MeiliSearch/dump/src/lib.rs

496 lines
17 KiB
Rust
Raw Normal View History

2022-10-22 16:35:42 +02:00
#![allow(clippy::type_complexity)]
#![allow(clippy::wrong_self_convention)]
2022-10-20 18:00:07 +02:00
use meilisearch_types::error::ResponseError;
use meilisearch_types::keys::Key;
use meilisearch_types::milli::update::IndexDocumentsMethod;
use meilisearch_types::settings::Unchecked;
use meilisearch_types::tasks::{Details, IndexSwap, KindWithContent, Status, Task, TaskId};
2022-10-20 18:00:07 +02:00
use meilisearch_types::InstanceUid;
2022-10-17 15:11:35 +02:00
use roaring::RoaringBitmap;
2022-09-29 16:17:06 +02:00
use serde::{Deserialize, Serialize};
use time::OffsetDateTime;
mod error;
2022-10-03 16:12:01 +02:00
mod reader;
mod writer;
pub use error::Error;
2022-10-16 01:39:01 +02:00
pub use reader::{DumpReader, UpdateFile};
pub use writer::DumpWriter;
2022-09-29 16:17:06 +02:00
2022-10-03 16:12:01 +02:00
const CURRENT_DUMP_VERSION: Version = Version::V6;
2022-09-29 16:17:06 +02:00
type Result<T> = std::result::Result<T, Error>;
2022-11-30 14:51:21 +01:00
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
2022-09-29 16:17:06 +02:00
#[serde(rename_all = "camelCase")]
pub struct Metadata {
2022-10-03 16:12:01 +02:00
pub dump_version: Version,
2022-09-29 16:17:06 +02:00
pub db_version: String,
2022-10-03 16:12:01 +02:00
#[serde(with = "time::serde::rfc3339")]
2022-09-29 16:17:06 +02:00
pub dump_date: OffsetDateTime,
}
2022-10-03 16:12:01 +02:00
2022-11-30 14:51:21 +01:00
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
2022-10-04 19:13:30 +02:00
#[serde(rename_all = "camelCase")]
pub struct IndexMetadata {
pub uid: String,
pub primary_key: Option<String>,
#[serde(with = "time::serde::rfc3339")]
pub created_at: OffsetDateTime,
#[serde(with = "time::serde::rfc3339")]
pub updated_at: OffsetDateTime,
}
2022-11-30 14:51:21 +01:00
#[derive(Debug, Clone, Copy, PartialEq, Eq, Deserialize, Serialize)]
2022-10-03 16:12:01 +02:00
pub enum Version {
V1,
V2,
V3,
V4,
V5,
V6,
}
2022-10-03 18:50:06 +02:00
2022-10-16 01:39:01 +02:00
#[derive(Debug, PartialEq, Serialize, Deserialize)]
2022-10-13 16:03:23 +02:00
#[serde(rename_all = "camelCase")]
pub struct TaskDump {
pub uid: TaskId,
#[serde(default)]
pub index_uid: Option<String>,
pub status: Status,
#[serde(rename = "type")]
pub kind: KindDump,
#[serde(skip_serializing_if = "Option::is_none")]
pub canceled_by: Option<TaskId>,
2022-10-13 16:03:23 +02:00
#[serde(skip_serializing_if = "Option::is_none")]
pub details: Option<Details>,
#[serde(skip_serializing_if = "Option::is_none")]
pub error: Option<ResponseError>,
#[serde(with = "time::serde::rfc3339")]
pub enqueued_at: OffsetDateTime,
#[serde(
with = "time::serde::rfc3339::option",
skip_serializing_if = "Option::is_none",
default
)]
pub started_at: Option<OffsetDateTime>,
#[serde(
with = "time::serde::rfc3339::option",
skip_serializing_if = "Option::is_none",
default
)]
pub finished_at: Option<OffsetDateTime>,
}
Bring back `release-v0.30.0` into `release-v0.30.0-temp` (final: into `main`) (#3145) * Fix error code of the "duplicate index found" error * Use the content of the ProcessingTasks in the tasks cancelation system * Change the missing_filters error code into missing_task_filters * WIP Introduce the invalid_task_uid error code * Use more precise error codes/message for the task routes + Allow star operator in delete/cancel tasks + rename originalQuery to originalFilters + Display error/canceled_by in task view even when they are = null + Rename task filter fields by using their plural forms + Prepare an error code for canceledBy filter + Only return global tasks if the API key action `index.