdef332d3ba9"
},
"hackernews-1_000_000.ndjson": {
"local_location": null,
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-1_000_000.ndjson",
"sha256": "27e25efd0b68b159b8b21350d9af76938710cb29ce0393fa71b41c4f3c630ffe"
}
},
// Core of the workload.
// A list of commands to run sequentially.
// Optional: A precommand is a request to the Meilisearch instance that is executed before the profiling runs.
"precommands": [
{
// Meilisearch route to call. `http://localhost:7700/` will be prepended.
"route": "indexes/movies/settings",
// HTTP method to call.
"method": "PATCH",
// If applicable, body of the request.
// Optional, if missing, the body will be empty.
"body": {
// One of "empty", "inline" or "asset".
// If using "empty", you can skip the entire "body" key.
"inline": {
// when "inline" is used, the body is the JSON object that is the value of the `"inline"` key.
"displayedAttributes": [
"title",
"by",
"score",
"time"
],
"searchableAttributes": [
"title"
],
"filterableAttributes": [
"by"
],
"sortableAttributes": [
"score",
"time"
]
}
},
// Whether to wait before running the next request.
// One of:
// - DontWait: run the next command without waiting the response to this one.
// - WaitForResponse: run the next command as soon as the response from the server is received.
// - WaitForTask: run the next command once **all** the Meilisearch tasks created up to now have finished processing.
"synchronous": "WaitForTask"
}
],
// A command is a request to the Meilisearch instance that is executed while the profiling runs.
"commands": [
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
// When using "asset", use the name of an asset as value to use the content of that asset as body.
// the content type is derived of the format of the asset:
// "NdJson" => "application/x-ndjson"
// "Json" => "application/json"
// "Raw" => "application/octet-stream"
// See [AssetFormat::to_content_type](https://github.com/meilisearch/meilisearch/blob/7b670a4afadb132ac4a01b6403108700501a391d/xtask/src/bench/assets.rs#L30)
// for details and up-to-date list.
"asset": "hackernews-100_000.ndjson"
},
"synchronous": "WaitForTask"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-200_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-300_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-400_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-500_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-600_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-700_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-800_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-900_000.ndjson"
},
"synchronous": "WaitForResponse"
},
{
"route": "indexes/movies/documents",
"method": "POST",
"body": {
"asset": "hackernews-1_000_000.ndjson"
},
"synchronous": "WaitForTask"
}
]
}
```
### Adding new assets
Assets reside in our DigitalOcean S3 space. Assuming you have team access to the DigitalOcean S3 space:
1. go to <https://cloud.digitalocean.com/spaces/milli-benchmarks?i=d1c552&path=bench%2Fdatasets%2F>
2. upload your dataset:
1. if your dataset is a single file, upload that single file using the "upload" button,
2. otherwise, create a folder using the "create folder" button, then inside that folder upload your individual files.
## Upgrading `https://bench.meilisearch.dev`
The URL of the server is in our password manager (look for "benchboard").
1. Make the needed modifications on the [benchboard repository](https://github.com/meilisearch/benchboard) and merge them to main.
2. Publish a new release to produce the Ubuntu/Debian binary.
3. Download the binary locally, send it to the server:
```
scp -6 ~/Downloads/benchboard root@\[<ipv6-address>\]:/bench/new-benchboard
```
Note that the ipv6 must be between escaped square brackets for SCP.
4. SSH to the server:
```
ssh root@<ipv6-address>
```
Note the ipv6 must **NOT** be between escaped square brackets for SSH 🥲
5. On the server, set the correct permissions for the new binary:
```
chown bench:bench /bench/new-benchboard
chmod 700 /bench/new-benchboard
```
6. On the server, move the new binary to the location of the running binary (if unsure, start by making a backup of the running binary):
```
mv /bench/{new-,}benchboard
```
7. Restart the benchboard service.
```
systemctl restart benchboard
```
8. Check that the service runs correctly.
```
systemctl status benchboard
```
9. Check the availability of the service by going to <https://bench.meilisearch.dev> on your browser.

View File

@@ -4,7 +4,7 @@ First, thank you for contributing to Meilisearch! The goal of this document is t
Remember that there are many ways to contribute other than writing code: writing [tutorials or blog posts](https://github.com/meilisearch/awesome-meilisearch), improving [the documentation](https://github.com/meilisearch/documentation), submitting [bug reports](https://github.com/meilisearch/meilisearch/issues/new?assignees=&labels=&template=bug_report.md&title=) and [feature requests](https://github.com/meilisearch/product/discussions/categories/feedback-feature-proposal)...
Meilisearch can manage multiple indexes, handle the update store, and expose an HTTP API. Search and indexation are the domain of our core engine, [`milli`](https://github.com/meilisearch/meilisearch/tree/main/milli), while tokenization is handled by [our `charabia` library](https://github.com/meilisearch/charabia/).
The code in this repository is only concerned with managing multiple indexes, handling the update store, and exposing an HTTP API. Search and indexation are the domain of our core engine, [`milli`](https://github.com/meilisearch/milli), while tokenization is handled by [our `charabia` library](https://github.com/meilisearch/charabia/).
If Meilisearch does not offer optimized support for your language, please consider contributing to `charabia` by following the [CONTRIBUTING.md file](https://github.com/meilisearch/charabia/blob/main/CONTRIBUTING.md) and integrating your intended normalizer/segmenter.
@@ -52,16 +52,6 @@ cargo test
This command will be triggered to each PR as a requirement for merging it.
#### Faster build
You can set the `LINDERA_CACHE` environment variable to speed up your successive builds by up to 2 minutes.
It'll store some built artifacts in the directory of your choice.
We recommend using the standard `$HOME/.cache/lindera` directory:
```sh
export LINDERA_CACHE=$HOME/.cache/lindera
```
#### Snapshot-based tests
We are using [insta](https://insta.rs) to perform snapshot-based testing.
@@ -73,7 +63,7 @@ Furthermore, we provide some macros on top of insta, notably a way to use snapsh
To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally:
```sh
```
export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ...
```
@@ -91,30 +81,6 @@ Meilisearch follows the [cargo xtask](https://github.com/matklad/cargo-xtask) wo
Run `cargo xtask --help` from the root of the repository to find out what is available.
### Logging
Meilisearch uses [`tracing`](https://lib.rs/crates/tracing) for logging purposes. Tracing logs are structured and can be displayed as JSON to the end user, so prefer passing arguments as fields rather than interpolating them in the message.
Refer to the [documentation](https://docs.rs/tracing/0.1.40/tracing/index.html#using-the-macros) for the syntax of the spans and events.
Logging spans are used for 3 distinct purposes:
1. Regular logging
2. Profiling
3. Benchmarking
As a result, the spans should follow some rules:
- They should not be put on functions that are called too often. That is because opening and closing a span causes some overhead. For regular logging, avoid putting spans on functions that are taking less than a few hundred nanoseconds. For profiling or benchmarking, avoid putting spans on functions that are taking less than a few microseconds.
- For profiling and benchmarking, use the `TRACE` level.
- For profiling and benchmarking, use the following `target` prefixes:
- `indexing::` for spans meant when profiling the indexing operations.
- `search::` for spans meant when profiling the search operations.
### Benchmarking
See [BENCHMARKS.md](./BENCHMARKS.md)
## Git Guidelines
### Git Branches

3110
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -18,11 +18,10 @@ members = [
"fuzzers",
"tracing-trace",
"xtask",
"build-info",
]
[workspace.package]
version = "1.9.0"
version = "1.6.0"
authors = [
"Quentin de Quelen <quentin@dequelen.me>",
"Clément Renault <clement@meilisearch.com>",

View File

@@ -1,14 +1,14 @@
# Compile
FROM rust:1.79.0-alpine3.20 AS compiler
FROM rust:1.75.0-alpine3.18 AS compiler
RUN apk add -q --no-cache build-base openssl-dev
RUN apk add -q --update-cache --no-cache build-base openssl-dev
WORKDIR /
ARG COMMIT_SHA
ARG COMMIT_DATE
ARG GIT_TAG
ENV VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_DESCRIBE=${GIT_TAG}
ENV VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
ENV RUSTFLAGS="-C target-feature=-crt-static"
COPY . .
@@ -20,12 +20,13 @@ RUN set -eux; \
cargo build --release -p meilisearch -p meilitool
# Run
FROM alpine:3.20
FROM alpine:3.16
ENV MEILI_HTTP_ADDR 0.0.0.0:7700
ENV MEILI_SERVER_PROVIDER docker
RUN apk add -q --no-cache libgcc tini curl
RUN apk update --quiet \
&& apk add -q --no-cache libgcc tini curl
# add meilisearch and meilitool to the `/bin` so you can run it from anywhere
# and it's easy to find.

View File

@@ -1,6 +1,9 @@
<p align="center">
<a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo" target="_blank">
<img src="assets/meilisearch-logo-kawaii.png">
<a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-light-mode-only" target="_blank">
<img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
</a>
<a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-dark-mode-only" target="_blank">
<img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
</a>
</p>
@@ -22,7 +25,7 @@
<p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
[Meilisearch](https://www.meilisearch.com?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=intro) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
<p align="center" name="demo">
<a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
@@ -33,22 +36,15 @@
</a>
</p>
## 🖥 Examples
- [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
- [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
- [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
See the list of all our example apps in our [demos repository](https://github.com/meilisearch/demos).
🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
## ✨ Features
- **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) & full-text search to get the most relevant results
- **Search-as-you-type:** Find & display results in less than 50 milliseconds to provide an intuitive experience
- **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
- **Search-as-you-type:** find search results in less than 50 milliseconds
- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
- **[Synonym support](https://www.meilisearch.com/docs/learn/configuration/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#synonyms):** configure synonyms to include more relevant content in your search results
- **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
- **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
- **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
@@ -59,15 +55,17 @@ See the list of all our example apps in our [demos repository](https://github.co
## 📖 Documentation
You can consult Meilisearch's documentation at [meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
## 🚀 Getting started
For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [documentation](https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
## 🌍 Supercharge your Meilisearch experience
You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) for an introduction to some of Meilisearch's most popular features.
Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). Additional features include analytics & monitoring in many regions around the world. No credit card is required.
## ⚡ Supercharge your Meilisearch experience
Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). No credit card required.
## 🧰 SDKs & integration tools
@@ -87,15 +85,15 @@ Finally, for more in-depth information, refer to our articles explaining fundame
## 📊 Telemetry
Meilisearch collects **anonymized** user data to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) of our documentation.
## 📫 Get in touch!
Meilisearch is a search engine created by [Meili]([https://www.welcometothejungle.com/en/companies/meilisearch](https://www.meilisearch.com/careers)), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
@@ -103,17 +101,17 @@ Meilisearch is a search engine created by [Meili]([https://www.welcometothejungl
- For feature requests, please visit our [product repository](https://github.com/meilisearch/product/discussions)
- Found a bug? Open an [issue](https://github.com/meilisearch/meilisearch/issues)!
- Want to be part of our Discord community? [Join us!](https://discord.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
- Want to be part of our Discord community? [Join us!](https://discord.gg/meilisearch)
Thank you for your support!
## 👩‍💻 Contributing
Meilisearch is, and will always be, open-source! If you want to contribute to the project, please look at [our contribution guidelines](CONTRIBUTING.md).
Meilisearch is, and will always be, open-source! If you want to contribute to the project, please take a look at [our contribution guidelines](CONTRIBUTING.md).
## 📦 Versioning
Meilisearch releases and their associated binaries are available on the project's [releases page](https://github.com/meilisearch/meilisearch/releases).
Meilisearch releases and their associated binaries are available [in this GitHub page](https://github.com/meilisearch/meilisearch/releases).
The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](https://github.com/meilisearch/engine-team/blob/main/resources/versioning-policy.md).

File diff suppressed because it is too large Load Diff

Binary file not shown.

Before

Width:  |  Height:  |  Size: 98 KiB

View File

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

View File

@@ -1,18 +0,0 @@
[package]
name = "build-info"
version.workspace = true
authors.workspace = true
description.workspace = true
homepage.workspace = true
readme.workspace = true
edition.workspace = true
license.workspace = true
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
time = { version = "0.3.36", features = ["parsing"] }
[build-dependencies]
anyhow = "1.0.86"
vergen-git2 = "1.0.0"

View File

@@ -1,22 +0,0 @@
fn main() {
if let Err(err) = emit_git_variables() {
println!("cargo:warning=vergen: {}", err);
}
}
fn emit_git_variables() -> anyhow::Result<()> {
// Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
// in the corresponding GitHub workflow (publish_docker.yml).
// This is due to the Dockerfile building the binary outside of the git directory.
let mut builder = vergen_git2::Git2Builder::default();
builder.branch(true);
builder.commit_timestamp(true);
builder.commit_message(true);
builder.describe(true, true, None);
builder.sha(false);
let git2 = builder.build()?;
vergen_git2::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
}

View File

@@ -1,203 +0,0 @@
use time::format_description::well_known::Iso8601;
#[derive(Debug, Clone)]
pub struct BuildInfo {
pub branch: Option<&'static str>,
pub describe: Option<DescribeResult>,
pub commit_sha1: Option<&'static str>,
pub commit_msg: Option<&'static str>,
pub commit_timestamp: Option<time::OffsetDateTime>,
}
impl BuildInfo {
pub fn from_build() -> Self {
let branch: Option<&'static str> = option_env!("VERGEN_GIT_BRANCH");
let describe = DescribeResult::from_build();
let commit_sha1 = option_env!("VERGEN_GIT_SHA");
let commit_msg = option_env!("VERGEN_GIT_COMMIT_MESSAGE");
let commit_timestamp = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP");
let commit_timestamp = commit_timestamp.and_then(|commit_timestamp| {
time::OffsetDateTime::parse(commit_timestamp, &Iso8601::DEFAULT).ok()
});
Self { branch, describe, commit_sha1, commit_msg, commit_timestamp }
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub enum DescribeResult {
Prototype { name: &'static str },
Release { version: &'static str, major: u64, minor: u64, patch: u64 },
Prerelease { version: &'static str, major: u64, minor: u64, patch: u64, rc: u64 },
NotATag { describe: &'static str },
}
impl DescribeResult {
pub fn new(describe: &'static str) -> Self {
if let Some(name) = prototype_name(describe) {
Self::Prototype { name }
} else if let Some(release) = release_version(describe) {
release
} else if let Some(prerelease) = prerelease_version(describe) {
prerelease
} else {
Self::NotATag { describe }
}
}
pub fn from_build() -> Option<Self> {
let describe: &'static str = option_env!("VERGEN_GIT_DESCRIBE")?;
Some(Self::new(describe))
}
pub fn as_tag(&self) -> Option<&'static str> {
match self {
DescribeResult::Prototype { name } => Some(name),
DescribeResult::Release { version, .. } => Some(version),
DescribeResult::Prerelease { version, .. } => Some(version),
DescribeResult::NotATag { describe: _ } => None,
}
}
pub fn as_prototype(&self) -> Option<&'static str> {
match self {
DescribeResult::Prototype { name } => Some(name),
DescribeResult::Release { .. }
| DescribeResult::Prerelease { .. }
| DescribeResult::NotATag { .. } => None,
}
}
}
/// Parses the input as a prototype name.
///
/// Returns `Some(prototype_name)` if the following conditions are met on this value:
///
/// 1. starts with `prototype-`,
/// 2. ends with `-<some_number>`,
/// 3. does not end with `<some_number>-<some_number>`.
///
/// Otherwise, returns `None`.
fn prototype_name(describe: &'static str) -> Option<&'static str> {
if !describe.starts_with("prototype-") {
return None;
}
let mut rsplit_prototype = describe.rsplit('-');
// last component MUST be a number
rsplit_prototype.next()?.parse::<u64>().ok()?;
// before than last component SHALL NOT be a number
rsplit_prototype.next()?.parse::<u64>().err()?;
Some(describe)
}
fn release_version(describe: &'static str) -> Option<DescribeResult> {
if !describe.starts_with('v') {
return None;
}
// full release version don't contain a `-`
if describe.contains('-') {
return None;
}
// full release version parse as vX.Y.Z, with X, Y, Z numbers.
let mut dots = describe[1..].split('.');
let major: u64 = dots.next()?.parse().ok()?;
let minor: u64 = dots.next()?.parse().ok()?;
let patch: u64 = dots.next()?.parse().ok()?;
if dots.next().is_some() {
return None;
}
Some(DescribeResult::Release { version: describe, major, minor, patch })
}
fn prerelease_version(describe: &'static str) -> Option<DescribeResult> {
// prerelease version is in the shape vM.N.P-rc.C
let mut hyphen = describe.rsplit('-');
let prerelease = hyphen.next()?;
if !prerelease.starts_with("rc.") {
return None;
}
let rc: u64 = prerelease[3..].parse().ok()?;
let release = hyphen.next()?;
let DescribeResult::Release { version: _, major, minor, patch } = release_version(release)?
else {
return None;
};
Some(DescribeResult::Prerelease { version: describe, major, minor, patch, rc })
}
#[cfg(test)]
mod test {
use super::DescribeResult;
fn assert_not_a_tag(describe: &'static str) {
assert_eq!(DescribeResult::NotATag { describe }, DescribeResult::new(describe))
}
fn assert_proto(describe: &'static str) {
assert_eq!(DescribeResult::Prototype { name: describe }, DescribeResult::new(describe))
}
fn assert_release(describe: &'static str, major: u64, minor: u64, patch: u64) {
assert_eq!(
DescribeResult::Release { version: describe, major, minor, patch },
DescribeResult::new(describe)
)
}
fn assert_prerelease(describe: &'static str, major: u64, minor: u64, patch: u64, rc: u64) {
assert_eq!(
DescribeResult::Prerelease { version: describe, major, minor, patch, rc },
DescribeResult::new(describe)
)
}
#[test]
fn not_a_tag() {
assert_not_a_tag("whatever-fuzzy");
assert_not_a_tag("whatever-fuzzy-5-ggg-dirty");
assert_not_a_tag("whatever-fuzzy-120-ggg-dirty");
// technically a tag, but not a proto nor a version, so not parsed as a tag
assert_not_a_tag("whatever");
// dirty version
assert_not_a_tag("v1.7.0-1-ggga-dirty");
assert_not_a_tag("v1.7.0-rc.1-1-ggga-dirty");
// after version
assert_not_a_tag("v1.7.0-1-ggga");
assert_not_a_tag("v1.7.0-rc.1-1-ggga");
// after proto
assert_not_a_tag("protoype-tag-0-1-ggga");
assert_not_a_tag("protoype-tag-0-1-ggga-dirty");
}
#[test]
fn prototype() {
assert_proto("prototype-tag-0");
assert_proto("prototype-tag-10");
assert_proto("prototype-long-name-tag-10");
}
#[test]
fn release() {
assert_release("v1.7.2", 1, 7, 2);
}
#[test]
fn prerelease() {
assert_prerelease("v1.7.2-rc.3", 1, 7, 2, 3);
}
}

