Merge #2745 #2789 #2814 #2826

2745: Config file support r=curquiza a=mlemesle

# Pull Request

## What does this PR do?
Fixes #2558

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Thank you so much for contributing to Meilisearch!


2789: Fix typos r=Kerollmops a=kianmeng

# Pull Request

## What does this PR do?

Found via `codespell -L crate,nam,hart`.

## PR checklist
Please check if your PR fulfills the following requirements:
- [ ] Does this PR fix an existing issue?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Thank you so much for contributing to Meilisearch!


2814: Skip dashboard test if mini-dashboard feature is disabled r=Kerollmops a=jirutka

Fixes #2813

Fixes the following error:

    cargo test --no-default-features
    ...
    error: couldn't read target/debug/build/meilisearch-http-ec029d8c902cf2cb/out/generated.rs: No such file or directory (os error 2)
     --> meilisearch-http/tests/dashboard/mod.rs:8:9
      |
    8 |         include!(concat!(env!("OUT_DIR"), "/generated.rs"));
      |         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      |
      = note: this error originates in the macro `include` (in Nightly builds, run with -Z macro-backtrace for more info)

    error: could not compile `meilisearch-http` due to previous error

2826: Rename receivedDocumentIds into matchedDocuments r=Kerollmops a=Ugzuzg

# Pull Request

## What does this PR do?

Fixes #2799 
Changes DocumentDeletion task details response.

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Tested with curl:
```
curl \
  -X POST 'http://localhost:7700/indexes/movies/documents/delete-batch' \
  -H 'Content-Type: application/json' \
  --data-binary '[
    23488,
    153738,
    437035,
    363869
  ]'

{"taskUid":1,"indexUid":"movies","status":"enqueued","type":"documentDeletion","enqueuedAt":"2022-10-01T20:06:37.105416054Z"}%

curl \
  -X GET 'http://localhost:7700/tasks/1'

{"uid":1,"indexUid":"movies","status":"succeeded","type":"documentDeletion","details":{"matchedDocuments":4,"deletedDocuments":2},"duration":"PT0.005708322S","enqueuedAt":"2022-10-01T20:06:37.105416054Z","startedAt":"2022-10-01T20:06:37.115562733Z","finishedAt":"2022-10-01T20:06:37.121271055Z"}
```

Co-authored-by: mlemesle <lemesle.martin@hotmail.fr>
Co-authored-by: Kian-Meng Ang <kianmeng@cpan.org>
Co-authored-by: Jakub Jirutka <jakub@jirutka.cz>
Co-authored-by: Jarasłaŭ Viktorčyk <ugzuzg@gmail.com>

meilisearch-lib/src/dump/compat/v2.rs

@@ -145,7 +145,7 @@ pub fn error_code_from_str(s: &str) -> anyhow::Result<Code> {
         "unsupported_media_type" => Code::UnsupportedMediaType,
         "dump_already_in_progress" => Code::DumpAlreadyInProgress,
         "dump_process_failed" => Code::DumpProcessFailed,
-        _ => bail!("unknow error code."),
+        _ => bail!("unknown error code."),
     };
 
     Ok(code)

meilisearch-lib/src/dump/loaders/v4.rs

@@ -57,10 +57,10 @@ fn patch_updates(src: impl AsRef<Path>, dst: impl AsRef<Path>) -> anyhow::Result
     let updates_path = src.as_ref().join("updates/data.jsonl");
     let output_updates_path = dst.as_ref().join("updates/data.jsonl");
     create_dir_all(output_updates_path.parent().unwrap())?;
-    let udpates_file = File::open(updates_path)?;
+    let updates_file = File::open(updates_path)?;
     let mut output_update_file = File::create(output_updates_path)?;
 