*` is there * Add canceledBy task filter * Update tests following task API changes * Rename original_query to original_filters everywhere * Update more insta-snap tests * Make clippy happy They're a happy clip now. * Make rustfmt happy >:-( * Fix Index name parsing error message to fit the specification * Bump milli version to 0.35.1 * Fix the new error messages * fix the error messages and add tests * rename the error codes for the sake of consistency * refactor the way we send the cli informations + add the analytics for the config file and ssl usage * Apply suggestions from code review Co-authored-by: Clément Renault <clement@meilisearch.com> * add a comment over the new infos structure * reformat, sorry @kero * Store analytics for the documents deletions * Add analytics on all the settings * Spawn threads with names * Spawn rayon threads with names * update the distinct attributes to the spec update * update the analytics on the search route * implements the analytics on the health and version routes * Fix task details serialization * Add the question mark to the task deletion query filter * Add the question mark to the task cancelation query filter * Fix tests * add analytics on the task route * Add all the missing fields of the new task query type * Create a new analytics for the task deletion * Create a new analytics for the task creation * batch the tasks seen events * Update the finite pagination analytics * add the analytics of the swap-indexes route * Stop removing the DB when failing to read it * Rename originalFilters into originalFilters * Rename matchedDocuments into providedIds * Add `workflow_dispatch` to flaky.yml * Bump grenad to 0.4.4 * Bump milli to version v0.37.0 * Don't multiply total memory returned by sysinfo anymore sysinfo now returns bytes rather than KB * Add a dispatch to the publish binaries workflow * Fix publish release CI * Don't use gold but the default linker * Always display details for the indexDeletion task * Fix the insta tests * refactorize the whole test suite 1. Make a call to assert_internally_consistent automatically when snapshoting the scheduler. There is no point in snapshoting something broken and expect the dumb humans to notice. 2. Replace every possible call to assert_internally_consistent by a snapshot of the scheduler. It takes as many lines and ensure we never change something without noticing in any tests ever. 3. Name every snapshots: it's easier to debug when something goes wrong and easier to review in general. 4. Stop skipping breakpoints, it's too easy to miss something. Now you must explicitely show which path is the scheduler supposed to use. 5. Add a timeout on the channel.recv, it eases the process of writing tests, now when something file you get a failure instead of a deadlock. * rebase on release-v0.30 * makes clippy happy * update the snapshots after a rebase * try to remove the flakyness of the failing test * Add more analytics on the ranking rules positions * Update the dump test to check for the dumpUid dumpCreation task details * send the ranking rules as a string because amplitude is too dumb to process an array as a single value * Display a null dumpUid until we computed the dump itself on disk * Update tests * Check if the master key is missing before returning an error Co-authored-by: Loïc Lecrenier <loic.lecrenier@me.com> Co-authored-by: bors[bot] <26634292+bors[bot]@users.noreply.github.com> Co-authored-by: Kerollmops <clement@meilisearch.com> Co-authored-by: ManyTheFish <many@meilisearch.com> Co-authored-by: Tamo <tamo@meilisearch.com> Co-authored-by: Louis Dureuil <louis@meilisearch.com>
2022-11-28 16:27:41 +01:00
// A `Kind` specific version made for the dump. If modified you may break the dump.