View File

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

View File

@@ -256,8 +256,8 @@ pub(crate) mod test {
pub fn create_test_settings() -> Settings<Checked> {
let settings = Settings {
displayed_attributes: Setting::Set(vec![S("race"), S("name")]).into(),
searchable_attributes: Setting::Set(vec![S("name"), S("race")]).into(),
displayed_attributes: Setting::Set(vec![S("race"), S("name")]),
searchable_attributes: Setting::Set(vec![S("name"), S("race")]),
filterable_attributes: Setting::Set(btreeset! { S("race"), S("age") }),
sortable_attributes: Setting::Set(btreeset! { S("age") }),
ranking_rules: Setting::NotSet,
@@ -277,7 +277,6 @@ pub(crate) mod test {
}),
pagination: Setting::NotSet,
embedders: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
_kind: std::marker::PhantomData,
};
settings.check()

View File

@@ -1,3 +1,4 @@
use std::convert::TryInto;
use std::str::FromStr;
use time::OffsetDateTime;
@@ -425,7 +426,7 @@ pub(crate) mod test {
let mut dump = v2::V2Reader::open(dir).unwrap().to_v3();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
// tasks
let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

View File

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

View File

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

View File

@@ -315,8 +315,8 @@ impl From<v5::ResponseError> for v6::ResponseError {
impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
fn from(settings: v5::Settings<T>) -> Self {
v6::Settings {
displayed_attributes: v6::Setting::from(settings.displayed_attributes).into(),
searchable_attributes: v6::Setting::from(settings.searchable_attributes).into(),
displayed_attributes: settings.displayed_attributes.into(),
searchable_attributes: settings.searchable_attributes.into(),
filterable_attributes: settings.filterable_attributes.into(),
sortable_attributes: settings.sortable_attributes.into(),
ranking_rules: {
@@ -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,
search_cutoff_ms: v6::Setting::NotSet,
_kind: std::marker::PhantomData,
}
}
@@ -442,8 +441,8 @@ pub(crate) mod test {
let mut dump = v5::V5Reader::open(dir).unwrap().to_v6();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();

View File

@@ -197,147 +197,13 @@ pub(crate) mod test {
use super::*;
use crate::reader::v6::RuntimeTogglableFeatures;
#[test]
fn import_dump_v6_with_vectors() {
// dump containing two indexes
//
// "vector", configured with an embedder
// contains:
// - one document with an overriden vector,
// - one document with a natural vector
// - one document with a _vectors map containing one additional embedder name and a natural vector
// - one document with a _vectors map containing one additional embedder name and an overriden vector
//
// "novector", no embedder
// contains:
// - a document without vector
// - a document with a random _vectors field
let dump = File::open("tests/assets/v6-with-vectors.dump").unwrap();
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
// tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"278f63325ef06ca04d01df98d8207b94");
assert_eq!(update_files.len(), 10);
assert!(update_files[0].is_none()); // the dump creation
assert!(update_files[1].is_none());
assert!(update_files[2].is_none());
assert!(update_files[3].is_none());
assert!(update_files[4].is_none());
assert!(update_files[5].is_none());
assert!(update_files[6].is_none());
assert!(update_files[7].is_none());
assert!(update_files[8].is_none());
assert!(update_files[9].is_none());
// indexes
let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
// the index are not ordered in any way by default
indexes.sort_by_key(|index| index.metadata().uid.to_string());
let mut vector_index = indexes.pop().unwrap();
let mut novector_index = indexes.pop().unwrap();
assert!(indexes.is_empty());
// vector
insta::assert_json_snapshot!(vector_index.metadata(), @r###"
{
"uid": "vector",
"primaryKey": "id",
"createdAt": "2024-05-16T15:33:17.240962Z",
"updatedAt": "2024-05-16T15:40:55.723052Z"
}
"###);
{
let documents: Result<Vec<_>> = vector_index.documents().unwrap().collect();
let mut documents = documents.unwrap();
assert_eq!(documents.len(), 4);
documents.sort_by_key(|doc| doc.get("id").unwrap().to_string());
{
let document = documents.pop().unwrap();
insta::assert_json_snapshot!(document);
}
{
let document = documents.pop().unwrap();
insta::assert_json_snapshot!(document);
}
{
let document = documents.pop().unwrap();
insta::assert_json_snapshot!(document);
}
{
let document = documents.pop().unwrap();
insta::assert_json_snapshot!(document);
}
}
// novector
insta::assert_json_snapshot!(novector_index.metadata(), @r###"
{
"uid": "novector",
"primaryKey": "id",
"createdAt": "2024-05-16T15:33:03.568055Z",
"updatedAt": "2024-05-16T15:33:07.530217Z"
}
"###);
insta::assert_json_snapshot!(novector_index.settings().unwrap().embedders, @"null");
{
let documents: Result<Vec<_>> = novector_index.documents().unwrap().collect();
let mut documents = documents.unwrap();
assert_eq!(documents.len(), 2);
documents.sort_by_key(|doc| doc.get("id").unwrap().to_string());
{
let document = documents.pop().unwrap();
insta::assert_json_snapshot!(document, @r###"
{
"id": "e1",
"other": "random1",
"_vectors": "toto"
}
"###);
}
{
let document = documents.pop().unwrap();
insta::assert_json_snapshot!(document, @r###"
{
"id": "e0",
"other": "random0"
}
"###);
}
}
assert_eq!(
dump.features().unwrap().unwrap(),
RuntimeTogglableFeatures { vector_store: true, ..Default::default() }
);
}
#[test]
fn import_dump_v6_experimental() {
let dump = File::open("tests/assets/v6-with-experimental.dump").unwrap();
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
// tasks
@@ -383,8 +249,8 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
@@ -463,8 +329,8 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
// tasks
let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
@@ -540,7 +406,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
assert_eq!(dump.instance_uid().unwrap(), None);
// tasks
@@ -633,7 +499,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
assert_eq!(dump.instance_uid().unwrap(), None);
// tasks
@@ -726,7 +592,7 @@ pub(crate) mod test {
let mut dump = DumpReader::open(dump).unwrap();
// top level infos
insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
assert_eq!(dump.instance_uid().unwrap(), None);
// tasks

View File

@@ -1,783 +0,0 @@
---
source: dump/src/reader/mod.rs
expression: document
---
{
"id": "e3",
"desc": "overriden vector + map",
"_vectors": {
"default": [
0.2,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1
],
"toto": [
0.1
]
}
}