-    serde_json::Deserializer::from_reader(udpates_file)
+    serde_json::Deserializer::from_reader(updates_file)
         .into_iter::<compat::v4::Task>()
         .try_for_each(|task| -> anyhow::Result<()> {
             let task: Task = task?.into();

meilisearch-lib/src/index/search.rs

@@ -27,7 +27,7 @@ pub const DEFAULT_CROP_MARKER: fn() -> String = || "…".to_string();
 pub const DEFAULT_HIGHLIGHT_PRE_TAG: fn() -> String = || "<em>".to_string();
 pub const DEFAULT_HIGHLIGHT_POST_TAG: fn() -> String = || "</em>".to_string();
 
-/// The maximimum number of results that the engine
+/// The maximum number of results that the engine
 /// will be able to return in one search call.
 pub const DEFAULT_PAGINATION_MAX_TOTAL_HITS: usize = 1000;
 

meilisearch-lib/src/index_resolver/index_store.rs

@@ -51,7 +51,7 @@ impl MapIndexStore {
 #[async_trait::async_trait]
 impl IndexStore for MapIndexStore {
     async fn create(&self, uuid: Uuid) -> Result<Index> {
-        // We need to keep the lock until we are sure the db file has been opened correclty, to
+        // We need to keep the lock until we are sure the db file has been opened correctly, to
         // ensure that another db is not created at the same time.
         let mut lock = self.index_store.write().await;
 

meilisearch-lib/src/lib.rs

@@ -11,6 +11,8 @@ mod snapshot;
 pub mod tasks;
 mod update_file_store;
 
+use std::env::VarError;
+use std::ffi::OsStr;
 use std::path::Path;
 
 pub use index_controller::MeiliSearch;
@@ -35,3 +37,14 @@ pub fn is_empty_db(db_path: impl AsRef<Path>) -> bool {
         true
     }
 }
+
+/// Checks if the key is defined in the environment variables.
+/// If not, inserts it with the given value.
+pub fn export_to_env_if_not_present<T>(key: &str, value: T)
+where
+    T: AsRef<OsStr>,
+{
+    if let Err(VarError::NotPresent) = std::env::var(key) {
+        std::env::set_var(key, value);
+    }
+}

meilisearch-lib/src/options.rs

@@ -1,33 +1,40 @@
+use crate::export_to_env_if_not_present;
+
 use core::fmt;
 use std::{convert::TryFrom, num::ParseIntError, ops::Deref, str::FromStr};
 
 use byte_unit::{Byte, ByteError};
 use clap::Parser;
 use milli::update::IndexerConfig;
-use serde::Serialize;
+use serde::{Deserialize, Serialize};
 use sysinfo::{RefreshKind, System, SystemExt};
 
-#[derive(Debug, Clone, Parser, Serialize)]
+const MEILI_MAX_INDEXING_MEMORY: &str = "MEILI_MAX_INDEXING_MEMORY";
+const MEILI_MAX_INDEXING_THREADS: &str = "MEILI_MAX_INDEXING_THREADS";
+const DISABLE_AUTO_BATCHING: &str = "DISABLE_AUTO_BATCHING";
+const DEFAULT_LOG_EVERY_N: usize = 100000;
+
+#[derive(Debug, Clone, Parser, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case", deny_unknown_fields)]
 pub struct IndexerOpts {
     /// The amount of documents to skip before printing
     /// a log regarding the indexing advancement.
-    #[serde(skip)]
-    #[clap(long, default_value = "100000", hide = true)] // 100k
+    #[serde(skip_serializing, default = "default_log_every_n")]
+    #[clap(long, default_value_t = default_log_every_n(), hide = true)] // 100k
     pub log_every_n: usize,
 
     /// Grenad max number of chunks in bytes.
-    #[serde(skip)]
+    #[serde(skip_serializing)]
     #[clap(long, hide = true)]
     pub max_nb_chunks: Option<usize>,
 