2022-10-16 01:39:01 +02:00
#[derive(Debug, PartialEq, Serialize, Deserialize)]
2022-10-13 16:03:23 +02:00
#[serde(rename_all = "camelCase")]
pub enum KindDump {
DocumentImport {
primary_key: Option<String>,
method: IndexDocumentsMethod,
documents_count: u64,
allow_index_creation: bool,
},
DocumentDeletion {
documents_ids: Vec<String>,
},
DocumentClear,
DocumentDeletionByFilter {
filter: serde_json::Value,
},
2022-10-13 16:03:23 +02:00
Settings {
2022-10-22 16:35:42 +02:00
settings: Box<meilisearch_types::settings::Settings<Unchecked>>,
2022-10-13 16:03:23 +02:00
is_deletion: bool,
allow_index_creation: bool,
},
IndexDeletion,
IndexCreation {
primary_key: Option<String>,
},
IndexUpdate {
primary_key: Option<String>,
},
2022-10-26 13:43:57 +02:00
IndexSwap {
swaps: Vec<IndexSwap>,
},
TaskCancelation {
query: String,
tasks: RoaringBitmap,
2022-10-13 16:03:23 +02:00
},
2022-10-17 18:11:28 +02:00
TasksDeletion {
2022-10-13 16:03:23 +02:00
query: String,
2022-10-17 15:11:35 +02:00
tasks: RoaringBitmap,
2022-10-13 16:03:23 +02:00
},
2022-10-24 19:08:15 +02:00
DumpCreation {
keys: Vec<Key>,
instance_uid: Option<InstanceUid>,
2022-10-16 01:39:01 +02:00
},
SnapshotCreation,
2022-10-13 16:03:23 +02:00
}
impl From<Task> for TaskDump {
fn from(task: Task) -> Self {
TaskDump {
uid: task.uid,
index_uid: task.index_uid().map(|uid| uid.to_string()),
status: task.status,
kind: task.kind.into(),
canceled_by: task.canceled_by,
2022-10-13 16:03:23 +02:00
details: task.details,
error: task.error,
enqueued_at: task.enqueued_at,
started_at: task.started_at,
finished_at: task.finished_at,
}
}
}
impl From<KindWithContent> for KindDump {
fn from(kind: KindWithContent) -> Self {
match kind {
KindWithContent::DocumentAdditionOrUpdate {
2022-10-13 16:03:23 +02:00
primary_key,
method,
documents_count,
allow_index_creation,
..
} => KindDump::DocumentImport {
primary_key,
method,
documents_count,
allow_index_creation,
},
KindWithContent::DocumentEdition { .. } => todo!(),
2022-10-13 16:03:23 +02:00
KindWithContent::DocumentDeletion { documents_ids, .. } => {
KindDump::DocumentDeletion { documents_ids }
}
KindWithContent::DocumentDeletionByFilter { filter_expr, .. } => {
KindDump::DocumentDeletionByFilter { filter: filter_expr }
}
2022-10-13 16:03:23 +02:00
KindWithContent::DocumentClear { .. } => KindDump::DocumentClear,
KindWithContent::SettingsUpdate {
new_settings,
is_deletion,
allow_index_creation,
..
2022-10-20 18:00:07 +02:00
} => KindDump::Settings { settings: new_settings, is_deletion, allow_index_creation },
2022-10-13 16:03:23 +02:00
KindWithContent::IndexDeletion { .. } => KindDump::IndexDeletion,
KindWithContent::IndexCreation { primary_key, .. } => {
KindDump::IndexCreation { primary_key }
}
KindWithContent::IndexUpdate { primary_key, .. } => {
KindDump::IndexUpdate { primary_key }
}
2022-10-17 16:30:18 +02:00
KindWithContent::IndexSwap { swaps } => KindDump::IndexSwap { swaps },
KindWithContent::TaskCancelation { query, tasks } => {
KindDump::TaskCancelation { query, tasks }
}
2022-10-17 15:11:35 +02:00
KindWithContent::TaskDeletion { query, tasks } => {
2022-10-17 18:11:28 +02:00
KindDump::TasksDeletion { query, tasks }
2022-10-17 15:11:35 +02:00
}