View File

@@ -1,786 +0,0 @@
---
source: dump/src/reader/mod.rs
expression: document
---
{
"id": "e2",
"desc": "natural vector + map",
"_vectors": {
"toto": [],
"default": {
"embeddings": [
[
-0.05189208313822746,
-0.9273212552070618,
0.1443813145160675,
0.0932632014155388,
0.2665371894836426,
0.36266782879829407,
0.6402910947799683,
0.32014018297195435,
0.030915971845388412,
-0.9312191605567932,
-0.3718109726905823,
-0.2700554132461548,
-1.1014580726623535,
0.9154956936836244,
-0.3406888246536255,
1.0077725648880005,
0.6577560901641846,
-0.3955195546150207,
-0.4148270785808563,
0.1855088472366333,
0.5062315464019775,
-0.3632686734199524,
-0.2277890294790268,
0.2560805082321167,
-0.3853609561920166,
-0.1604762226343155,
-0.13947471976280212,
-0.20147813856601715,
-0.4466346800327301,
-0.3761846721172333,
0.1443382054567337,
0.18205296993255615,
0.49359792470932007,
-0.22538000345230105,
-0.4996317625045776,
-0.22734887897968292,
-0.6034309267997742,
-0.7857939600944519,
-0.34923747181892395,
-0.3466345965862274,
0.21176661550998688,
-0.5101462006568909,
-0.3403083384037018,
0.000315118464641273,
0.236465722322464,
-0.10246097296476364,
-1.3013339042663574,
0.3419138789176941,
-0.32963496446609497,
-0.0901619717478752,
-0.5426247119903564,
0.22656650841236117,
-0.44758284091949463,
0.14151698350906372,
-0.1089438870549202,
0.5500766634941101,
-0.670711100101471,
-0.6227269768714905,
0.3894464075565338,
-0.27609574794769287,
0.7028202414512634,
-0.19697771966457367,
0.328511506319046,
0.5063360929489136,
0.4065195322036743,
0.2614171802997589,
-0.30274391174316406,
1.0393824577331543,
-0.7742937207221985,
-0.7874112129211426,
-0.6749666929244995,
0.5190866589546204,
0.004123548045754433,
-0.28312963247299194,
-0.038731709122657776,
-1.0142987966537476,
-0.09519586712121964,
0.8755272626876831,
0.4876938760280609,
0.7811151742935181,
0.85174959897995,
0.11826585978269576,
0.5373436808586121,
0.3649002015590668,
0.19064077734947205,
-0.00287026260048151,
-0.7305403351783752,
-0.015206154435873032,
-0.7899249196052551,
0.19407285749912265,
0.08596625179052353,
-0.28976231813430786,
-0.1525907665491104,
0.3798313438892365,
0.050306469202041626,
-0.5697937607765198,
0.4219021201133728,
0.276252806186676,
0.1559903472661972,
0.10030482709407806,
-0.4043720066547394,
-0.1969818025827408,
0.5739826560020447,
0.2116064727306366,
-1.4620544910430908,
-0.7802462577819824,
-0.24739810824394223,
-0.09791352599859238,
-0.4413802027702331,
0.21549351513385773,
-0.9520436525344848,
-0.08762510865926743,
0.08154498040676117,
-0.6154940724372864,
-1.01079523563385,
0.885427713394165,
0.6967288851737976,
0.27186504006385803,
-0.43194177746772766,
-0.11248451471328735,
0.7576630711555481,
0.4998855590820313,
0.0264343973249197,
0.9872855544090272,
0.5634694695472717,
0.053698331117630005,
0.19410227239131927,
0.3570743501186371,
-0.23670297861099243,
-0.9114483594894408,
0.07884842902421951,
0.7318344116210938,
0.44630110263824463,
0.08745364099740982,
-0.347101628780365,
-0.4314247667789459,
-0.5060274004936218,
0.003706763498485088,
0.44320008158683777,
-0.00788921769708395,
-0.1368623524904251,
-0.17391923069953918,
0.14473655819892883,
0.10927865654230118,
0.6974599361419678,
0.005052129738032818,
-0.016953065991401672,
-0.1256176233291626,
-0.036742497235536575,
0.5591985583305359,
-0.37619709968566895,
0.22429119050502777,
0.5403043031692505,
-0.8603790998458862,
-0.3456307053565979,
0.9292937517166138,
0.5074859261512756,
0.6310645937919617,
-0.3091641068458557,
0.46902573108673096,
0.7891915440559387,
0.4499550759792328,
0.2744995653629303,
0.2712305784225464,
-0.04349074140191078,
-0.3638863265514374,
0.7839881777763367,
0.7352104783058167,
-0.19457511603832245,
-0.5957832932472229,
-0.43704694509506226,
-1.084769368171692,
0.4904985725879669,
0.5385226011276245,
0.1891629993915558,
0.12338479608297348,
0.8315675258636475,
-0.07830192148685455,
1.0916285514831543,
-0.28066861629486084,
-1.3585069179534912,
0.5203898549079895,
0.08678033947944641,
-0.2566044330596924,
0.09484415501356123,
-0.0180208683013916,
1.0264745950698853,
-0.023572135716676712,
0.5864979028701782,
0.7625196576118469,
-0.2543414533138275,
-0.8877770900726318,
0.7611982822418213,
-0.06220436468720436,
0.937336564064026,
0.2704363465309143,
-0.37733694911003113,
0.5076137781143188,
-0.30641937255859375,
0.6252772808074951,
-0.0823579877614975,
-0.03736555948853493,
0.4131673276424408,
-0.6514252424240112,
0.12918265163898468,
-0.4483584463596344,
0.6750786304473877,
-0.37008383870124817,
-0.02324833907186985,
0.38027650117874146,
-0.26374951004981995,
0.4346931278705597,
0.42882832884788513,
-0.48798441886901855,
1.1882442235946655,
0.5132288336753845,
0.5284568667411804,
-0.03538886830210686,
0.29620853066444397,
-1.0683696269989014,
0.25936177372932434,
0.10404160618782043,
-0.25796034932136536,
0.027896970510482788,
-0.09225251525640488,
1.4811025857925415,
0.641173779964447,
-0.13838383555412292,
-0.3437179923057556,
0.5667019486427307,
-0.5400741696357727,
0.31090837717056274,
0.6470608115196228,
-0.3747067153453827,
-0.7364534735679626,
-0.07431528717279434,
0.5173454880714417,
-0.6578747034072876,
0.7107478976249695,
-0.7918999791145325,
-0.0648345872759819,
0.609937846660614,
-0.7329513430595398,
0.9741371870040894,
0.17912346124649048,
-0.02658769302070141,
0.5162150859832764,
-0.3978803157806397,
-0.7833885550498962,
-0.6497276425361633,
-0.3898126780986786,
-0.0952848568558693,
0.2663288116455078,
-0.1604052186012268,
0.373076468706131,
-0.8357769250869751,
-0.05217683315277099,
-0.2680160701274872,
0.8389158248901367,
0.6833611130714417,
-0.6712407469749451,
0.7406917214393616,
-0.44522786140441895,
-0.34645363688468933,
-0.27384576201438904,
-0.9878405928611756,
-0.8166060447692871,
0.06268279999494553,
0.38567957282066345,
-0.3274703919887543,
0.5296315550804138,
-0.11810623109340668,
0.23029841482639313,
0.08616159111261368,
-0.2195747196674347,
0.09430307894945145,
0.4057176411151886,
0.4892159104347229,
-0.1636916548013687,
-0.6071445345878601,
0.41256585717201233,
0.622254490852356,
-0.41223976016044617,
-0.6686707139015198,
-0.7474371790885925,
-0.8509522080421448,
-0.16754287481307983,
-0.9078601002693176,
-0.29653599858283997,
-0.5020652413368225,
0.4692700505256653,
0.01281109917908907,
-0.16071580350399017,
0.03388889133930206,
-0.020511148497462273,
0.5027827024459839,
-0.20729811489582065,
0.48107290267944336,
0.33669769763946533,
-0.5275911688804626,
0.48271527886390686,
0.2738940715789795,
-0.033152539283037186,
-0.13629786670207977,
-0.05965912342071533,
-0.26200807094573975,
0.04002794995903969,
-0.34095603227615356,
-3.986898899078369,
-0.46819332242012024,
-0.422744482755661,
-0.169097900390625,
0.6008929014205933,
0.058016058057546616,
-0.11401277780532836,
-0.3077819049358368,
-0.09595538675785063,
0.6723822355270386,
0.19367831945419312,
0.28304359316825867,
0.1609862744808197,
0.7567598819732666,
0.6889985799789429,
0.06907720118761063,
-0.04188092052936554,
-0.7434936165809631,
0.13321782648563385,
0.8456063270568848,
-0.10364038497209548,
-0.45084846019744873,
-0.4758241474628449,
0.43882066011428833,
-0.6432598829269409,
0.7217311859130859,
-0.24189773201942444,
0.12737572193145752,
-1.1008601188659668,
-0.3305315673351288,
0.14614742994308472,
-0.7819333076477051,
0.5287120342254639,
-0.055538054555654526,
0.1877404749393463,
-0.6907662153244019,
0.5616975426673889,
-0.4611121714115143,
-0.26109233498573303,
-0.12898315489292145,
-0.3724522292613983,
-0.7191406488418579,
-0.4425233602523804,
-0.644108235836029,
0.8424481153488159,
0.17532426118850708,
-0.5121750235557556,
-0.6467239260673523,
-0.0008507720194756985,
0.7866212129592896,
-0.02644744887948036,
-0.005045140627771616,
0.015782782807946205,
0.16334445774555206,
-0.1913367658853531,
-0.13697923719882965,
-0.6684983372688293,
0.18346354365348816,
-0.341105580329895,
0.5427411198616028,
0.3779832422733307,
-0.6778115034103394,
-0.2931850254535675,
-0.8805161714553833,
-0.4212774932384491,
-0.5368952751159668,
-1.3937891721725464,
-1.225494146347046,
0.4276703894138336,
1.1205668449401855,
-0.6005299687385559,
0.15732505917549133,
-0.3914784789085388,
-1.357046604156494,
-0.4707142114639282,
-0.1497287154197693,
-0.25035548210144043,
-0.34328439831733704,
0.39083412289619446,
0.1623048633337021,
-0.9275814294815063,
-0.6430015563964844,
0.2973862886428833,
0.5580436587333679,
-0.6232585310935974,
-0.6611042022705078,
0.4015969038009643,
-1.0232892036437988,
-0.2585645020008087,
-0.5431421399116516,
0.5021264553070068,
-0.48601630330085754,
-0.010242084041237833,
0.5862035155296326,
0.7316920161247253,
0.4036808013916016,
0.4269520044326782,
-0.705938458442688,
0.7747307419776917,
0.10164368897676468,
0.7887958884239197,
-0.9612497091293336,
0.12755516171455383,
0.06812842190265656,
-0.022603651508688927,
0.14722754061222076,
-0.5588505268096924,
-0.20689940452575684,
0.3557641804218292,
-0.6812759637832642,
0.2860803008079529,
-0.38954633474349976,
0.1759403496980667,
-0.5678874850273132,
-0.1692986786365509,
-0.14578519761562347,
0.5711379051208496,
1.0208125114440918,
0.7759483456611633,
-0.372348427772522,
-0.5460885763168335,
0.7190321683883667,
-0.6914990544319153,
0.13365162909030914,
-0.4854792356491089,
0.4054908752441406,
0.4502798914909363,
-0.3041122555732727,
-0.06726965308189392,
-0.05570871382951737,
-0.0455719493329525,
0.4785125255584717,
0.8867972493171692,
0.4107886850833893,
0.6121342182159424,
-0.20477132499217987,
-0.5598517656326294,
-0.6443566679954529,
-0.5905212759971619,
-0.5571200251579285,
0.17573799192905426,
-0.28621870279312134,
0.1685224026441574,
0.09719007462263109,
-0.04223639518022537,
-0.28623101115226746,
-0.1449810117483139,
-0.3789580464363098,
-0.5227636098861694,
-0.049728814512491226,
0.7849089503288269,
0.16792525351047516,
0.9849340915679932,
-0.6559549570083618,
0.35723909735679626,
-0.6822739243507385,
1.2873116731643677,
0.19993330538272855,
0.03512010723352432,
-0.6972134113311768,
0.18453484773635864,
-0.2437680810689926,
0.2156416028738022,
0.5230382680892944,
0.22020135819911957,
0.8314080238342285,
0.15627102553844452,
-0.7330264449119568,
0.3888184726238251,
-0.22034703195095065,
0.5457669496536255,
-0.48084837198257446,
-0.45576658844947815,
-0.09287727624177931,
-0.06968110054731369,
0.35125672817230225,
-0.4278119504451752,
0.2038476765155792,
0.11392722278833388,
0.9433983564376832,
-0.4097744226455689,
0.035297419875860214,
-0.4274404048919678,
-0.25100165605545044,
1.0943366289138794,
-0.07634022831916809,
-0.2925529479980469,
-0.7512530088424683,
0.2649727463722229,
-0.4078235328197479,
-0.3372223973274231,
0.05190162733197212,
0.005654910113662481,
-0.0001571219472680241,
-0.35445958375930786,
-0.7837416529655457,
0.1500556766986847,
0.4383024573326111,
0.6099548935890198,
0.05951934307813645,
-0.21325334906578064,
0.0199207104742527,
-0.22704418003559113,
-0.6481077671051025,
0.37442275881767273,
-1.015955924987793,
0.38637226819992065,
-0.06489371508359909,
-0.494120329618454,
0.3469836115837097,
0.15402406454086304,
-0.7660972476005554,
-0.7053225040435791,
-0.25964751839637756,
0.014004424214363098,
-0.2860170006752014,
-0.17565494775772095,
-0.45117494463920593,
-0.0031954257283359766,
0.09676837921142578,
-0.514464259147644,
0.41698193550109863,
-0.21642713248729703,
-0.5398141145706177,
-0.3647628426551819,
0.37005379796028137,
0.239425927400589,
-0.08833975344896317,
0.934946596622467,
-0.48340797424316406,
0.6241437792778015,
-0.7253676652908325,
-0.04303571209311485,
1.1125205755233765,
-0.15692919492721558,
-0.2914651036262512,
-0.5117168426513672,
0.21365483105182648,
0.4924402534961701,
0.5269662141799927,
0.0352792888879776,
-0.149167999625206,
-0.6019760370254517,
0.08245442807674408,
0.4900692105293274,
0.518824577331543,
-0.00005570516441366635,
-0.553304135799408,
0.22217543423175812,
0.5047767758369446,
0.135724738240242,
1.1511540412902832,
-0.3541218340396881,
-0.9712511897087096,
0.8353699445724487,
-0.39227569103240967,
-0.9117669463157654,
-0.26349931955337524,
0.05597023293375969,
0.20695461332798004,
0.3178807199001312,
1.0663238763809204,
0.5062212347984314,
0.7288597822189331,
0.09899299591779707,
0.553720235824585,
0.675009548664093,
-0.20067055523395536,
0.3138423264026642,
-0.6886593103408813,
-0.2910398542881012,
-1.3186300992965698,
-0.4684459865093231,
-0.095743365585804,
-0.1257995069026947,
-0.4858281314373016,
-0.4935407340526581,
-0.3266896903514862,
-0.3928797245025635,
-0.40803104639053345,
-0.9975396394729614,
0.4229583740234375,
0.37309643626213074,
0.4431034922599793,
0.30364808440208435,
-0.3765178918838501,
0.5616499185562134,
0.16904796659946442,
-0.7343707084655762,
0.2560209631919861,
0.6166825294494629,
0.3200829327106476,
-0.4483652710914612,
0.16224201023578644,
-0.31495288014411926,
-0.42713335156440735,
0.7270734906196594,
0.7049484848976135,
-0.0571461021900177,
0.04477125033736229,
-0.6647796034812927,
1.183672308921814,
0.36199676990509033,
0.046881116926670074,
0.4515796303749085,
0.9278061985969543,
0.31471705436706543,
-0.7073333859443665,
-0.3443860113620758,
0.5440067052841187,
-0.15020819008350372,
-0.541202962398529,
0.5203295946121216,
1.2192286252975464,
-0.9983593225479126,
-0.18758884072303772,
0.2758221924304962,
-0.6511523723602295,
-0.1584404855966568,
-0.236241415143013,
0.2692437767982483,
-0.4941152036190033,
0.4987454116344452,
-0.3331359028816223,
0.3163745701313019,
0.745529294013977,
-0.2905873656272888,
0.13602906465530396,
0.4679684340953827,
1.0555986166000366,
1.075700044631958,
0.5368486046791077,
-0.5118206739425659,
0.8668332099914551,
-0.5726966857910156,
-0.7811751961708069,
0.1938626915216446,
-0.1929349899291992,
0.1757766306400299,
0.6384295225143433,
0.26462844014167786,
0.9542630314826964,
0.19313029944896695,
1.264248013496399,
-0.6304428577423096,
0.0487106591463089,
-0.16211535036563873,
-0.7894763350486755,
0.3582514822483063,
-0.04153040423989296,
0.635784387588501,
0.6554391980171204,
-0.47010496258735657,
-0.8302040696144104,
-0.1350124627351761,
0.2568812072277069,
0.13614831864833832,
-0.2563649117946625,
-1.0434694290161133,
0.3232482671737671,
0.47882452607154846,
0.4298652410507202,
1.0563770532608032,
-0.28917592763900757,
-0.8533256649971008,
0.10648339986801147,
0.6376127004623413,
-0.20832888782024384,
0.2370245456695557,
0.0018312990432605147,
-0.2034837007522583,
0.01051164511591196,
-1.105310082435608,
0.29724350571632385,
0.15604574978351593,
0.1973688006401062,
0.44394731521606445,
0.3974513411521912,
-0.13625948131084442,
0.9571986198425292,
0.2257384955883026,
0.2323588728904724,
-0.5583669543266296,
-0.7854922413825989,
0.1647188365459442,
-1.6098142862319946,
0.318587988615036,
-0.13399995863437653,
-0.2172701060771942,
-0.767514705657959,
-0.5813586711883545,
-0.3195130527019501,
-0.04894036799669266,
0.2929930090904236,
-0.8213384747505188,
0.07181350141763687,
0.7469993829727173,
0.6407455801963806,
0.16365697979927063,
0.7870153188705444,
0.6524736881256104,
0.6399973630905151,
-0.04992736503481865,
-0.03959266096353531,
-0.2512352466583252,
0.8448855876922607,
-0.1422702670097351,
0.1216789186000824,
-1.2647287845611572,
0.5931149125099182,
0.7186052203178406,
-0.06118432432413101,
-1.1942816972732544,
-0.17677085101604462,
0.31543800234794617,
-0.32252824306488037,
0.8255583047866821,
-0.14529970288276672,
-0.2695446312427521,
-0.33378756046295166,
-0.1653425395488739,
0.1454019844532013,
-0.3920115828514099,
0.912214994430542,
-0.7279734015464783,
0.7374742031097412,
0.933980405330658,
0.13429680466651917,
-0.514870285987854,
0.3989711999893189,
-0.11613689363002776,
0.4022413492202759,
-0.9990655779838562,
-0.33749932050704956,
-0.4334589838981629,
-1.376373291015625,
-0.2993924915790558,
-0.09454808384180068,
-0.01314175222069025,
-0.001090060803107917,
0.2137461006641388,
0.2938512861728668,
0.17508235573768616,
0.8260607123374939,
-0.7218498587608337,
0.2414487451314926,
-0.47296759486198425,
-0.3002610504627228,
-1.238540768623352,
0.08663805574178696,
0.6805586218833923,
0.5909030437469482,
-0.42807504534721375,
-0.22887496650218964,
0.47537800669670105,
-1.0474627017974854,
0.6338009238243103,
0.06548397243022919,
0.4971011281013489,
1.3484878540039063
]
],
"regenerate": true
}
}
}