-    /// The maximum amount of memory the indexer will use. It defaults to 2/3
-    /// of the available memory. It is recommended to use something like 80%-90%
-    /// of the available memory, no more.
+    /// The maximum amount of memory the indexer will use.
     ///
     /// In case the engine is unable to retrieve the available memory the engine will
     /// try to use the memory it needs but without real limit, this can lead to
     /// Out-Of-Memory issues and it is recommended to specify the amount of memory to use.
-    #[clap(long, env = "MEILI_MAX_INDEXING_MEMORY", default_value_t)]
+    #[clap(long, env = MEILI_MAX_INDEXING_MEMORY, default_value_t)]
+    #[serde(default)]
     pub max_indexing_memory: MaxMemory,
 
     /// The maximum number of threads the indexer will use.
@@ -35,18 +42,43 @@ pub struct IndexerOpts {
     /// it will use the maximum number of available cores.
     ///
     /// It defaults to half of the available threads.
-    #[clap(long, env = "MEILI_MAX_INDEXING_THREADS", default_value_t)]
+    #[clap(long, env = MEILI_MAX_INDEXING_THREADS, default_value_t)]
+    #[serde(default)]
     pub max_indexing_threads: MaxThreads,
 }
 
-#[derive(Debug, Clone, Parser, Default, Serialize)]
+#[derive(Debug, Clone, Parser, Default, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case", deny_unknown_fields)]
 pub struct SchedulerConfig {
     /// The engine will disable task auto-batching,
     /// and will sequencialy compute each task one by one.
-    #[clap(long, env = "DISABLE_AUTO_BATCHING")]
+    #[clap(long, env = DISABLE_AUTO_BATCHING)]
+    #[serde(default)]
     pub disable_auto_batching: bool,
 }
 
+impl IndexerOpts {
+    /// Exports the values to their corresponding env vars if they are not set.
+    pub fn export_to_env(self) {
+        let IndexerOpts {
+            max_indexing_memory,
+            max_indexing_threads,
+            log_every_n: _,
+            max_nb_chunks: _,
+        } = self;
+        if let Some(max_indexing_memory) = max_indexing_memory.0 {
+            export_to_env_if_not_present(
+                MEILI_MAX_INDEXING_MEMORY,
+                max_indexing_memory.to_string(),
+            );
+        }
+        export_to_env_if_not_present(
+            MEILI_MAX_INDEXING_THREADS,
+            max_indexing_threads.0.to_string(),
+        );
+    }
+}
+
 impl TryFrom<&IndexerOpts> for IndexerConfig {
     type Error = anyhow::Error;
 
@@ -77,8 +109,17 @@ impl Default for IndexerOpts {
     }
 }
 
+impl SchedulerConfig {
+    pub fn export_to_env(self) {
+        let SchedulerConfig {
+            disable_auto_batching,
+        } = self;
+        export_to_env_if_not_present(DISABLE_AUTO_BATCHING, disable_auto_batching.to_string());
+    }
+}
+
 /// A type used to detect the max memory available and use 2/3 of it.
-#[derive(Debug, Clone, Copy, Serialize)]
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
 pub struct MaxMemory(Option<Byte>);
 
 impl FromStr for MaxMemory {
@@ -134,7 +175,7 @@ fn total_memory_bytes() -> Option<u64> {
     }
 }
 
-#[derive(Debug, Clone, Copy, Serialize)]
+#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
 pub struct MaxThreads(usize);
 
 impl FromStr for MaxThreads {
@@ -164,3 +205,7 @@ impl Deref for MaxThreads {
         &self.0
     }
 }
+
+fn default_log_every_n() -> usize {
+    DEFAULT_LOG_EVERY_N
+}

meilisearch-lib/src/tasks/task_store/store.rs

@@ -63,7 +63,7 @@ impl Store {
     /// Returns the id for the next task.
     ///
     /// The required `mut txn` acts as a reservation system. It guarantees that as long as you commit
-    /// the task to the store in the same transaction, no one else will hav this task id.
+    /// the task to the store in the same transaction, no one else will have this task id.
     pub fn next_task_id(&self, txn: &mut RwTxn) -> Result<TaskId> {
         let id = self
             .tasks