Bring back `release-v0.30.0` into `release-v0.30.0-temp` (final: into `main`) (#3145) * Fix error code of the "duplicate index found" error * Use the content of the ProcessingTasks in the tasks cancelation system * Change the missing_filters error code into missing_task_filters * WIP Introduce the invalid_task_uid error code * Use more precise error codes/message for the task routes + Allow star operator in delete/cancel tasks + rename originalQuery to originalFilters + Display error/canceled_by in task view even when they are = null + Rename task filter fields by using their plural forms + Prepare an error code for canceledBy filter + Only return global tasks if the API key action `index.*` is there * Add canceledBy task filter * Update tests following task API changes * Rename original_query to original_filters everywhere * Update more insta-snap tests * Make clippy happy They're a happy clip now. * Make rustfmt happy >:-( * Fix Index name parsing error message to fit the specification * Bump milli version to 0.35.1 * Fix the new error messages * fix the error messages and add tests * rename the error codes for the sake of consistency * refactor the way we send the cli informations + add the analytics for the config file and ssl usage * Apply suggestions from code review Co-authored-by: Clément Renault <clement@meilisearch.com> * add a comment over the new infos structure * reformat, sorry @kero * Store analytics for the documents deletions * Add analytics on all the settings * Spawn threads with names * Spawn rayon threads with names * update the distinct attributes to the spec update * update the analytics on the search route * implements the analytics on the health and version routes * Fix task details serialization * Add the question mark to the task deletion query filter * Add the question mark to the task cancelation query filter * Fix tests * add analytics on the task route * Add all the missing fields of the new task query type * Create a new analytics for the task deletion * Create a new analytics for the task creation * batch the tasks seen events * Update the finite pagination analytics * add the analytics of the swap-indexes route * Stop removing the DB when failing to read it * Rename originalFilters into originalFilters * Rename matchedDocuments into providedIds * Add `workflow_dispatch` to flaky.yml * Bump grenad to 0.4.4 * Bump milli to version v0.37.0 * Don't multiply total memory returned by sysinfo anymore sysinfo now returns bytes rather than KB * Add a dispatch to the publish binaries workflow * Fix publish release CI * Don't use gold but the default linker * Always display details for the indexDeletion task * Fix the insta tests * refactorize the whole test suite 1. Make a call to assert_internally_consistent automatically when snapshoting the scheduler. There is no point in snapshoting something broken and expect the dumb humans to notice. 2. Replace every possible call to assert_internally_consistent by a snapshot of the scheduler. It takes as many lines and ensure we never change something without noticing in any tests ever. 3. Name every snapshots: it's easier to debug when something goes wrong and easier to review in general. 4. Stop skipping breakpoints, it's too easy to miss something. Now you must explicitely show which path is the scheduler supposed to use. 5. Add a timeout on the channel.recv, it eases the process of writing tests, now when something file you get a failure instead of a deadlock. * rebase on release-v0.30 * makes clippy happy * update the snapshots after a rebase * try to remove the flakyness of the failing test * Add more analytics on the ranking rules positions * Update the dump test to check for the dumpUid dumpCreation task details * send the ranking rules as a string because amplitude is too dumb to process an array as a single value * Display a null dumpUid until we computed the dump itself on disk * Update tests * Check if the master key is missing before returning an error Co-authored-by: Loïc Lecrenier <loic.lecrenier@me.com> Co-authored-by: bors[bot] <26634292+bors[bot]@users.noreply.github.com> Co-authored-by: Kerollmops <clement@meilisearch.com> Co-authored-by: ManyTheFish <many@meilisearch.com> Co-authored-by: Tamo <tamo@meilisearch.com> Co-authored-by: Louis Dureuil <louis@meilisearch.com>