View File

@@ -1,785 +0,0 @@
---
source: dump/src/reader/mod.rs
expression: document
---
{
"id": "e1",
"desc": "natural vector",
"_vectors": {
"default": {
"embeddings": [
[
-0.2979458272457123,
-0.5288640856742859,
-0.019957859069108963,
-0.18495318293571472,
0.7429973483085632,
0.5238497257232666,
0.432366281747818,
0.32744166254997253,
0.0020762972999364138,
-0.9507834911346436,
-0.35097137093544006,
0.08469701558351517,
-1.4176613092422483,
0.4647577106952667,
-0.69340580701828,
1.0372896194458008,
0.3716741800308227,
0.06031008064746857,
-0.6152024269104004,
0.007914665155112743,
0.7954924702644348,
-0.20773003995418549,
0.09376765787601472,
0.04508133605122566,
-0.2084471583366394,
-0.1518009901046753,
0.018195509910583496,
-0.07044368237257004,
-0.18119366466999057,
-0.4480230510234833,
0.3822529911994934,
0.1911812424659729,
0.4674372375011444,
0.06963984668254852,
-0.09341949224472046,
0.005675444379448891,
-0.6774799227714539,
-0.7066726684570313,
-0.39256376028060913,
0.04005039855837822,
0.2084812968969345,
-0.7872875928878784,
-0.8205880522727966,
0.2919981777667999,
-0.06004738807678223,
-0.4907574355602264,
-1.5937862396240234,
0.24249385297298431,
-0.14709846675395966,
-0.11860740929841997,
-0.8299489617347717,
0.472964346408844,
-0.497518390417099,
-0.22205302119255063,
-0.4196169078350067,
0.32697558403015137,
-0.360930860042572,
-0.9789686799049376,
0.1887447088956833,
-0.403737336397171,
0.18524253368377688,
0.3768732249736786,
0.3666233420372009,
0.3511938452720642,
0.6985810995101929,
0.41721710562705994,
0.09754953533411026,
0.6204307079315186,
-1.0762996673583984,
-0.06263761967420578,
-0.7376511693000793,
0.6849768161773682,
-0.1745152473449707,
-0.40449759364128113,
0.20757411420345304,
-0.8424443006515503,
0.330015629529953,
0.3489064872264862,
1.0954371690750122,
0.8487558960914612,
1.1076823472976685,
0.61430823802948,
0.4155903458595276,
0.4111340939998626,
0.05753209814429283,
-0.06429877132177353,
-0.765606164932251,
-0.41703930497169495,
-0.508820652961731,
0.19859947264194489,
-0.16607828438282013,
-0.28112146258354187,
0.11032675206661224,
0.38809511065483093,
-0.36498191952705383,
-0.48671194911003113,
0.6755134463310242,
0.03958442434668541,
0.4478721618652344,
-0.10335399955511092,
-0.9546685814857484,
-0.6087718605995178,
0.17498846352100372,
0.08320838958024979,
-1.4478336572647097,
-0.605027437210083,
-0.5867993235588074,
-0.14711688458919525,
-0.5447602272033691,
-0.026259321719408035,
-0.6997418403625488,
-0.07349082082509995,
0.10638900846242905,
-0.7133527398109436,
-0.9396815299987792,
1.087092399597168,
1.1885089874267578,
0.4011896848678589,
-0.4089202582836151,
-0.10938972979784012,
0.6726722121238708,
0.24576938152313232,
-0.24247920513153076,
1.1499971151351929,
0.47813335061073303,
-0.05331678315997124,
0.32338133454322815,
0.4870913326740265,
-0.23144258558750153,
-1.2023426294326782,
0.2349330335855484,
1.080536961555481,
0.29334118962287903,
0.391574501991272,
-0.15818795561790466,
-0.2948290705680847,
-0.024689948186278343,
0.06602869182825089,
0.5937030911445618,
-0.047901444137096405,
-0.512734591960907,
-0.35780075192451477,
0.28751692175865173,
0.4298716187477112,
0.9242428541183472,
-0.17208744585514069,
0.11515070497989656,
-0.0335976779460907,
-0.3422986567020416,
0.5344581604003906,
0.19895796477794647,
0.33001241087913513,
0.6390730142593384,
-0.6074934005737305,
-0.2553696632385254,
0.9644920229911804,
0.2699219584465027,
0.6403993368148804,
-0.6380003690719604,
-0.027310986071825027,
0.638815701007843,
0.27719101309776306,
-0.13553589582443237,
0.750195324420929,
0.1224869191646576,
-0.20613941550254825,
0.8444448709487915,
0.16200250387191772,
-0.24750925600528717,
-0.739950954914093,
-0.28443849086761475,
-1.176282525062561,
0.516107976436615,
0.3774825632572174,
0.10906043648719788,
0.07962015271186829,
0.7384604215621948,
-0.051241904497146606,
1.1730090379714966,
-0.4828610122203827,
-1.404372215270996,
0.8811132311820984,
-0.3839482367038727,
0.022516896948218346,
-0.0491158664226532,
-0.43027013540267944,
1.2049334049224854,
-0.27309560775756836,
0.6883630752563477,
0.8264574408531189,
-0.5020735263824463,
-0.4874092042446137,
0.6007202863693237,
-0.4965405762195587,
1.1302915811538696,
0.032572727650403976,
-0.3731859028339386,
0.658271849155426,
-0.9023059010505676,
0.7400162220001221,
0.014550759457051754,
-0.19699542224407196,
0.2319706380367279,
-0.789058268070221,
-0.14905710518360138,
-0.5826214551925659,
0.207652747631073,
-0.4507439732551574,
-0.3163885474205017,
0.3604124188423157,
-0.45119962096214294,
0.3428427278995514,
0.3005594313144684,
-0.36026081442832947,
1.1014249324798584,
0.40884315967559814,
0.34991952776908875,
-0.1806638240814209,
0.27440476417541504,
-0.7118373513221741,
0.4645499587059021,
0.214790478348732,
-0.2343102991580963,
0.10500429570674896,
-0.28034430742263794,
1.2267805337905884,
1.0561333894729614,
-0.497364342212677,
-0.6143305897712708,
0.24963727593421936,
-0.33136463165283203,
-0.01473914459347725,
0.495918869972229,
-0.6985538005828857,
-1.0033197402954102,
0.35937801003456116,
0.6325868368148804,
-0.6808838844299316,
1.0354058742523191,
-0.7214401960372925,
-0.33318862318992615,
0.874398410320282,
-0.6594992280006409,
0.6830640435218811,
-0.18534131348133087,
0.024834271520376205,
0.19901277124881744,
-0.5992477536201477,
-1.2126628160476685,
-0.9245557188987732,
-0.3898217976093292,
-0.1286519467830658,
0.4217943847179413,
-0.1143646091222763,
0.5630772709846497,
-0.5240639448165894,
0.21152715384960177,
-0.3792001008987427,
0.8266305327415466,
1.170984387397766,
-0.8072142004966736,
0.11382893472909927,
-0.17953898012638092,
-0.1789460331201553,
-0.15078622102737427,
-1.2082908153533936,
-0.7812382578849792,
-0.10903695970773696,
0.7303897142410278,
-0.39054441452026367,
0.19511254131793976,
-0.09121843427419662,
0.22400228679180145,
0.30143046379089355,
0.1141919493675232,
0.48112115263938904,
0.7307931780815125,
0.09701362252235413,
-0.2795647978782654,
-0.3997688889503479,
0.5540812611579895,
0.564578115940094,
-0.40065160393714905,
-0.3629159033298493,
-0.3789091110229492,
-0.7298538088798523,
-0.6996853351593018,
-0.4477842152118683,
-0.289089560508728,
-0.6430277824401855,
0.2344944179058075,
0.3742927014827728,
-0.5079357028007507,
0.28841453790664673,
0.06515737622976303,
0.707315981388092,
0.09498685598373412,
0.8365515470504761,
0.10002726316452026,
-0.7695478200912476,
0.6264724135398865,
0.7562043070793152,
-0.23112858831882477,
-0.2871039807796478,
-0.25010058283805847,
0.2783474028110504,
-0.03224996477365494,
-0.9119359850883484,
-3.6940200328826904,
-0.5099936127662659,
-0.1604711413383484,
0.17453284561634064,
0.41759559512138367,
0.1419190913438797,
-0.11362407356500626,
-0.33312007784843445,
0.11511333286762238,
0.4667884409427643,
-0.0031647447030991316,
0.15879854559898376,
0.3042248487472534,
0.5404849052429199,
0.8515422344207764,
0.06286454200744629,
0.43790125846862793,
-0.8682025074958801,
-0.06363756954669952,
0.5547921657562256,
-0.01483887154608965,
-0.07361344993114471,
-0.929947018623352,
0.3502565622329712,
-0.5080993175506592,
1.0380364656448364,
-0.2017953395843506,
0.21319580078125,
-1.0763001441955566,
-0.556368887424469,
0.1949922740459442,
-0.6445739269256592,
0.6791343688964844,
0.21188358962535855,
0.3736183941364288,
-0.21800459921360016,
0.7597446441650391,
-0.3732394874095917,
-0.4710160195827484,
0.025146087631583217,
0.05341297015547752,
-0.9522109627723694,
-0.6000866889953613,
-0.08469046652317047,
0.5966026186943054,
0.3444081246852875,
-0.461188405752182,
-0.5279349088668823,
0.10296865552663804,
0.5175143480300903,
-0.20671147108078003,
0.13392412662506104,
0.4812754988670349,
0.2993808686733246,
-0.3005635440349579,
0.5141698122024536,
-0.6239235401153564,
0.2877119481563568,
-0.4452739953994751,
0.5621107816696167,
0.5047508478164673,
-0.4226335883140564,
-0.18578553199768064,
-1.1967322826385498,
0.28178197145462036,
-0.8692031502723694,
-1.1812998056411743,
-1.4526212215423584,
0.4645712077617645,
0.9327932000160216,
-0.6560136675834656,
0.461549699306488,
-0.5621527433395386,
-1.328449010848999,
-0.08676894754171371,
0.00021918353741057217,
-0.18864136934280396,
0.1259666532278061,
0.18240638077259064,
-0.14919660985469818,
-0.8965857625007629,
-0.7539900541305542,
0.013973715715110302,
0.504276692867279,
-0.704748272895813,
-0.6428424119949341,
0.6303996443748474,
-0.5404738187789917,
-0.31176653504371643,
-0.21262824535369873,
0.18736739456653595,
-0.7998970746994019,
0.039946746081113815,
0.7390344738960266,
0.4283199906349182,
0.3795057237148285,
0.07204607129096985,
-0.9230587482452391,
0.9440426230430604,
0.26272690296173096,
0.5598306655883789,
-1.0520871877670288,
-0.2677186131477356,
-0.1888762265443802,
0.30426350235939026,
0.4746131896972656,
-0.5746733546257019,
-0.4197768568992615,
0.8565112948417664,
-0.6767723560333252,
0.23448683321475983,
-0.2010004222393036,
0.4112907350063324,
-0.6497949957847595,
-0.418667733669281,
-0.4950824975967407,
0.44438859820365906,
1.026281714439392,
0.482397586107254,
-0.26220494508743286,
-0.3640787005424499,
0.5907743573188782,
-0.8771642446517944,
0.09708411991596222,
-0.3671700060367584,
0.4331349730491638,
0.619417667388916,
-0.2684665620326996,
-0.5123821496963501,
-0.1502324342727661,
-0.012190685607492924,
0.3580845892429352,
0.8617186546325684,
0.3493645489215851,
1.0270192623138428,
0.18297909200191495,
-0.5881339311599731,
-0.1733516901731491,
-0.5040576457977295,
-0.340370237827301,
-0.26767754554748535,
-0.28570041060447693,
-0.032928116619586945,
0.6029254794120789,
0.17397655546665192,
0.09346921741962431,
0.27815181016921997,
-0.46699589490890503,
-0.8148876428604126,
-0.3964351713657379,
0.3812595009803772,
0.13547226786613464,
0.7126688361167908,
-0.3473474085330963,
-0.06573959439992905,
-0.6483767032623291,
1.4808889627456665,
0.30924928188323975,
-0.5085946917533875,
-0.8613000512123108,
0.3048902451992035,
-0.4241599142551422,
0.15909206867218018,
0.5764641761779785,
-0.07879110425710678,
1.015336513519287,
0.07599356025457382,
-0.7025855779647827,
0.30047643184661865,
-0.35094937682151794,
0.2522146999835968,
-0.2338722199201584,
-0.8326804637908936,
-0.13695412874221802,
-0.03452421352267265,
0.47974953055381775,
-0.18385636806488037,
0.32438594102859497,
0.1797013282775879,
0.787494957447052,
-0.12579888105392456,
-0.07507286965847015,
-0.4389670491218567,
0.2720070779323578,
0.8138866424560547,
0.01974171027541161,
-0.3057698905467987,
-0.6709924936294556,
0.0885881632566452,
-0.2862754464149475,
0.03475658595561981,
-0.1285519152879715,
0.3838353455066681,
-0.2944154739379883,
-0.4204859137535095,
-0.4416137933731079,
0.13426260650157928,
0.36733248829841614,
0.573428750038147,
-0.14928072690963745,
-0.026076916605234143,
0.33286052942276,
-0.5340145826339722,
-0.17279052734375,
-0.01154550164937973,
-0.6620771884918213,
0.18390542268753052,
-0.08265615254640579,
-0.2489682286977768,
0.2429984211921692,
-0.044153645634651184,
-0.986578404903412,
-0.33574509620666504,
-0.5387663841247559,
0.19767941534519196,
0.12540718913078308,
-0.3403128981590271,
-0.4154576361179352,
0.17275673151016235,
0.09407442808151244,
-0.5414086580276489,
0.4393929839134216,
0.1725579798221588,
-0.4998118281364441,
-0.6926208138465881,
0.16552448272705078,
0.6659538149833679,
-0.10949844866991044,
0.986426830291748,
0.01748848147690296,
0.4003709554672241,
-0.5430638194084167,
0.35347291827201843,
0.6887399554252625,
0.08274628221988678,
0.13407137989997864,
-0.591465950012207,
0.3446292281150818,
0.6069018244743347,
0.1935492902994156,
-0.0989871397614479,
0.07008486241102219,
-0.8503749370574951,
-0.09507356584072112,
0.6259510517120361,
0.13934025168418884,
0.06392545253038406,
-0.4112265408039093,
-0.08475656062364578,
0.4974113404750824,
-0.30606114864349365,
1.111435890197754,
-0.018766529858112335,
-0.8422622680664063,
0.4325508773326874,
-0.2832120656967163,
-0.4859798848628998,
-0.41498348116874695,
0.015977520495653152,
0.5292825698852539,
0.4538311660289765,
1.1328668594360352,
0.22632671892642975,
0.7918671369552612,
0.33401933312416077,
0.7306135296821594,
0.3548600673675537,
0.12506209313869476,
0.8573207855224609,
-0.5818327069282532,
-0.6953738927841187,
-1.6171947717666626,
-0.1699674427509308,
0.6318262815475464,
-0.05671752244234085,
-0.28145185112953186,
-0.3976689279079437,
-0.2041076272726059,
-0.5495951175689697,
-0.5152917504310608,
-0.9309796094894408,
0.101932130753994,
0.1367802917957306,
0.1490798443555832,
0.5304336547851563,
-0.5082434415817261,
0.06688683480024338,
0.14657628536224365,
-0.782435953617096,
0.2962816655635834,
0.6965363621711731,
0.8496337532997131,
-0.3042965829372406,
0.04343798756599426,
0.0330701619386673,
-0.5662598013877869,
1.1086925268173218,
0.756072998046875,
-0.204134538769722,
0.2404300570487976,
-0.47848284244537354,
1.3659011125564575,
0.5645433068275452,
-0.15836156904697418,
0.43395575881004333,
0.5944653749465942,
1.0043466091156006,
-0.49446743726730347,
-0.5954391360282898,
0.5341240763664246,
0.020598189905285835,
-0.4036853015422821,
0.4473709762096405,
1.1998231410980225,
-0.9317775368690492,
-0.23321466147899628,
0.2052552700042725,
-0.7423108816146851,
-0.19917210936546328,
-0.1722569614648819,
-0.034072667360305786,
-0.00671181408688426,
0.46396249532699585,
-0.1372445821762085,
0.053376372903585434,
0.7392690777778625,
-0.38447609543800354,
0.07497968524694443,
0.5197252631187439,
1.3746477365493774,
0.9060075879096984,
0.20000585913658145,
-0.4053704142570496,
0.7497360110282898,
-0.34087055921554565,
-1.101803183555603,
0.273650586605072,
-0.5125769376754761,
0.22472351789474487,
0.480757474899292,
-0.19845178723335263,
0.8857700824737549,
0.30752456188201904,
1.1109285354614258,
-0.6768012642860413,
0.524367094039917,
-0.22495046257972717,
-0.4224412739276886,
0.40753406286239624,
-0.23133376240730288,
0.3297771215438843,
0.4905449151992798,
-0.6813114285469055,
-0.7543983459472656,
-0.5599071383476257,
0.14351597428321838,
-0.029278717935085297,
-0.3970443606376648,
-0.303079217672348,
0.24161772429943085,
0.008353390730917454,
-0.0062365154735744,
1.0824860334396362,
-0.3704061508178711,
-1.0337258577346802,
0.04638749733567238,
1.163011074066162,
-0.31737643480300903,
0.013986887410283089,
0.19223114848136905,
-0.2260770797729492,
-0.210910826921463,
-1.0191949605941772,
0.22356095910072327,
0.09353553503751756,
0.18096882104873657,
0.14867214858531952,
0.43408671021461487,
-0.33312076330184937,
0.8173948526382446,
0.6428242921829224,
0.20215003192424777,
-0.6634518504142761,
-0.4132290482521057,
0.29815030097961426,
-1.579406976699829,
-0.0981958732008934,
-0.03941014781594277,
0.1709178239107132,
-0.5481140613555908,
-0.5338194966316223,
-0.3528362512588501,
-0.11561278253793716,
-0.21793591976165771,
-1.1570470333099363,
0.2157980799674988,
0.42083489894866943,
0.9639263153076172,
0.09747201204299928,
0.15671424567699432,
0.4034591615200043,
0.6728067994117737,
-0.5216875672340393,
0.09657668322324751,
-0.2416689097881317,
0.747975766658783,
0.1021689772605896,
0.11652665585279463,
-1.0484966039657593,
0.8489304780960083,
0.7169828414916992,
-0.09012343734502792,
-1.3173753023147583,
0.057890523225069046,
-0.006231260951608419,
-0.1018214002251625,
0.936040461063385,
-0.0502331368625164,
-0.4284322261810303,
-0.38209280371665955,
-0.22668412327766416,
0.0782942995429039,
-0.4881664514541626,
0.9268959760665894,
0.001867273123934865,
0.42261114716529846,
0.8283362984657288,
0.4256294071674347,
-0.7965338826179504,
0.4840078353881836,
-0.19861412048339844,
0.33977967500686646,
-0.4604192078113556,
-0.3107339143753052,
-0.2839638590812683,
-1.5734281539916992,
0.005220232997089624,
0.09239906817674635,
-0.7828494906425476,
-0.1397123783826828,
0.2576255202293396,
0.21372435986995697,
-0.23169949650764465,
0.4016408920288086,
-0.462497353553772,
-0.2186472862958908,
-0.5617868900299072,
-0.3649831712245941,
-1.1585862636566162,
-0.08222806453704834,
0.931126832962036,
0.4327389597892761,
-0.46451422572135925,
-0.5430706143379211,
-0.27434298396110535,
-0.9479129314422609,
0.1845661848783493,
0.3972720205783844,
0.4883299469947815,
1.04031240940094
]
],
"regenerate": true
}
}
}

View File

@@ -1,780 +0,0 @@
---
source: dump/src/reader/mod.rs
expression: document
---
{
"id": "e0",
"desc": "overriden vector",
"_vectors": {
"default": [
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1,
0.1
]
}
}

View File

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

View File

@@ -61,7 +61,7 @@ pub enum IndexDocumentsMethod {
#[cfg_attr(test, derive(serde::Serialize))]
#[non_exhaustive]
pub enum UpdateFormat {
/// The given update is a real **comma separated** CSV with headers on the first line.
/// The given update is a real **comma seperated** CSV with headers on the first line.
Csv,
/// The given update is a JSON array with documents inside.
Json,

View File

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

View File

@@ -152,7 +152,6 @@ impl Settings<Unchecked> {
}
#[derive(Debug, Clone, Deserialize)]
#[allow(dead_code)] // otherwise rustc complains that the fields go unused
#[cfg_attr(test, derive(serde::Serialize))]
#[serde(deny_unknown_fields)]
#[serde(rename_all = "camelCase")]

View File

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

View File

@@ -182,7 +182,6 @@ impl Settings<Unchecked> {
}
}
#[allow(dead_code)] // otherwise rustc complains that the fields go unused
#[derive(Debug, Clone, Deserialize)]
#[cfg_attr(test, derive(serde::Serialize))]
#[serde(deny_unknown_fields)]

View File

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

View File

@@ -200,7 +200,6 @@ impl std::ops::Deref for IndexUid {
}
}
#[allow(dead_code)] // otherwise rustc complains that the fields go unused
#[derive(Debug)]
#[cfg_attr(test, derive(serde::Serialize))]
#[cfg_attr(test, serde(rename_all = "camelCase"))]

View File

@@ -219,7 +219,7 @@ pub(crate) mod test {
fn _create_directory_hierarchy(dir: &Path, depth: usize) -> String {
let mut ret = String::new();
// the entries are not guaranteed to be returned in the same order thus we need to sort them.
// the entries are not guarenteed to be returned in the same order thus we need to sort them.
let mut entries =
fs::read_dir(dir).unwrap().collect::<std::result::Result<Vec<_>, _>>().unwrap();
@@ -281,7 +281,7 @@ pub(crate) mod test {
let dump_path = dump.path();
// ==== checking global file hierarchy (we want to be sure there isn't too many files or too few)
insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r###"
insta::assert_display_snapshot!(create_directory_hierarchy(dump_path), @r###"
.
├---- indexes/
│ └---- doggos/

View File

@@ -11,7 +11,9 @@ edition.workspace = true
license.workspace = true
[dependencies]
tempfile = "3.10.1"
thiserror = "1.0.61"
tracing = "0.1.40"
uuid = { version = "1.10.0", features = ["serde", "v4"] }
tempfile = "3.9.0"
thiserror = "1.0.56"
uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies]
faux = "0.1.10"

View File

@@ -1,5 +1,5 @@
use std::fs::File as StdFile;
use std::io::Write;
use std::ops::{Deref, DerefMut};
use std::path::{Path, PathBuf};
use std::str::FromStr;
@@ -22,6 +22,20 @@ pub enum Error {
pub type Result<T> = std::result::Result<T, Error>;
impl Deref for File {
type Target = NamedTempFile;
fn deref(&self) -> &Self::Target {
&self.file
}
}
impl DerefMut for File {
fn deref_mut(&mut self) -> &mut Self::Target {
&mut self.file
}
}
#[derive(Clone, Debug)]
pub struct FileStore {
path: PathBuf,
@@ -42,7 +56,7 @@ impl FileStore {
let file = NamedTempFile::new_in(&self.path)?;
let uuid = Uuid::new_v4();
let path = self.path.join(uuid.to_string());
let update_file = File { file: Some(file), path };
let update_file = File { file, path };
Ok((uuid, update_file))
}
@@ -53,7 +67,7 @@ impl FileStore {
let file = NamedTempFile::new_in(&self.path)?;
let uuid = Uuid::from_u128(uuid);
let path = self.path.join(uuid.to_string());
let update_file = File { file: Some(file), path };
let update_file = File { file, path };
Ok((uuid, update_file))
}
@@ -61,13 +75,7 @@ impl FileStore {
/// Returns the file corresponding to the requested uuid.
pub fn get_update(&self, uuid: Uuid) -> Result<StdFile> {
let path = self.get_update_path(uuid);
let file = match StdFile::open(path) {
Ok(file) => file,
Err(e) => {
tracing::error!("Can't access update file {uuid}: {e}");
return Err(e.into());
}
};
let file = StdFile::open(path)?;
Ok(file)
}
@@ -102,12 +110,8 @@ impl FileStore {
pub fn delete(&self, uuid: Uuid) -> Result<()> {
let path = self.path.join(uuid.to_string());
if let Err(e) = std::fs::remove_file(path) {
tracing::error!("Can't delete file {uuid}: {e}");
Err(e.into())
} else {
Ok(())
}
std::fs::remove_file(path)?;
Ok(())
}
/// List the Uuids of the files in the FileStore
@@ -132,40 +136,16 @@ impl FileStore {
pub struct File {
path: PathBuf,
file: Option<NamedTempFile>,
file: NamedTempFile,
}
impl File {
pub fn dry_file() -> Result<Self> {
Ok(Self { path: PathBuf::new(), file: None })
}
pub fn persist(self) -> Result<()> {
if let Some(file) = self.file {
file.persist(&self.path)?;
}
self.file.persist(&self.path)?;
Ok(())
}
}
impl Write for File {
fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
if let Some(file) = self.file.as_mut() {
file.write(buf)
} else {
Ok(buf.len())
}
}
fn flush(&mut self) -> std::io::Result<()> {
if let Some(file) = self.file.as_mut() {
file.flush()
} else {
Ok(())
}
}
}
#[cfg(test)]
mod test {
use std::io::Write;