2022-11-28 16:27:41 +01:00
KindWithContent::DumpCreation { keys, instance_uid } => {
KindDump::DumpCreation { keys, instance_uid }
2022-10-20 18:00:07 +02:00
}
KindWithContent::SnapshotCreation => KindDump::SnapshotCreation,
2022-10-13 16:03:23 +02:00
}
}
}
2022-10-03 18:50:06 +02:00
#[cfg(test)]
pub(crate) mod test {
2022-10-20 18:00:07 +02:00
use std::fs::File;
2023-01-30 17:17:35 +01:00
use std::io::Seek;
2022-10-20 18:00:07 +02:00
use std::str::FromStr;
2022-10-03 18:50:06 +02:00
use big_s::S;
use maplit::{btreemap, btreeset};
use meilisearch_types::facet_values_sort::FacetValuesSort;
2023-07-06 14:22:29 +02:00
use meilisearch_types::features::RuntimeTogglableFeatures;
2023-02-08 14:54:05 +01:00
use meilisearch_types::index_uid_pattern::IndexUidPattern;
2022-10-13 16:21:54 +02:00
use meilisearch_types::keys::{Action, Key};
use meilisearch_types::milli;
2022-10-20 18:00:07 +02:00
use meilisearch_types::milli::update::Setting;
use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
2022-10-20 18:00:07 +02:00
use meilisearch_types::tasks::{Details, Status};
2022-10-03 18:50:06 +02:00
use serde_json::{json, Map, Value};
2022-10-13 16:21:54 +02:00
use time::macros::datetime;
2022-10-03 18:50:06 +02:00
use uuid::Uuid;
2022-10-20 18:00:07 +02:00
use crate::reader::Document;
use crate::{DumpReader, DumpWriter, IndexMetadata, KindDump, TaskDump, Version};
2022-10-03 18:50:06 +02:00
pub fn create_test_instance_uid() -> Uuid {
Uuid::parse_str("9e15e977-f2ae-4761-943f-1eaf75fd736d").unwrap()
}
2022-10-04 19:13:30 +02:00
pub fn create_test_index_metadata() -> IndexMetadata {
IndexMetadata {
uid: S("doggo"),
primary_key: None,
created_at: datetime!(2022-11-20 12:00 UTC),
updated_at: datetime!(2022-11-21 00:00 UTC),
}
}
2022-10-03 18:50:06 +02:00
pub fn create_test_documents() -> Vec<Map<String, Value>> {
vec![
json!({ "id": 1, "race": "golden retriever", "name": "paul", "age": 4 })
.as_object()
.unwrap()
.clone(),
json!({ "id": 2, "race": "bernese mountain", "name": "tamo", "age": 6 })
.as_object()
.unwrap()
.clone(),
json!({ "id": 3, "race": "great pyrenees", "name": "patou", "age": 5 })
.as_object()
.unwrap()
.clone(),
]
}
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(),
2023-01-11 12:33:56 +01:00
filterable_attributes: Setting::Set(btreeset! { S("race"), S("age") }),
sortable_attributes: Setting::Set(btreeset! { S("age") }),
ranking_rules: Setting::NotSet,
stop_words: Setting::NotSet,
2023-07-24 17:00:18 +02:00
non_separator_tokens: Setting::NotSet,
separator_tokens: Setting::NotSet,
dictionary: Setting::NotSet,
2023-01-11 12:33:56 +01:00
synonyms: Setting::NotSet,
distinct_attribute: Setting::NotSet,
2023-12-06 14:49:29 +01:00
proximity_precision: Setting::NotSet,
2023-01-11 12:33:56 +01:00
typo_tolerance: Setting::NotSet,
faceting: Setting::Set(FacetingSettings {
max_values_per_facet: Setting::Set(111),
sort_facet_values_by: Setting::Set(
btreemap! { S("age") => FacetValuesSort::Count },
),
}),
2023-01-11 12:33:56 +01:00
pagination: Setting::NotSet,
embedders: Setting::NotSet,
search_cutoff_ms: Setting::NotSet,
2022-10-03 18:50:06 +02:00
_kind: std::marker::PhantomData,
};
settings.check()
}
2022-10-13 16:03:23 +02:00
pub fn create_test_tasks() -> Vec<(TaskDump, Option<Vec<Document>>)> {
2022-10-03 18:50:06 +02:00
vec![
(
2022-10-13 16:03:23 +02:00
TaskDump {
2022-10-03 18:50:06 +02:00
uid: 0,
2022-10-13 16:03:23 +02:00
index_uid: Some(S("doggo")),
2022-10-03 18:50:06 +02:00
status: Status::Succeeded,
2022-10-13 16:03:23 +02:00
kind: KindDump::DocumentImport {
method: milli::update::IndexDocumentsMethod::UpdateDocuments,
2022-10-09 17:30:34 +02:00
allow_index_creation: true,
2022-10-13 16:03:23 +02:00
primary_key: Some(S("bone")),
documents_count: 12,
2022-10-09 17:30:34 +02:00
},
canceled_by: None,
details: Some(Details::DocumentAdditionOrUpdate {
2022-10-13 16:03:23 +02:00
received_documents: 12,
indexed_documents: Some(10),
2022-10-03 18:50:06 +02:00
}),
error: None,
enqueued_at: datetime!(2022-11-11 0:00 UTC),
started_at: Some(datetime!(2022-11-20 0:00 UTC)),
finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
},
None,
),
(
2022-10-13 16:03:23 +02:00
TaskDump {
2022-10-03 18:50:06 +02:00
uid: 1,
2022-10-13 16:03:23 +02:00
index_uid: Some(S("doggo")),
2022-10-03 18:50:06 +02:00
status: Status::Enqueued,
2022-10-13 16:03:23 +02:00
kind: KindDump::DocumentImport {
method: milli::update::IndexDocumentsMethod::UpdateDocuments,
2022-10-09 17:30:34 +02:00
allow_index_creation: true,
2022-10-13 16:03:23 +02:00
primary_key: None,
documents_count: 2,
2022-10-09 17:30:34 +02:00
},
canceled_by: None,
details: Some(Details::DocumentAdditionOrUpdate {
2022-10-13 16:03:23 +02:00
received_documents: 2,
indexed_documents: None,
}),
2022-10-03 18:50:06 +02:00
error: None,
enqueued_at: datetime!(2022-11-11 0:00 UTC),
2022-10-13 16:03:23 +02:00
started_at: None,
finished_at: None,
2022-10-03 18:50:06 +02:00
},
Some(vec![
2022-10-20 18:00:07 +02:00
json!({ "id": 4, "race": "leonberg" }).as_object().unwrap().clone(),
json!({ "id": 5, "race": "patou" }).as_object().unwrap().clone(),
]),
2022-10-03 18:50:06 +02:00
),
(
2022-10-13 16:03:23 +02:00
TaskDump {
2022-10-03 18:50:06 +02:00
uid: 5,
2022-10-13 16:03:23 +02:00
index_uid: Some(S("catto")),
2022-10-03 18:50:06 +02:00
status: Status::Enqueued,
2022-10-13 16:03:23 +02:00
kind: KindDump::IndexDeletion,
canceled_by: None,
2022-10-03 18:50:06 +02:00
details: None,
error: None,
enqueued_at: datetime!(2022-11-15 0:00 UTC),
started_at: None,
finished_at: None,
},
None,
),
]
}
pub fn create_test_api_keys() -> Vec<Key> {
vec![
Key {
description: Some(S("The main key to manage all the doggos")),
name: Some(S("doggos_key")),
uid: Uuid::from_str("9f8a34da-b6b2-42f0-939b-dbd4c3448655").unwrap(),
actions: vec![Action::DocumentsAll],
2023-02-08 14:54:05 +01:00
indexes: vec![IndexUidPattern::from_str("doggos").unwrap()],
2022-10-03 18:50:06 +02:00
expires_at: Some(datetime!(4130-03-14 12:21 UTC)),
created_at: datetime!(1960-11-15 0:00 UTC),
updated_at: datetime!(2022-11-10 0:00 UTC),
},
Key {
description: Some(S("The master key for everything and even the doggos")),
name: Some(S("master_key")),
uid: Uuid::from_str("4622f717-1c00-47bb-a494-39d76a49b591").unwrap(),
actions: vec![Action::All],
2023-02-08 14:54:05 +01:00
indexes: vec![IndexUidPattern::all()],
2022-10-03 18:50:06 +02:00
expires_at: None,
created_at: datetime!(0000-01-01 00:01 UTC),
updated_at: datetime!(1964-05-04 17:25 UTC),
},
Key {
description: Some(S("The useless key to for nothing nor the doggos")),
name: Some(S("useless_key")),
uid: Uuid::from_str("fb80b58b-0a34-412f-8ba7-1ce868f8ac5c").unwrap(),
actions: vec![],
indexes: vec![],
expires_at: None,
created_at: datetime!(400-02-29 0:00 UTC),
updated_at: datetime!(1024-02-29 0:00 UTC),
},
]
}
pub fn create_test_dump() -> File {
let instance_uid = create_test_instance_uid();
2022-10-22 16:35:42 +02:00