View File

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

View File

@@ -564,121 +564,121 @@ pub mod tests {
#[test]
fn parse_escaped() {
insta::assert_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#);
insta::assert_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#);
insta::assert_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#);
insta::assert_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
// but it also works with other sequences
insta::assert_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
insta::assert_display_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#);
insta::assert_display_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#);
insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#);
insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
// but it also works with other sequencies
insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
}
#[test]
fn parse() {
// Test equal
insta::assert_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
insta::assert_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");
insta::assert_snapshot!(p("channel = 'Mister Mv'"), @"{channel} = {Mister Mv}");
insta::assert_snapshot!(p("channel = \"Mister Mv\""), @"{channel} = {Mister Mv}");
insta::assert_snapshot!(p("'dog race' = Borzoi"), @"{dog race} = {Borzoi}");
insta::assert_snapshot!(p("\"dog race\" = Chusky"), @"{dog race} = {Chusky}");
insta::assert_snapshot!(p("\"dog race\" = \"Bernese Mountain\""), @"{dog race} = {Bernese Mountain}");
insta::assert_snapshot!(p("'dog race' = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
insta::assert_snapshot!(p("\"dog race\" = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
insta::assert_display_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
insta::assert_display_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");
insta::assert_display_snapshot!(p("channel = 'Mister Mv'"), @"{channel} = {Mister Mv}");
insta::assert_display_snapshot!(p("channel = \"Mister Mv\""), @"{channel} = {Mister Mv}");
insta::assert_display_snapshot!(p("'dog race' = Borzoi"), @"{dog race} = {Borzoi}");
insta::assert_display_snapshot!(p("\"dog race\" = Chusky"), @"{dog race} = {Chusky}");
insta::assert_display_snapshot!(p("\"dog race\" = \"Bernese Mountain\""), @"{dog race} = {Bernese Mountain}");
insta::assert_display_snapshot!(p("'dog race' = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
insta::assert_display_snapshot!(p("\"dog race\" = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
// Test IN
insta::assert_snapshot!(p("colour IN[]"), @"{colour} IN[]");
insta::assert_snapshot!(p("colour IN[green]"), @"{colour} IN[{green}, ]");
insta::assert_snapshot!(p("colour IN[green,]"), @"{colour} IN[{green}, ]");
insta::assert_snapshot!(p("colour NOT IN[green,blue]"), @"NOT ({colour} IN[{green}, {blue}, ])");
insta::assert_snapshot!(p(" colour IN [ green , blue , ]"), @"{colour} IN[{green}, {blue}, ]");
insta::assert_display_snapshot!(p("colour IN[]"), @"{colour} IN[]");
insta::assert_display_snapshot!(p("colour IN[green]"), @"{colour} IN[{green}, ]");
insta::assert_display_snapshot!(p("colour IN[green,]"), @"{colour} IN[{green}, ]");
insta::assert_display_snapshot!(p("colour NOT IN[green,blue]"), @"NOT ({colour} IN[{green}, {blue}, ])");
insta::assert_display_snapshot!(p(" colour IN [ green , blue , ]"), @"{colour} IN[{green}, {blue}, ]");
// Test IN + OR/AND/()
insta::assert_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
insta::assert_snapshot!(p("NOT (colour IN [green, blue]) AND color = green "), @"AND[NOT ({colour} IN[{green}, {blue}, ]), {color} = {green}, ]");
insta::assert_snapshot!(p("x = 1 OR NOT (colour IN [green, blue] OR color = green) "), @"OR[{x} = {1}, NOT (OR[{colour} IN[{green}, {blue}, ], {color} = {green}, ]), ]");
insta::assert_display_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
insta::assert_display_snapshot!(p("NOT (colour IN [green, blue]) AND color = green "), @"AND[NOT ({colour} IN[{green}, {blue}, ]), {color} = {green}, ]");
insta::assert_display_snapshot!(p("x = 1 OR NOT (colour IN [green, blue] OR color = green) "), @"OR[{x} = {1}, NOT (OR[{colour} IN[{green}, {blue}, ], {color} = {green}, ]), ]");
// Test whitespace start/end
insta::assert_snapshot!(p(" colour = green "), @"{colour} = {green}");
insta::assert_snapshot!(p(" (colour = green OR colour = red) "), @"OR[{colour} = {green}, {colour} = {red}, ]");
insta::assert_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
insta::assert_snapshot!(p(" colour NOT IN [green, blue] "), @"NOT ({colour} IN[{green}, {blue}, ])");
insta::assert_snapshot!(p(" colour IN [green, blue] "), @"{colour} IN[{green}, {blue}, ]");
insta::assert_display_snapshot!(p(" colour = green "), @"{colour} = {green}");
insta::assert_display_snapshot!(p(" (colour = green OR colour = red) "), @"OR[{colour} = {green}, {colour} = {red}, ]");
insta::assert_display_snapshot!(p(" colour IN [green, blue] AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
insta::assert_display_snapshot!(p(" colour NOT IN [green, blue] "), @"NOT ({colour} IN[{green}, {blue}, ])");
insta::assert_display_snapshot!(p(" colour IN [green, blue] "), @"{colour} IN[{green}, {blue}, ]");
// Test conditions
insta::assert_snapshot!(p("channel != ponce"), @"{channel} != {ponce}");
insta::assert_snapshot!(p("NOT channel = ponce"), @"NOT ({channel} = {ponce})");
insta::assert_snapshot!(p("subscribers < 1000"), @"{subscribers} < {1000}");
insta::assert_snapshot!(p("subscribers > 1000"), @"{subscribers} > {1000}");
insta::assert_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
insta::assert_snapshot!(p("subscribers >= 1000"), @"{subscribers} >= {1000}");
insta::assert_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
insta::assert_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}");
insta::assert_display_snapshot!(p("channel != ponce"), @"{channel} != {ponce}");
insta::assert_display_snapshot!(p("NOT channel = ponce"), @"NOT ({channel} = {ponce})");
insta::assert_display_snapshot!(p("subscribers < 1000"), @"{subscribers} < {1000}");
insta::assert_display_snapshot!(p("subscribers > 1000"), @"{subscribers} > {1000}");
insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
insta::assert_display_snapshot!(p("subscribers >= 1000"), @"{subscribers} >= {1000}");
insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
insta::assert_display_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}");
// Test NOT
insta::assert_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})");
insta::assert_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
insta::assert_display_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})");
insta::assert_display_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
// Test NULL + NOT NULL
insta::assert_snapshot!(p("subscribers IS NULL"), @"{subscribers} IS NULL");
insta::assert_snapshot!(p("NOT subscribers IS NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_snapshot!(p("NOT subscribers IS NOT NULL"), @"{subscribers} IS NULL");
insta::assert_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_display_snapshot!(p("subscribers IS NULL"), @"{subscribers} IS NULL");
insta::assert_display_snapshot!(p("NOT subscribers IS NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_display_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
insta::assert_display_snapshot!(p("NOT subscribers IS NOT NULL"), @"{subscribers} IS NULL");
insta::assert_display_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
// Test EMPTY + NOT EMPTY
insta::assert_snapshot!(p("subscribers IS EMPTY"), @"{subscribers} IS EMPTY");
insta::assert_snapshot!(p("NOT subscribers IS EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY");
insta::assert_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_display_snapshot!(p("subscribers IS EMPTY"), @"{subscribers} IS EMPTY");
insta::assert_display_snapshot!(p("NOT subscribers IS EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_display_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
insta::assert_display_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY");
insta::assert_display_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
// Test EXISTS + NOT EXITS
insta::assert_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
insta::assert_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
insta::assert_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_display_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
insta::assert_display_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_display_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
insta::assert_display_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
insta::assert_display_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
// Test nested NOT
insta::assert_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
insta::assert_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
insta::assert_display_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
insta::assert_display_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
// Test geo radius
insta::assert_snapshot!(p("_geoRadius(12, 13, 14)"), @"_geoRadius({12}, {13}, {14})");
insta::assert_snapshot!(p("NOT _geoRadius(12, 13, 14)"), @"NOT (_geoRadius({12}, {13}, {14}))");
insta::assert_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})");
insta::assert_display_snapshot!(p("_geoRadius(12, 13, 14)"), @"_geoRadius({12}, {13}, {14})");
insta::assert_display_snapshot!(p("NOT _geoRadius(12, 13, 14)"), @"NOT (_geoRadius({12}, {13}, {14}))");
insta::assert_display_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})");
// Test geo bounding box
insta::assert_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
insta::assert_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))");
insta::assert_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
insta::assert_display_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
insta::assert_display_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))");
insta::assert_display_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
// Test OR + AND
insta::assert_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
insta::assert_snapshot!(p("channel = ponce OR 'dog race' != 'bernese mountain'"), @"OR[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
insta::assert_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000"), @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ]");
insta::assert_snapshot!(
insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
insta::assert_display_snapshot!(p("channel = ponce OR 'dog race' != 'bernese mountain'"), @"OR[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000"), @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ]");
insta::assert_display_snapshot!(
p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000 OR colour = red OR colour = blue AND size = 7"),
@"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, {colour} = {red}, AND[{colour} = {blue}, {size} = {7}, ], ]"
);
// Test parentheses
insta::assert_snapshot!(p("channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )"), @"AND[{channel} = {ponce}, OR[{dog race} != {bernese mountain}, {subscribers} > {1000}, ], ]");
insta::assert_snapshot!(p("(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)"), @"AND[OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ], _geoRadius({12}, {13}, {14}), ]");
insta::assert_display_snapshot!(p("channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )"), @"AND[{channel} = {ponce}, OR[{dog race} != {bernese mountain}, {subscribers} > {1000}, ], ]");
insta::assert_display_snapshot!(p("(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)"), @"AND[OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ], _geoRadius({12}, {13}, {14}), ]");
// Test recursion
// This is the most that is allowed
insta::assert_snapshot!(
insta::assert_display_snapshot!(
p("(((((((((((((((((((((((((((((((((((((((((((((((((x = 1)))))))))))))))))))))))))))))))))))))))))))))))))"),
@"{x} = {1}"
);
insta::assert_snapshot!(
insta::assert_display_snapshot!(
p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"),
@"NOT ({x} = {1})"
);
// Confusing keywords
insta::assert_snapshot!(p(r#"NOT "OR" EXISTS AND "EXISTS" NOT EXISTS"#), @"AND[NOT ({OR} EXISTS), NOT ({EXISTS} EXISTS), ]");
insta::assert_display_snapshot!(p(r#"NOT "OR" EXISTS AND "EXISTS" NOT EXISTS"#), @"AND[NOT ({OR} EXISTS), NOT ({EXISTS} EXISTS), ]");
}
#[test]
@@ -689,182 +689,182 @@ pub mod tests {
Fc::parse(s).unwrap_err().to_string()
}
insta::assert_snapshot!(p("channel = Ponce = 12"), @r###"
insta::assert_display_snapshot!(p("channel = Ponce = 12"), @r###"
Found unexpected characters at the end of the filter: `= 12`. You probably forgot an `OR` or an `AND` rule.
17:21 channel = Ponce = 12
"###);
insta::assert_snapshot!(p("channel = "), @r###"
insta::assert_display_snapshot!(p("channel = "), @r###"
Was expecting a value but instead got nothing.
14:14 channel =
"###);
insta::assert_snapshot!(p("channel = 🐻"), @r###"
insta::assert_display_snapshot!(p("channel = 🐻"), @r###"
Was expecting a value but instead got `🐻`.
11:12 channel = 🐻
"###);
insta::assert_snapshot!(p("channel = 🐻 AND followers < 100"), @r###"
insta::assert_display_snapshot!(p("channel = 🐻 AND followers < 100"), @r###"
Was expecting a value but instead got `🐻`.
11:12 channel = 🐻 AND followers < 100
"###);
insta::assert_snapshot!(p("'OR'"), @r###"
insta::assert_display_snapshot!(p("'OR'"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
1:5 'OR'
"###);
insta::assert_snapshot!(p("OR"), @r###"
insta::assert_display_snapshot!(p("OR"), @r###"
Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
1:3 OR
"###);
insta::assert_snapshot!(p("channel Ponce"), @r###"
insta::assert_display_snapshot!(p("channel Ponce"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
1:14 channel Ponce
"###);
insta::assert_snapshot!(p("channel = Ponce OR"), @r###"
insta::assert_display_snapshot!(p("channel = Ponce OR"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
19:19 channel = Ponce OR
"###);
insta::assert_snapshot!(p("_geoRadius"), @r###"
insta::assert_display_snapshot!(p("_geoRadius"), @r###"
The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.
1:11 _geoRadius
"###);
insta::assert_snapshot!(p("_geoRadius = 12"), @r###"
insta::assert_display_snapshot!(p("_geoRadius = 12"), @r###"
The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.
1:16 _geoRadius = 12
"###);
insta::assert_snapshot!(p("_geoBoundingBox"), @r###"
insta::assert_display_snapshot!(p("_geoBoundingBox"), @r###"
The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
1:16 _geoBoundingBox
"###);
insta::assert_snapshot!(p("_geoBoundingBox = 12"), @r###"
insta::assert_display_snapshot!(p("_geoBoundingBox = 12"), @r###"
The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
1:21 _geoBoundingBox = 12
"###);
insta::assert_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###"
insta::assert_display_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###"
The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
1:26 _geoBoundingBox(1.0, 1.0)
"###);
insta::assert_snapshot!(p("_geoPoint(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("_geoPoint(12, 13, 14)"), @r###"
`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
1:22 _geoPoint(12, 13, 14)
"###);
insta::assert_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###"
`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
13:34 position <= _geoPoint(12, 13, 14)
"###);
insta::assert_snapshot!(p("_geoDistance(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("_geoDistance(12, 13, 14)"), @r###"
`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
1:25 _geoDistance(12, 13, 14)
"###);
insta::assert_snapshot!(p("position <= _geoDistance(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("position <= _geoDistance(12, 13, 14)"), @r###"
`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
13:37 position <= _geoDistance(12, 13, 14)
"###);
insta::assert_snapshot!(p("_geo(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("_geo(12, 13, 14)"), @r###"
`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
1:17 _geo(12, 13, 14)
"###);
insta::assert_snapshot!(p("position <= _geo(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("position <= _geo(12, 13, 14)"), @r###"
`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.
13:29 position <= _geo(12, 13, 14)
"###);
insta::assert_snapshot!(p("position <= _geoRadius(12, 13, 14)"), @r###"
insta::assert_display_snapshot!(p("position <= _geoRadius(12, 13, 14)"), @r###"
The `_geoRadius` filter is an operation and can't be used as a value.
13:35 position <= _geoRadius(12, 13, 14)
"###);
insta::assert_snapshot!(p("channel = 'ponce"), @r###"
insta::assert_display_snapshot!(p("channel = 'ponce"), @r###"
Expression `\'ponce` is missing the following closing delimiter: `'`.
11:17 channel = 'ponce
"###);
insta::assert_snapshot!(p("channel = \"ponce"), @r###"
insta::assert_display_snapshot!(p("channel = \"ponce"), @r###"
Expression `\"ponce` is missing the following closing delimiter: `"`.
11:17 channel = "ponce
"###);
insta::assert_snapshot!(p("channel = mv OR (followers >= 1000"), @r###"
insta::assert_display_snapshot!(p("channel = mv OR (followers >= 1000"), @r###"
Expression `(followers >= 1000` is missing the following closing delimiter: `)`.
17:35 channel = mv OR (followers >= 1000
"###);
insta::assert_snapshot!(p("channel = mv OR followers >= 1000)"), @r###"
insta::assert_display_snapshot!(p("channel = mv OR followers >= 1000)"), @r###"
Found unexpected characters at the end of the filter: `)`. You probably forgot an `OR` or an `AND` rule.
34:35 channel = mv OR followers >= 1000)
"###);
insta::assert_snapshot!(p("colour NOT EXIST"), @r###"
insta::assert_display_snapshot!(p("colour NOT EXIST"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
1:17 colour NOT EXIST
"###);
insta::assert_snapshot!(p("subscribers 100 TO1000"), @r###"
insta::assert_display_snapshot!(p("subscribers 100 TO1000"), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
1:23 subscribers 100 TO1000
"###);
insta::assert_snapshot!(p("channel = ponce ORdog != 'bernese mountain'"), @r###"
insta::assert_display_snapshot!(p("channel = ponce ORdog != 'bernese mountain'"), @r###"
Found unexpected characters at the end of the filter: `ORdog != \'bernese mountain\'`. You probably forgot an `OR` or an `AND` rule.
17:44 channel = ponce ORdog != 'bernese mountain'
"###);
insta::assert_snapshot!(p("colour IN blue, green]"), @r###"
insta::assert_display_snapshot!(p("colour IN blue, green]"), @r###"
Expected `[` after `IN` keyword.
11:23 colour IN blue, green]
"###);
insta::assert_snapshot!(p("colour IN [blue, green, 'blue' > 2]"), @r###"
insta::assert_display_snapshot!(p("colour IN [blue, green, 'blue' > 2]"), @r###"
Expected only comma-separated field names inside `IN[..]` but instead found `> 2]`.
32:36 colour IN [blue, green, 'blue' > 2]
"###);
insta::assert_snapshot!(p("colour IN [blue, green, AND]"), @r###"
insta::assert_display_snapshot!(p("colour IN [blue, green, AND]"), @r###"
Expected only comma-separated field names inside `IN[..]` but instead found `AND]`.
25:29 colour IN [blue, green, AND]
"###);
insta::assert_snapshot!(p("colour IN [blue, green"), @r###"
insta::assert_display_snapshot!(p("colour IN [blue, green"), @r###"
Expected matching `]` after the list of field names given to `IN[`
23:23 colour IN [blue, green
"###);
insta::assert_snapshot!(p("colour IN ['blue, green"), @r###"
insta::assert_display_snapshot!(p("colour IN ['blue, green"), @r###"
Expression `\'blue, green` is missing the following closing delimiter: `'`.
12:24 colour IN ['blue, green
"###);
insta::assert_snapshot!(p("x = EXISTS"), @r###"
insta::assert_display_snapshot!(p("x = EXISTS"), @r###"
Was expecting a value but instead got `EXISTS`, which is a reserved keyword. To use `EXISTS` as a field name or a value, surround it by quotes.
5:11 x = EXISTS
"###);
insta::assert_snapshot!(p("AND = 8"), @r###"
insta::assert_display_snapshot!(p("AND = 8"), @r###"
Was expecting a value but instead got `AND`, which is a reserved keyword. To use `AND` as a field name or a value, surround it by quotes.
1:4 AND = 8
"###);
insta::assert_snapshot!(p("((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))"), @r###"
insta::assert_display_snapshot!(p("((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))"), @r###"
The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions.
51:106 ((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))
"###);
insta::assert_snapshot!(
insta::assert_display_snapshot!(
p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"),
@r###"
The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions.
@@ -872,40 +872,40 @@ pub mod tests {
"###
);
insta::assert_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###"
insta::assert_display_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###"
Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
5:7 NOT OR EXISTS AND EXISTS NOT EXISTS
"###);
insta::assert_snapshot!(p(r#"value NULL"#), @r###"
insta::assert_display_snapshot!(p(r#"value NULL"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
1:11 value NULL
"###);
insta::assert_snapshot!(p(r#"value NOT NULL"#), @r###"
insta::assert_display_snapshot!(p(r#"value NOT NULL"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
1:15 value NOT NULL
"###);
insta::assert_snapshot!(p(r#"value EMPTY"#), @r###"
insta::assert_display_snapshot!(p(r#"value EMPTY"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
1:12 value EMPTY
"###);
insta::assert_snapshot!(p(r#"value NOT EMPTY"#), @r###"
insta::assert_display_snapshot!(p(r#"value NOT EMPTY"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
1:16 value NOT EMPTY
"###);
insta::assert_snapshot!(p(r#"value IS"#), @r###"
insta::assert_display_snapshot!(p(r#"value IS"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
1:9 value IS
"###);
insta::assert_snapshot!(p(r#"value IS NOT"#), @r###"
insta::assert_display_snapshot!(p(r#"value IS NOT"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
1:13 value IS NOT
"###);
insta::assert_snapshot!(p(r#"value IS EXISTS"#), @r###"
insta::assert_display_snapshot!(p(r#"value IS EXISTS"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
1:16 value IS EXISTS
"###);
insta::assert_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
insta::assert_display_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
1:20 value IS NOT EXISTS
"###);

View File

@@ -42,7 +42,7 @@ fn quoted_by(quote: char, input: Span) -> IResult<Token> {
)));
}
}
// if it was preceded by a `\` or if it was anything else we can continue to advance
// if it was preceeded by a `\` or if it was anything else we can continue to advance
}
Ok((

View File

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

View File

@@ -110,7 +110,7 @@ fn main() {
// after executing a batch we check if the database is corrupted
let res = index.search(&wtxn).execute().unwrap();
index.compressed_documents(&wtxn, res.documents_ids).unwrap();
index.documents(&wtxn, res.documents_ids).unwrap();
progression.fetch_add(1, Ordering::Relaxed);
}
wtxn.abort();

View File

@@ -11,38 +11,36 @@ edition.workspace = true
license.workspace = true
[dependencies]
anyhow = "1.0.86"
anyhow = "1.0.79"
bincode = "1.3.3"
csv = "1.3.0"
derive_builder = "0.20.0"
derive_builder = "0.12.0"
dump = { path = "../dump" }
enum-iterator = "2.1.0"
enum-iterator = "1.5.0"
file-store = { path = "../file-store" }
flate2 = "1.0.30"
flate2 = "1.0.28"
meilisearch-auth = { path = "../meilisearch-auth" }
meilisearch-types = { path = "../meilisearch-types" }
page_size = "0.6.0"
rayon = "1.10.0"
roaring = { version = "0.10.6", features = ["serde"] }
serde = { version = "1.0.204", features = ["derive"] }
serde_json = { version = "1.0.120", features = ["preserve_order"] }
page_size = "0.5.0"
puffin = { version = "0.16.0", features = ["serialization"] }
roaring = { version = "0.10.2", features = ["serde"] }
serde = { version = "1.0.195", features = ["derive"] }
serde_json = { version = "1.0.111", features = ["preserve_order"] }
synchronoise = "1.0.1"
tempfile = "3.10.1"
thiserror = "1.0.61"
time = { version = "0.3.36", features = [
tempfile = "3.9.0"
thiserror = "1.0.56"
time = { version = "0.3.31", features = [
"serde-well-known",
"formatting",
"parsing",
"macros",
] }
tracing = "0.1.40"
ureq = "2.10.0"
uuid = { version = "1.10.0", features = ["serde", "v4"] }
ureq = "2.9.1"
uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies]
arroy = "0.4.0"
big_s = "1.0.2"
crossbeam = "0.8.4"
insta = { version = "1.39.0", features = ["json", "redactions"] }
maplit = "1.0.2"
insta = { version = "1.34.0", features = ["json", "redactions"] }
meili-snap = { path = "../meili-snap" }

View File

@@ -870,7 +870,7 @@ mod tests {
debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_imp(ReplaceDocuments,false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
// The third and final case is when the first task doesn't create an index but is directly followed by a task creating an index. In this case we can't batch whit what
// The third and final case is when the first task doesn't create an index but is directly followed by a task creating an index. In this case we can't batch whith what
// follows because we first need to process the erronous batch.
debug_snapshot!(autobatch_from(false,None, [doc_imp(ReplaceDocuments,false, None), settings(true), idx_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
debug_snapshot!(autobatch_from(false,None, [doc_imp(UpdateDocuments, false, None), settings(true), idx_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");

View File

@@ -13,7 +13,7 @@ We can combine the two tasks in a single batch:
1. import documents X and Y
Processing this batch is functionally equivalent to processing the two
tasks individually, but should be much faster since we are only performing
tasks individally, but should be much faster since we are only performing
one indexing operation.
*/
@@ -31,9 +31,6 @@ use meilisearch_types::milli::heed::CompactionOption;
use meilisearch_types::milli::update::{
IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
};
use meilisearch_types::milli::vector::parsed_vectors::{
ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME,
};
use meilisearch_types::milli::{self, Filter};
use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
@@ -145,28 +142,22 @@ pub(crate) enum IndexOperation {
impl Batch {
/// Return the task ids associated with this batch.
pub fn ids(&self) -> RoaringBitmap {
pub fn ids(&self) -> Vec<TaskId> {
match self {
Batch::TaskCancelation { task, .. }
| Batch::Dump(task)
| Batch::IndexCreation { task, .. }
| Batch::IndexUpdate { task, .. } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
}
| Batch::IndexUpdate { task, .. } => vec![task.uid],
Batch::SnapshotCreation(tasks)
| Batch::TaskDeletions(tasks)
| Batch::IndexDeletion { tasks, .. } => {
RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
}
| Batch::IndexDeletion { tasks, .. } => tasks.iter().map(|task| task.uid).collect(),
Batch::IndexOperation { op, .. } => match op {
IndexOperation::DocumentOperation { tasks, .. }
| IndexOperation::Settings { tasks, .. }
| IndexOperation::DocumentClear { tasks, .. } => {
RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
}
IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
tasks.iter().map(|task| task.uid).collect()
}
IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
IndexOperation::SettingsAndDocumentOperation {
document_import_tasks: tasks,
settings_tasks: other,
@@ -176,11 +167,9 @@ impl Batch {
cleared_tasks: tasks,
settings_tasks: other,
..
} => RoaringBitmap::from_iter(tasks.iter().chain(other).map(|task| task.uid)),
} => tasks.iter().chain(other).map(|task| task.uid).collect(),
},
Batch::IndexSwap { task } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
}
Batch::IndexSwap { task } => vec![task.uid],
}
}
@@ -529,6 +518,8 @@ impl IndexScheduler {
#[cfg(test)]
self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
puffin::profile_function!();
let enqueued = &self.get_status(rtxn, Status::Enqueued)?;
let to_cancel = self.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
@@ -637,6 +628,8 @@ impl IndexScheduler {
self.breakpoint(crate::Breakpoint::InsideProcessBatch);
}
puffin::profile_function!(batch.to_string());
match batch {
Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
// 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -784,12 +777,10 @@ impl IndexScheduler {
let dst = temp_snapshot_dir.path().join("auth");
fs::create_dir_all(&dst)?;
// TODO We can't use the open_auth_store_env function here but we should
let auth = unsafe {
milli::heed::EnvOpenOptions::new()
.map_size(1024 * 1024 * 1024) // 1 GiB
.max_dbs(2)
.open(&self.auth_path)
}?;
let auth = milli::heed::EnvOpenOptions::new()
.map_size(1024 * 1024 * 1024) // 1 GiB
.max_dbs(2)
.open(&self.auth_path)?;
auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
// 5. Copy and tarball the flat snapshot
@@ -908,83 +899,20 @@ impl IndexScheduler {
let mut index_dumper = dump.create_index(uid, &metadata)?;
let fields_ids_map = index.fields_ids_map(&rtxn)?;
let dictionary = index.document_decompression_dictionary(&rtxn)?;
let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
let embedding_configs = index.embedding_configs(&rtxn)?;
let mut buffer = Vec::new();
// 3.1. Dump the documents
for ret in index.all_compressed_documents(&rtxn)? {
for ret in index.all_documents(&rtxn)? {
if self.must_stop_processing.get() {
return Err(Error::AbortedTask);
}
let (id, compressed) = ret?;
let doc = compressed.decompress_with_optional_dictionary(
&mut buffer,
dictionary.as_ref(),
)?;
let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
'inject_vectors: {
let embeddings = index.embeddings(&rtxn, id)?;
if embeddings.is_empty() {
break 'inject_vectors;
}
let vectors = document
.entry(RESERVED_VECTORS_FIELD_NAME.to_owned())
.or_insert(serde_json::Value::Object(Default::default()));
let serde_json::Value::Object(vectors) = vectors else {
return Err(milli::Error::UserError(
milli::UserError::InvalidVectorsMapType {
document_id: {
if let Ok(Some(Ok(index))) = index
.external_id_of(&rtxn, std::iter::once(id))
.map(|it| it.into_iter().next())
{
index
} else {
format!("internal docid={id}")
}
},
value: vectors.clone(),
},
)
.into());
};
for (embedder_name, embeddings) in embeddings {
let user_provided = embedding_configs
.iter()
.find(|conf| conf.name == embedder_name)
.is_some_and(|conf| conf.user_provided.contains(id));
let embeddings = ExplicitVectors {
embeddings: Some(
VectorOrArrayOfVectors::from_array_of_vectors(embeddings),
),
regenerate: !user_provided,
};
vectors.insert(
embedder_name,
serde_json::to_value(embeddings).unwrap(),
);
}
}
let (_id, doc) = ret?;
let document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
index_dumper.push_document(&document)?;
}
// 3.2. Dump the settings
let settings = meilisearch_types::settings::settings(
index,
&rtxn,
meilisearch_types::settings::SecretPolicy::RevealSecrets,
)?;
let settings = meilisearch_types::settings::settings(index, &rtxn)?;
index_dumper.settings(&settings)?;
Ok(())
})?;
@@ -1234,6 +1162,8 @@ impl IndexScheduler {
index: &'i Index,
operation: IndexOperation,
) -> Result<Vec<Task>> {
puffin::profile_function!();
match operation {
IndexOperation::DocumentClear { mut tasks, .. } => {
let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;

View File

@@ -48,8 +48,6 @@ impl From<DateField> for Code {
pub enum Error {
#[error("{1}")]
WithCustomErrorCode(Code, Box<Self>),
#[error("Received bad task id: {received} should be >= to {expected}.")]
BadTaskId { received: TaskId, expected: TaskId },
#[error("Index `{0}` not found.")]
IndexNotFound(String),
#[error("Index `{0}` already exists.")]
@@ -163,7 +161,6 @@ impl Error {
match self {
Error::IndexNotFound(_)
| Error::WithCustomErrorCode(_, _)
| Error::BadTaskId { .. }
| Error::IndexAlreadyExists(_)
| Error::SwapDuplicateIndexFound(_)
| Error::SwapDuplicateIndexesFound(_)
@@ -208,7 +205,6 @@ impl ErrorCode for Error {
fn error_code(&self) -> Code {
match self {
Error::WithCustomErrorCode(code, _) => *code,
Error::BadTaskId { .. } => Code::BadRequest,
Error::IndexNotFound(_) => Code::IndexNotFound,
Error::IndexAlreadyExists(_) => Code::IndexAlreadyExists,
Error::SwapDuplicateIndexesFound(_) => Code::InvalidSwapDuplicateIndexFound,

View File

@@ -30,6 +30,19 @@ impl RoFeatures {
self.runtime
}
pub fn check_score_details(&self) -> Result<()> {
if self.runtime.score_details {
Ok(())
} else {
Err(FeatureNotEnabledError {
disabled_action: "Computing score details",
feature: "score details",
issue_link: "https://github.com/meilisearch/product/discussions/674",
}
.into())
}
}
pub fn check_metrics(&self) -> Result<()> {
if self.runtime.metrics {
Ok(())
@@ -48,7 +61,7 @@ impl RoFeatures {
Ok(())
} else {
Err(FeatureNotEnabledError {
disabled_action: "Modifying logs through the `/logs/*` routes",
disabled_action: "getting logs through the `/logs/stream` route",
feature: "logs route",
issue_link: "https://github.com/orgs/meilisearch/discussions/721",
}
@@ -68,6 +81,19 @@ impl RoFeatures {
.into())
}
}
pub fn check_puffin(&self) -> Result<()> {
if self.runtime.export_puffin_reports {
Ok(())
} else {
Err(FeatureNotEnabledError {
disabled_action: "Outputting Puffin reports to disk",
feature: "export puffin reports",
issue_link: "https://github.com/meilisearch/product/discussions/693",
}
.into())
}
}
}
impl FeatureData {

View File

@@ -15,7 +15,6 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
let IndexScheduler {
autobatching_enabled,
cleanup_enabled: _,
must_stop_processing: _,
processing_tasks,
file_store,
@@ -32,6 +31,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
features: _,
max_number_of_tasks: _,
max_number_of_batched_tasks: _,
puffin_frame: _,
wake_up: _,
dumps_path: _,
snapshots_path: _,

File diff suppressed because it is too large Load Diff

View File

@@ -1,15 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: doc
---
{
"doggo": "Intel",
"breed": "beagle",
"_vectors": {
"noise": [
0.1,
0.2,
0.3
]
}
}

View File

@@ -1,20 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: task.details
---
{
"embedders": {
"A_fakerest": {
"source": "rest",
"apiKey": "MyXXXX...",
"dimensions": 384,
"url": "http://localhost:7777"
},
"B_small_hf": {
"source": "huggingFace",
"model": "sentence-transformers/all-MiniLM-L6-v2",
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
"documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
}
}
}

View File

@@ -1,15 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: doc
---
{
"doggo": "kefir",
"breed": "patou",
"_vectors": {
"noise": [
0.1,
0.2,
0.3
]
}
}

View File

@@ -1,23 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: fakerest_config.embedder_options
---
{
"Rest": {
"api_key": "My super secret",
"distribution": null,
"dimensions": 384,
"url": "http://localhost:7777",
"query": null,
"input_field": [
"input"
],
"path_to_embeddings": [
"data"
],
"embedding_object": [
"embedding"
],
"input_type": "text"
}
}

View File

@@ -1,11 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: simple_hf_config.embedder_options
---
{
"HuggingFace": {
"model": "sentence-transformers/all-MiniLM-L6-v2",
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
"distribution": null
}
}