let dump = DumpWriter::new(Some(instance_uid)).unwrap();
2022-10-03 18:50:06 +02:00
// ========== Adding an index
let documents = create_test_documents();
let settings = create_test_settings();
2022-10-20 18:00:07 +02:00
let mut index = dump.create_index("doggos", &create_test_index_metadata()).unwrap();
2022-10-03 18:50:06 +02:00
for document in &documents {
index.push_document(document).unwrap();
}
index.flush().unwrap();
2022-10-03 18:50:06 +02:00
index.settings(&settings).unwrap();
// ========== pushing the task queue
let tasks = create_test_tasks();
let mut task_queue = dump.create_tasks_queue().unwrap();
for (task, update_file) in &tasks {
2022-10-10 19:57:47 +02:00
let mut update = task_queue.push_task(task).unwrap();
if let Some(update_file) = update_file {
for u in update_file {
update.push_document(u).unwrap();
}
}
2022-10-03 18:50:06 +02:00
}
task_queue.flush().unwrap();
2022-10-03 18:50:06 +02:00
// ========== pushing the api keys
let api_keys = create_test_api_keys();
let mut keys = dump.create_keys().unwrap();
for key in &api_keys {
keys.push_key(key).unwrap();
}
keys.flush().unwrap();
2022-10-03 18:50:06 +02:00
2023-07-06 14:22:29 +02:00
// ========== experimental features
let features = create_test_features();
dump.create_experimental_features(features).unwrap();
2023-06-26 12:24:55 +02:00
2022-10-03 18:50:06 +02:00
// create the dump
let mut file = tempfile::tempfile().unwrap();
dump.persist_to(&mut file).unwrap();
2023-01-30 17:17:35 +01:00
file.rewind().unwrap();
2022-10-03 18:50:06 +02:00
file
}
2023-07-06 14:22:29 +02:00
fn create_test_features() -> RuntimeTogglableFeatures {
RuntimeTogglableFeatures { vector_store: true, ..Default::default() }
}
2022-10-03 18:50:06 +02:00
#[test]
2022-10-04 19:13:30 +02:00
fn test_creating_and_read_dump() {
2022-10-03 18:50:06 +02:00
let mut file = create_test_dump();
2022-10-13 16:21:54 +02:00
let mut dump = DumpReader::open(&mut file).unwrap();
2022-10-03 18:50:06 +02:00
// ==== checking the top level infos
assert_eq!(dump.version(), Version::V6);
assert!(dump.date().is_some());
2022-10-20 18:00:07 +02:00
assert_eq!(dump.instance_uid().unwrap().unwrap(), create_test_instance_uid());
2022-10-03 18:50:06 +02:00
// ==== checking the index
let mut indexes = dump.indexes().unwrap();
let mut index = indexes.next().unwrap().unwrap();
assert!(indexes.next().is_none()); // there was only one index in the dump
for (document, expected) in index.documents().unwrap().zip(create_test_documents()) {
assert_eq!(document.unwrap(), expected);
}
assert_eq!(index.settings().unwrap(), create_test_settings());
2022-10-04 19:13:30 +02:00
assert_eq!(index.metadata(), &create_test_index_metadata());
drop(index);
drop(indexes);
2022-10-03 18:50:06 +02:00
// ==== checking the task queue
for (task, expected) in dump.tasks().unwrap().zip(create_test_tasks()) {
2022-10-03 18:50:06 +02:00
let (task, content_file) = task.unwrap();
assert_eq!(task, expected.0);
if let Some(expected_update) = expected.1 {
assert!(
content_file.is_some(),
"A content file was expected for the task {}.",
expected.0.uid
);
2022-10-20 18:00:07 +02:00
let updates = content_file.unwrap().collect::<Result<Vec<_>, _>>().unwrap();
assert_eq!(updates, expected_update);
2022-10-03 18:50:06 +02:00
}
}
// ==== checking the keys
for (key, expected) in dump.keys().unwrap().zip(create_test_api_keys()) {
2022-10-03 18:50:06 +02:00
assert_eq!(key.unwrap(), expected);
}
2023-07-06 14:22:29 +02:00
// ==== checking the features
let expected = create_test_features();
assert_eq!(dump.features().unwrap().unwrap(), expected);
2022-10-03 18:50:06 +02:00
}
}