View File

@@ -1,20 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: task.details
---
{
"embedders": {
"A_fakerest": {
"source": "rest",
"apiKey": "MyXXXX...",
"dimensions": 384,
"url": "http://localhost:7777"
},
"B_small_hf": {
"source": "huggingFace",
"model": "sentence-transformers/all-MiniLM-L6-v2",
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
"documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
}
}
}

View File

@@ -1,14 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: task.details
---
{
"embedders": {
"default": {
"source": "rest",
"apiKey": "MyXXXX...",
"dimensions": 4,
"url": "http://localhost:7777"
}
}
}

View File

@@ -1,23 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: embedding_config.embedder_options
---
{
"Rest": {
"api_key": "My super secret",
"distribution": null,
"dimensions": 4,
"url": "http://localhost:7777",
"query": null,
"input_field": [
"input"
],
"path_to_embeddings": [
"data"
],
"embedding_object": [
"embedding"
],
"input_type": "text"
}
}

View File

@@ -1,14 +0,0 @@
---
source: index-scheduler/src/lib.rs
expression: task.details
---
{
"embedders": {
"default": {
"source": "rest",
"apiKey": "MyXXXX...",
"dimensions": 4,
"url": "http://localhost:7777"
}
}
}

View File

@@ -1,49 +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: 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 }}
----------------------------------------------------------------------
### Status:
enqueued []
succeeded [0,1,2,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,2,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,2,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,48 +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: 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 }}
----------------------------------------------------------------------
### Status:
enqueued [2,]
succeeded [0,1,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,2,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,2,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
[timestamp] [2,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
00000000-0000-0000-0000-000000000001
----------------------------------------------------------------------

View File

@@ -1,45 +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: 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:
enqueued []
succeeded [0,1,]
----------------------------------------------------------------------
### Kind:
"documentAdditionOrUpdate" [1,]
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,1,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
[timestamp] [1,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,44 +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: 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:
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

@@ -1,36 +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: 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,]
----------------------------------------------------------------------
### Kind:
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,]
----------------------------------------------------------------------
### Index Mapper:
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
----------------------------------------------------------------------
### Started At:
----------------------------------------------------------------------
### Finished At:
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,40 +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: 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 []
succeeded [0,]
----------------------------------------------------------------------
### Kind:
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,90 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
[
{
"uid": 0,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "succeeded",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 1,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": {
"message": "Index `doggo` already exists.",
"code": "index_already_exists",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#index_already_exists"
},
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "failed",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 2,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 3,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
}
]

View File

@@ -1,90 +0,0 @@
---
source: index-scheduler/src/lib.rs
---
[
{
"uid": 0,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "succeeded",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 1,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": {
"message": "Index `doggo` already exists.",
"code": "index_already_exists",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#index_already_exists"
},
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "failed",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 2,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
},
{
"uid": 3,
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]",
"error": null,
"canceledBy": null,
"details": {
"IndexInfo": {
"primary_key": null
}
},
"status": "enqueued",
"kind": {
"indexCreation": {
"index_uid": "doggo",
"primary_key": null
}
}
}
]

View File

@@ -1,36 +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: 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,]
----------------------------------------------------------------------
### Kind:
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,]
----------------------------------------------------------------------
### Index Mapper:
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
----------------------------------------------------------------------
### Started At:
----------------------------------------------------------------------
### Finished At:
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -1,40 +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: 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 []
succeeded [0,]
----------------------------------------------------------------------
### Kind:
"settingsUpdate" [0,]
----------------------------------------------------------------------
### Index Tasks:
doggos [0,]
----------------------------------------------------------------------
### Index Mapper:
doggos: { number_of_documents: 0, field_distribution: {} }
----------------------------------------------------------------------
### Canceled By:
----------------------------------------------------------------------
### Enqueued At:
[timestamp] [0,]
----------------------------------------------------------------------
### Started At:
[timestamp] [0,]
----------------------------------------------------------------------
### Finished At:
[timestamp] [0,]
----------------------------------------------------------------------
### File Store:
----------------------------------------------------------------------

View File

@@ -272,9 +272,9 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
}
for index_uid in index_uids {
if index_uid == swap.0 {
swap.1.clone_into(index_uid);
*index_uid = swap.1.to_owned();
} else if index_uid == swap.1 {
swap.0.clone_into(index_uid);
*index_uid = swap.0.to_owned();
}
}
}

View File

@@ -1,4 +1,5 @@
use std::borrow::Cow;
use std::convert::TryInto;
use meilisearch_types::heed::{BoxedError, BytesDecode, BytesEncode};
use uuid::Uuid;

View File

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

View File

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

View File

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

View File

@@ -1,6 +1,7 @@
use std::borrow::Cow;
use std::cmp::Reverse;
use std::collections::HashSet;
use std::convert::{TryFrom, TryInto};
use std::fs::create_dir_all;
use std::path::Path;
use std::result::Result as StdResult;
@@ -49,7 +50,7 @@ pub fn open_auth_store_env(path: &Path) -> milli::heed::Result<milli::heed::Env>
let mut options = EnvOpenOptions::new();
options.map_size(AUTH_STORE_SIZE); // 1GB
options.max_dbs(2);
unsafe { options.open(path) }
options.open(path)
}
impl HeedAuthStore {

View File

@@ -11,36 +11,31 @@ edition.workspace = true
license.workspace = true
[dependencies]
actix-web = { version = "4.8.0", default-features = false }
anyhow = "1.0.86"
actix-web = { version = "4.4.1", default-features = false }
anyhow = "1.0.79"
convert_case = "0.6.0"
csv = "1.3.0"
deserr = { version = "0.6.2", features = ["actix-web"] }
either = { version = "1.13.0", features = ["serde"] }
enum-iterator = "2.1.0"
deserr = { version = "0.6.1", features = ["actix-web"] }
either = { version = "1.9.0", features = ["serde"] }
enum-iterator = "1.5.0"
file-store = { path = "../file-store" }
flate2 = "1.0.30"
flate2 = "1.0.28"
fst = "0.4.7"
memmap2 = "0.9.4"
memmap2 = "0.7.1"
milli = { path = "../milli" }
roaring = { version = "0.10.6", features = ["serde"] }
serde = { version = "1.0.204", features = ["derive"] }
roaring = { version = "0.10.2", features = ["serde"] }
serde = { version = "1.0.195", features = ["derive"] }
serde-cs = "0.2.4"
serde_json = "1.0.120"
tar = "0.4.41"
tempfile = "3.10.1"
thiserror = "1.0.61"
time = { version = "0.3.36", features = [
"serde-well-known",
"formatting",
"parsing",
"macros",
] }
tokio = "1.38"
uuid = { version = "1.10.0", features = ["serde", "v4"] }
serde_json = "1.0.111"
tar = "0.4.40"
tempfile = "3.9.0"
thiserror = "1.0.56"
time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
tokio = "1.35"
uuid = { version = "1.6.1", features = ["serde", "v4"] }
[dev-dependencies]
insta = "1.39.0"
insta = "1.34.0"
meili-snap = { path = "../meili-snap" }
[features]
@@ -49,20 +44,13 @@ all-tokenizations = ["milli/all-tokenizations"]
# chinese specialized tokenization
chinese = ["milli/chinese"]
chinese-pinyin = ["milli/chinese-pinyin"]
# hebrew specialized tokenization
hebrew = ["milli/hebrew"]
# japanese specialized tokenization
japanese = ["milli/japanese"]
# korean specialized tokenization
korean = ["milli/korean"]
# thai specialized tokenization
thai = ["milli/thai"]
# allow greek specialized tokenization
greek = ["milli/greek"]
# allow khmer specialized tokenization
khmer = ["milli/khmer"]
# allow vietnamese specialized tokenization
vietnamese = ["milli/vietnamese"]
# force swedish character recomposition
swedish-recomposition = ["milli/swedish-recomposition"]

View File

@@ -26,7 +26,7 @@ pub type DeserrQueryParamError<C = BadRequest> = DeserrError<DeserrQueryParam, C
/// A request deserialization error.
///
/// The first generic parameter is a marker type describing the format of the request: either json (e.g. [`DeserrJson`] or [`DeserrQueryParam`]).
/// The first generic paramater is a marker type describing the format of the request: either json (e.g. [`DeserrJson`] or [`DeserrQueryParam`]).
/// The second generic parameter is the default error code for the deserialization error, in case it is not given.
pub struct DeserrError<Format, C: Default + ErrorCode> {
pub msg: String,
@@ -189,6 +189,3 @@ merge_with_error_impl_take_error_message!(ParseTaskKindError);
merge_with_error_impl_take_error_message!(ParseTaskStatusError);
merge_with_error_impl_take_error_message!(IndexUidFormatError);
merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);
merge_with_error_impl_take_error_message!(InvalidSearchRankingScoreThreshold);
merge_with_error_impl_take_error_message!(InvalidSimilarRankingScoreThreshold);
merge_with_error_impl_take_error_message!(InvalidSimilarId);

View File

@@ -1,6 +1,6 @@
use std::fmt::{self, Debug, Display};
use std::fs::File;
use std::io::{self, BufWriter, Write};
use std::io::{self, Seek, Write};
use std::marker::PhantomData;
use memmap2::MmapOptions;
@@ -104,8 +104,8 @@ impl ErrorCode for DocumentFormatError {
}
/// Reads CSV from input and write an obkv batch to writer.
pub fn read_csv(file: &File, writer: impl Write, delimiter: u8) -> Result<u64> {
let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
pub fn read_csv(file: &File, writer: impl Write + Seek, delimiter: u8) -> Result<u64> {
let mut builder = DocumentsBatchBuilder::new(writer);
let mmap = unsafe { MmapOptions::new().map(file)? };
let csv = csv::ReaderBuilder::new().delimiter(delimiter).from_reader(mmap.as_ref());
builder.append_csv(csv).map_err(|e| (PayloadType::Csv { delimiter }, e))?;
@@ -116,9 +116,9 @@ pub fn read_csv(file: &File, writer: impl Write, delimiter: u8) -> Result<u64> {
Ok(count as u64)
}
/// Reads JSON from temporary file and write an obkv batch to writer.
pub fn read_json(file: &File, writer: impl Write) -> Result<u64> {
let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
/// Reads JSON from temporary file and write an obkv batch to writer.
pub fn read_json(file: &File, writer: impl Write + Seek) -> Result<u64> {
let mut builder = DocumentsBatchBuilder::new(writer);
let mmap = unsafe { MmapOptions::new().map(file)? };
let mut deserializer = serde_json::Deserializer::from_slice(&mmap);
@@ -151,8 +151,8 @@ pub fn read_json(file: &File, writer: impl Write) -> Result<u64> {
}
/// Reads JSON from temporary file and write an obkv batch to writer.
pub fn read_ndjson(file: &File, writer: impl Write) -> Result<u64> {
let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
pub fn read_ndjson(file: &File, writer: impl Write + Seek) -> Result<u64> {
let mut builder = DocumentsBatchBuilder::new(writer);
let mmap = unsafe { MmapOptions::new().map(file)? };
for result in serde_json::Deserializer::from_slice(&mmap).into_iter() {

View File

@@ -2,7 +2,6 @@ use std::{fmt, io};
use actix_web::http::StatusCode;
use actix_web::{self as aweb, HttpResponseBuilder};
use aweb::http::header;
use aweb::rt::task::JoinError;
use convert_case::Casing;
use milli::heed::{Error as HeedError, MdbError};
@@ -57,14 +56,7 @@ where
impl aweb::error::ResponseError for ResponseError {
fn error_response(&self) -> aweb::HttpResponse {
let json = serde_json::to_vec(self).unwrap();
let mut builder = HttpResponseBuilder::new(self.status_code());
builder.content_type("application/json");
if self.code == StatusCode::SERVICE_UNAVAILABLE {
builder.insert_header((header::RETRY_AFTER, "10"));
}
builder.body(json)
HttpResponseBuilder::new(self.status_code()).content_type("application/json").body(json)
}
fn status_code(&self) -> StatusCode {
@@ -222,7 +214,6 @@ InvalidApiKeyUid , InvalidRequest , BAD_REQUEST ;
InvalidContentType , InvalidRequest , UNSUPPORTED_MEDIA_TYPE ;
InvalidDocumentCsvDelimiter , InvalidRequest , BAD_REQUEST ;
InvalidDocumentFields , InvalidRequest , BAD_REQUEST ;
InvalidDocumentRetrieveVectors , InvalidRequest , BAD_REQUEST ;
MissingDocumentFilter , InvalidRequest , BAD_REQUEST ;
InvalidDocumentFilter , InvalidRequest , BAD_REQUEST ;
InvalidDocumentGeoField , InvalidRequest , BAD_REQUEST ;
@@ -240,27 +231,18 @@ InvalidIndexUid , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToSearchOn , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToCrop , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToHighlight , InvalidRequest , BAD_REQUEST ;
InvalidSimilarAttributesToRetrieve , InvalidRequest , BAD_REQUEST ;
InvalidSimilarRetrieveVectors , InvalidRequest , BAD_REQUEST ;
InvalidSearchAttributesToRetrieve , InvalidRequest , BAD_REQUEST ;
InvalidSearchRankingScoreThreshold , InvalidRequest , BAD_REQUEST ;
InvalidSimilarRankingScoreThreshold , InvalidRequest , BAD_REQUEST ;
InvalidSearchRetrieveVectors , InvalidRequest , BAD_REQUEST ;
InvalidSearchCropLength , InvalidRequest , BAD_REQUEST ;
InvalidSearchCropMarker , InvalidRequest , BAD_REQUEST ;
InvalidSearchFacets , InvalidRequest , BAD_REQUEST ;
InvalidSearchSemanticRatio , InvalidRequest , BAD_REQUEST ;
InvalidFacetSearchFacetName , InvalidRequest , BAD_REQUEST ;
InvalidSimilarId , InvalidRequest , BAD_REQUEST ;
InvalidSearchFilter , InvalidRequest , BAD_REQUEST ;
InvalidSimilarFilter , InvalidRequest , BAD_REQUEST ;
InvalidSearchHighlightPostTag , InvalidRequest , BAD_REQUEST ;
InvalidSearchHighlightPreTag , InvalidRequest , BAD_REQUEST ;
InvalidSearchHitsPerPage , InvalidRequest , BAD_REQUEST ;
InvalidSimilarLimit , InvalidRequest , BAD_REQUEST ;
InvalidSearchLimit , InvalidRequest , BAD_REQUEST ;
InvalidSearchMatchingStrategy , InvalidRequest , BAD_REQUEST ;
InvalidSimilarOffset , InvalidRequest , BAD_REQUEST ;
InvalidSearchOffset , InvalidRequest , BAD_REQUEST ;
InvalidSearchPage , InvalidRequest , BAD_REQUEST ;
InvalidSearchQ , InvalidRequest , BAD_REQUEST ;
@@ -269,18 +251,14 @@ InvalidFacetSearchName , InvalidRequest , BAD_REQUEST ;
InvalidSearchVector , InvalidRequest , BAD_REQUEST ;
InvalidSearchShowMatchesPosition , InvalidRequest , BAD_REQUEST ;
InvalidSearchShowRankingScore , InvalidRequest , BAD_REQUEST ;
InvalidSimilarShowRankingScore , InvalidRequest , BAD_REQUEST ;
InvalidSearchShowRankingScoreDetails , InvalidRequest , BAD_REQUEST ;
InvalidSimilarShowRankingScoreDetails , InvalidRequest , BAD_REQUEST ;
InvalidSearchSort , InvalidRequest , BAD_REQUEST ;
InvalidSearchDistinct , InvalidRequest , BAD_REQUEST ;
InvalidSettingsDisplayedAttributes , InvalidRequest , BAD_REQUEST ;
InvalidSettingsDistinctAttribute , InvalidRequest , BAD_REQUEST ;
InvalidSettingsProximityPrecision , InvalidRequest , BAD_REQUEST ;
InvalidSettingsFaceting , InvalidRequest , BAD_REQUEST ;
InvalidSettingsFilterableAttributes , InvalidRequest , BAD_REQUEST ;
InvalidSettingsPagination , InvalidRequest , BAD_REQUEST ;
InvalidSettingsSearchCutoffMs , InvalidRequest , BAD_REQUEST ;
InvalidSettingsEmbedders , InvalidRequest , BAD_REQUEST ;
InvalidSettingsRankingRules , InvalidRequest , BAD_REQUEST ;
InvalidSettingsSearchableAttributes , InvalidRequest , BAD_REQUEST ;
@@ -326,7 +304,6 @@ MissingSwapIndexes , InvalidRequest , BAD_REQUEST ;
MissingTaskFilters , InvalidRequest , BAD_REQUEST ;
NoSpaceLeftOnDevice , System , UNPROCESSABLE_ENTITY;
PayloadTooLarge , InvalidRequest , PAYLOAD_TOO_LARGE ;
TooManySearchRequests , System , SERVICE_UNAVAILABLE ;
TaskNotFound , InvalidRequest , NOT_FOUND ;
TooManyOpenFiles , System , UNPROCESSABLE_ENTITY ;
TooManyVectors , InvalidRequest , BAD_REQUEST ;
@@ -335,8 +312,7 @@ UnretrievableErrorCode , InvalidRequest , BAD_REQUEST ;
UnsupportedMediaType , InvalidRequest , UNSUPPORTED_MEDIA_TYPE ;
// Experimental features
VectorEmbeddingError , InvalidRequest , BAD_REQUEST ;
NotFoundSimilarId , InvalidRequest , BAD_REQUEST
VectorEmbeddingError , InvalidRequest , BAD_REQUEST
}
impl ErrorCode for JoinError {
@@ -373,10 +349,6 @@ impl ErrorCode for milli::Error {
UserError::InvalidFieldForSource { .. }
| UserError::MissingFieldForSource { .. }
| UserError::InvalidOpenAiModel { .. }
| UserError::InvalidOpenAiModelDimensions { .. }
| UserError::InvalidOpenAiModelDimensionsMax { .. }
| UserError::InvalidSettingsDimensions { .. }
| UserError::InvalidUrl { .. }
| UserError::InvalidPrompt(_) => Code::InvalidSettingsEmbedders,
UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
@@ -385,7 +357,6 @@ impl ErrorCode for milli::Error {
Code::IndexPrimaryKeyMultipleCandidatesFound
}
UserError::PrimaryKeyCannotBeChanged(_) => Code::IndexPrimaryKeyAlreadyExists,
UserError::InvalidDistinctAttribute { .. } => Code::InvalidSearchDistinct,
UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
@@ -398,8 +369,8 @@ impl ErrorCode for milli::Error {
UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
UserError::InvalidVectorsMapType { .. }
| UserError::InvalidVectorsEmbedderConf { .. } => Code::InvalidVectorsType,
UserError::InvalidVectorsMapType { .. } => Code::InvalidVectorsType,
UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
UserError::TooManyVectors(_, _) => Code::TooManyVectors,
UserError::SortError(_) => Code::InvalidSearchSort,
UserError::InvalidMinTypoWordLenSetting(_, _) => {
@@ -438,6 +409,7 @@ impl ErrorCode for HeedError {
HeedError::Mdb(_)
| HeedError::Encoding(_)
| HeedError::Decoding(_)
| HeedError::InvalidDatabaseTyping
| HeedError::DatabaseClosing
| HeedError::BadOpenOptions { .. } => Code::Internal,
}
@@ -502,32 +474,6 @@ impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
}
}
impl fmt::Display for deserr_codes::InvalidSimilarId {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(
f,
"the value of `id` is invalid. \
A document identifier can be of type integer or string, \
only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."
)
}
}
impl fmt::Display for deserr_codes::InvalidSearchRankingScoreThreshold {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(
f,
"the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`."
)
}
}
impl fmt::Display for deserr_codes::InvalidSimilarRankingScoreThreshold {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
deserr_codes::InvalidSearchRankingScoreThreshold.fmt(f)
}
}
#[macro_export]
macro_rules! internal_error {
($target:ty : $($other:path), *) => {

View File

@@ -3,9 +3,11 @@ use serde::{Deserialize, Serialize};
#[derive(Serialize, Deserialize, Debug, Clone, Copy, Default, PartialEq, Eq)]
#[serde(rename_all = "camelCase", default)]
pub struct RuntimeTogglableFeatures {
pub score_details: bool,
pub vector_store: bool,
pub metrics: bool,
pub logs_route: bool,
pub export_puffin_reports: bool,
}
#[derive(Default, Debug, Clone, Copy)]

View File

@@ -12,7 +12,7 @@ pub mod star_or;
pub mod task_view;
pub mod tasks;
pub mod versioning;
pub use milli::{heed, zstd, Index};
pub use milli::{heed, Index};
use uuid::Uuid;
pub use versioning::VERSION_FILE_NAME;
pub use {milli, serde_cs};

View File

@@ -3,12 +3,11 @@ use std::convert::Infallible;
use std::fmt;
use std::marker::PhantomData;
use std::num::NonZeroUsize;
use std::ops::{ControlFlow, Deref};
use std::ops::ControlFlow;
use std::str::FromStr;
use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
use fst::IntoStreamer;
use milli::index::IndexEmbeddingConfig;
use milli::proximity::ProximityPrecision;
use milli::update::Setting;
use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
@@ -144,13 +143,21 @@ impl MergeWithError<milli::CriterionError> for DeserrJsonError<InvalidSettingsRa
)]
#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
pub struct Settings<T> {
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[serde(
default,
serialize_with = "serialize_with_wildcard",
skip_serializing_if = "Setting::is_not_set"
)]
#[deserr(default, error = DeserrJsonError<InvalidSettingsDisplayedAttributes>)]
pub displayed_attributes: WildcardSetting,
pub displayed_attributes: Setting<Vec<String>>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[serde(
default,
serialize_with = "serialize_with_wildcard",
skip_serializing_if = "Setting::is_not_set"
)]
#[deserr(default, error = DeserrJsonError<InvalidSettingsSearchableAttributes>)]
pub searchable_attributes: WildcardSetting,
pub searchable_attributes: Setting<Vec<String>>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default, error = DeserrJsonError<InvalidSettingsFilterableAttributes>)]
@@ -195,57 +202,17 @@ pub struct Settings<T> {
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default, error = DeserrJsonError<InvalidSettingsEmbedders>)]
pub embedders: Setting<BTreeMap<String, Setting<milli::vector::settings::EmbeddingSettings>>>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default, error = DeserrJsonError<InvalidSettingsSearchCutoffMs>)]
pub search_cutoff_ms: Setting<u64>,
#[serde(skip)]
#[deserr(skip)]
pub _kind: PhantomData<T>,
}
impl<T> Settings<T> {
pub fn hide_secrets(&mut self) {
let Setting::Set(embedders) = &mut self.embedders else {
return;
};
for mut embedder in embedders.values_mut() {
let Setting::Set(embedder) = &mut embedder else {
continue;
};
let Setting::Set(api_key) = &mut embedder.api_key else {
continue;
};
Self::hide_secret(api_key);
}
}
fn hide_secret(secret: &mut String) {
match secret.len() {
x if x < 10 => {
secret.replace_range(.., "XXX...");
}
x if x < 20 => {
secret.replace_range(2.., "XXXX...");
}
x if x < 30 => {
secret.replace_range(3.., "XXXXX...");
}
_x => {
secret.replace_range(5.., "XXXXXX...");
}
}
}
}
impl Settings<Checked> {
pub fn cleared() -> Settings<Checked> {
Settings {
displayed_attributes: Setting::Reset.into(),
searchable_attributes: Setting::Reset.into(),
displayed_attributes: Setting::Reset,
searchable_attributes: Setting::Reset,
filterable_attributes: Setting::Reset,
sortable_attributes: Setting::Reset,
ranking_rules: Setting::Reset,
@@ -260,7 +227,6 @@ impl Settings<Checked> {
faceting: Setting::Reset,
pagination: Setting::Reset,
embedders: Setting::Reset,
search_cutoff_ms: Setting::Reset,
_kind: PhantomData,
}
}
@@ -283,7 +249,6 @@ impl Settings<Checked> {
faceting,
pagination,
embedders,
search_cutoff_ms,
..
} = self;
@@ -304,7 +269,6 @@ impl Settings<Checked> {
faceting,
pagination,
embedders,
search_cutoff_ms,
_kind: PhantomData,
}
}
@@ -312,7 +276,7 @@ impl Settings<Checked> {
impl Settings<Unchecked> {
pub fn check(self) -> Settings<Checked> {
let displayed_attributes = match self.displayed_attributes.0 {
let displayed_attributes = match self.displayed_attributes {
Setting::Set(fields) => {
if fields.iter().any(|f| f == "*") {
Setting::Reset
@@ -323,7 +287,7 @@ impl Settings<Unchecked> {
otherwise => otherwise,
};
let searchable_attributes = match self.searchable_attributes.0 {
let searchable_attributes = match self.searchable_attributes {
Setting::Set(fields) => {
if fields.iter().any(|f| f == "*") {
Setting::Reset
@@ -335,8 +299,8 @@ impl Settings<Unchecked> {
};
Settings {
displayed_attributes: displayed_attributes.into(),
searchable_attributes: searchable_attributes.into(),
displayed_attributes,
searchable_attributes,
filterable_attributes: self.filterable_attributes,
sortable_attributes: self.sortable_attributes,
ranking_rules: self.ranking_rules,
@@ -351,7 +315,6 @@ impl Settings<Unchecked> {
faceting: self.faceting,
pagination: self.pagination,
embedders: self.embedders,
search_cutoff_ms: self.search_cutoff_ms,
_kind: PhantomData,
}
}
@@ -384,40 +347,19 @@ pub fn apply_settings_to_builder(
settings: &Settings<Checked>,
builder: &mut milli::update::Settings,
) {
let Settings {
displayed_attributes,
searchable_attributes,
filterable_attributes,
sortable_attributes,
ranking_rules,
stop_words,
non_separator_tokens,
separator_tokens,
dictionary,
synonyms,
distinct_attribute,
proximity_precision,
typo_tolerance,
faceting,
pagination,
embedders,
search_cutoff_ms,
_kind,
} = settings;
match searchable_attributes.deref() {
match settings.searchable_attributes {
Setting::Set(ref names) => builder.set_searchable_fields(names.clone()),
Setting::Reset => builder.reset_searchable_fields(),
Setting::NotSet => (),
}
match displayed_attributes.deref() {
match settings.displayed_attributes {
Setting::Set(ref names) => builder.set_displayed_fields(names.clone()),
Setting::Reset => builder.reset_displayed_fields(),
Setting::NotSet => (),
}
match filterable_attributes {
match settings.filterable_attributes {
Setting::Set(ref facets) => {
builder.set_filterable_fields(facets.clone().into_iter().collect())
}
@@ -425,13 +367,13 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match sortable_attributes {
match settings.sortable_attributes {
Setting::Set(ref fields) => builder.set_sortable_fields(fields.iter().cloned().collect()),
Setting::Reset => builder.reset_sortable_fields(),
Setting::NotSet => (),
}
match ranking_rules {
match settings.ranking_rules {
Setting::Set(ref criteria) => {
builder.set_criteria(criteria.iter().map(|c| c.clone().into()).collect())
}
@@ -439,13 +381,13 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match stop_words {
match settings.stop_words {
Setting::Set(ref stop_words) => builder.set_stop_words(stop_words.clone()),
Setting::Reset => builder.reset_stop_words(),
Setting::NotSet => (),
}
match non_separator_tokens {
match settings.non_separator_tokens {
Setting::Set(ref non_separator_tokens) => {
builder.set_non_separator_tokens(non_separator_tokens.clone())
}
@@ -453,7 +395,7 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match separator_tokens {
match settings.separator_tokens {
Setting::Set(ref separator_tokens) => {
builder.set_separator_tokens(separator_tokens.clone())
}
@@ -461,31 +403,31 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match dictionary {
match settings.dictionary {
Setting::Set(ref dictionary) => builder.set_dictionary(dictionary.clone()),
Setting::Reset => builder.reset_dictionary(),
Setting::NotSet => (),
}
match synonyms {
match settings.synonyms {
Setting::Set(ref synonyms) => builder.set_synonyms(synonyms.clone().into_iter().collect()),
Setting::Reset => builder.reset_synonyms(),
Setting::NotSet => (),
}
match distinct_attribute {
match settings.distinct_attribute {
Setting::Set(ref attr) => builder.set_distinct_field(attr.clone()),
Setting::Reset => builder.reset_distinct_field(),
Setting::NotSet => (),
}
match proximity_precision {
match settings.proximity_precision {
Setting::Set(ref precision) => builder.set_proximity_precision((*precision).into()),
Setting::Reset => builder.reset_proximity_precision(),
Setting::NotSet => (),
}
match typo_tolerance {
match settings.typo_tolerance {
Setting::Set(ref value) => {
match value.enabled {
Setting::Set(val) => builder.set_autorize_typos(val),
@@ -540,7 +482,7 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match faceting {
match &settings.faceting {
Setting::Set(FacetingSettings { max_values_per_facet, sort_facet_values_by }) => {
match max_values_per_facet {
Setting::Set(val) => builder.set_max_values_per_facet(*val),
@@ -562,7 +504,7 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match pagination {
match settings.pagination {
Setting::Set(ref value) => match value.max_total_hits {
Setting::Set(val) => builder.set_pagination_max_total_hits(val),
Setting::Reset => builder.reset_pagination_max_total_hits(),
@@ -572,28 +514,16 @@ pub fn apply_settings_to_builder(
Setting::NotSet => (),
}
match embedders {
Setting::Set(value) => builder.set_embedder_settings(value.clone()),
match settings.embedders.clone() {
Setting::Set(value) => builder.set_embedder_settings(value),
Setting::Reset => builder.reset_embedder_settings(),
Setting::NotSet => (),
}
match search_cutoff_ms {
Setting::Set(cutoff) => builder.set_search_cutoff(*cutoff),
Setting::Reset => builder.reset_search_cutoff(),
Setting::NotSet => (),
}
}
pub enum SecretPolicy {
RevealSecrets,
HideSecrets,
}
pub fn settings(
index: &Index,
rtxn: &crate::heed::RoTxn,
secret_policy: SecretPolicy,
) -> Result<Settings<Checked>, milli::Error> {
let displayed_attributes =
index.displayed_fields(rtxn)?.map(|fields| fields.into_iter().map(String::from).collect());
@@ -673,23 +603,19 @@ pub fn settings(
let embedders: BTreeMap<_, _> = index
.embedding_configs(rtxn)?
.into_iter()
.map(|IndexEmbeddingConfig { name, config, .. }| (name, Setting::Set(config.into())))
.map(|(name, config)| (name, Setting::Set(config.into())))
.collect();
let embedders = if embedders.is_empty() { Setting::NotSet } else { Setting::Set(embedders) };
let search_cutoff_ms = index.search_cutoff(rtxn)?;
let mut settings = Settings {
Ok(Settings {
displayed_attributes: match displayed_attributes {
Some(attrs) => Setting::Set(attrs),
None => Setting::Reset,
}
.into(),
},
searchable_attributes: match searchable_attributes {
Some(attrs) => Setting::Set(attrs),
None => Setting::Reset,
}
.into(),
},
filterable_attributes: Setting::Set(filterable_attributes),
sortable_attributes: Setting::Set(sortable_attributes),
ranking_rules: Setting::Set(criteria.iter().map(|c| c.clone().into()).collect()),
@@ -707,18 +633,8 @@ pub fn settings(
faceting: Setting::Set(faceting),
pagination: Setting::Set(pagination),
embedders,
search_cutoff_ms: match search_cutoff_ms {
Some(cutoff) => Setting::Set(cutoff),
None => Setting::Reset,
},
_kind: PhantomData,
};
if let SecretPolicy::HideSecrets = secret_policy {
settings.hide_secrets()
}
Ok(settings)
})
}
#[derive(Debug, Clone, PartialEq, Eq, Deserr)]
@@ -843,41 +759,6 @@ impl From<ProximityPrecisionView> for ProximityPrecision {
}
}
#[derive(Debug, Clone, Default, Deserialize, PartialEq, Eq)]
pub struct WildcardSetting(Setting<Vec<String>>);
impl From<Setting<Vec<String>>> for WildcardSetting {
fn from(setting: Setting<Vec<String>>) -> Self {
Self(setting)
}
}
impl Serialize for WildcardSetting {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
serialize_with_wildcard(&self.0, serializer)
}
}
impl<E: deserr::DeserializeError> Deserr<E> for WildcardSetting {
fn deserialize_from_value<V: deserr::IntoValue>(
value: deserr::Value<V>,
location: ValuePointerRef<'_>,
) -> Result<Self, E> {
Ok(Self(Setting::deserialize_from_value(value, location)?))
}
}
impl std::ops::Deref for WildcardSetting {
type Target = Setting<Vec<String>>;
fn deref(&self) -> &Self::Target {
&self.0
}
}
#[cfg(test)]
pub(crate) mod test {
use super::*;
@@ -886,8 +767,8 @@ pub(crate) mod test {
fn test_setting_check() {
// test no changes
let settings = Settings {
displayed_attributes: Setting::Set(vec![String::from("hello")]).into(),
searchable_attributes: Setting::Set(vec![String::from("hello")]).into(),
displayed_attributes: Setting::Set(vec![String::from("hello")]),
searchable_attributes: Setting::Set(vec![String::from("hello")]),
filterable_attributes: Setting::NotSet,
sortable_attributes: Setting::NotSet,
ranking_rules: Setting::NotSet,
@@ -902,7 +783,6 @@ pub(crate) mod test {
faceting: Setting::NotSet,
pagination: Setting::NotSet,
embedders: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
_kind: PhantomData::<Unchecked>,
};
@@ -913,9 +793,8 @@ pub(crate) mod test {
// test wildcard
// test no changes
let settings = Settings {
displayed_attributes: Setting::Set(vec![String::from("*")]).into(),
searchable_attributes: Setting::Set(vec![String::from("hello"), String::from("*")])
.into(),
displayed_attributes: Setting::Set(vec![String::from("*")]),
searchable_attributes: Setting::Set(vec![String::from("hello"), String::from("*")]),
filterable_attributes: Setting::NotSet,
sortable_attributes: Setting::NotSet,
ranking_rules: Setting::NotSet,
@@ -930,12 +809,11 @@ pub(crate) mod test {
faceting: Setting::NotSet,
pagination: Setting::NotSet,
embedders: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
_kind: PhantomData::<Unchecked>,
};
let checked = settings.check();
assert_eq!(checked.displayed_attributes, Setting::Reset.into());
assert_eq!(checked.searchable_attributes, Setting::Reset.into());
assert_eq!(checked.displayed_attributes, Setting::Reset);
assert_eq!(checked.searchable_attributes, Setting::Reset);
}
}

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