implement a first version of the clear indexes

Cargo.lock

@@ -463,7 +463,7 @@ checksum = "b645a089122eccb6111b4f81cbc1a49f5900ac4666bb93ac027feaecf15607bf"
 
 [[package]]
 name = "benchmarks"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "anyhow",
  "bytes",
@@ -1209,7 +1209,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1428,7 +1428,7 @@ dependencies = [
 
 [[package]]
 name = "file-store"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "faux",
  "tempfile",
@@ -1450,7 +1450,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "insta",
  "nom",
@@ -1476,7 +1476,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "criterion",
  "serde_json",
@@ -1794,7 +1794,7 @@ checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
 [[package]]
 name = "heed"
 version = "0.12.5"
-source = "git+https://github.com/meilisearch/heed?tag=v0.12.6#8c5b94225fc949c02bb7b900cc50ffaf6b584b1e"
+source = "git+https://github.com/meilisearch/heed?tag=v0.12.5#4158a6c484752afaaf9e2530a6ee0e7ab0f24ee8"
 dependencies = [
  "byteorder",
  "heed-traits",
@@ -1811,12 +1811,12 @@ dependencies = [
 [[package]]
 name = "heed-traits"
 version = "0.7.0"
-source = "git+https://github.com/meilisearch/heed?tag=v0.12.6#8c5b94225fc949c02bb7b900cc50ffaf6b584b1e"
+source = "git+https://github.com/meilisearch/heed?tag=v0.12.5#4158a6c484752afaaf9e2530a6ee0e7ab0f24ee8"
 
 [[package]]
 name = "heed-types"
 version = "0.7.2"
-source = "git+https://github.com/meilisearch/heed?tag=v0.12.6#8c5b94225fc949c02bb7b900cc50ffaf6b584b1e"
+source = "git+https://github.com/meilisearch/heed?tag=v0.12.5#4158a6c484752afaaf9e2530a6ee0e7ab0f24ee8"
 dependencies = [
  "bincode",
  "heed-traits",
@@ -1959,7 +1959,7 @@ dependencies = [
 
 [[package]]
 name = "index-scheduler"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "anyhow",
  "big_s",
@@ -2113,7 +2113,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2539,7 +2539,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "insta",
  "md5",
@@ -2548,7 +2548,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -2636,7 +2636,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "base64 0.21.0",
  "enum-iterator",
@@ -2655,7 +2655,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -2709,7 +2709,7 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "big_s",
  "bimap",
@@ -3064,7 +3064,7 @@ checksum = "478c572c3d73181ff3c2539045f6eb99e5491218eae919370993b890cdbdd98e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.2.0"
+version = "1.1.1"
 dependencies = [
  "big_s",
  "serde_json",

Cargo.toml

@@ -17,7 +17,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.2.0"
+version = "1.1.1"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"

benchmarks/Cargo.toml

@@ -13,7 +13,7 @@ license.workspace = true
 [dependencies]
 anyhow = "1.0.70"
 csv = "1.2.1"
-milli = { path = "../milli" }
+milli = { path = "../milli", default-features = false }
 mimalloc = { version = "0.1.36", default-features = false }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
 
@@ -31,7 +31,7 @@ flate2 = "1.0.25"
 reqwest = { version = "0.11.16", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
-default = ["milli/all-tokenizations"]
+default = ["milli/default"]
 
 [[bench]]
 name = "search_songs"

config.toml

@@ -126,6 +126,3 @@ ssl_tickets = false
 experimental_enable_metrics = false
 # Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
 # Enables the Prometheus metrics on the `GET /metrics` endpoint.
-
-experimental_reduce_indexing_memory_usage = false
-# Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>

dump/src/lib.rs

@@ -110,6 +110,9 @@ pub enum KindDump {
         allow_index_creation: bool,
     },
     IndexDeletion,
+    IndexClear {
+        index_uids: Vec<String>,
+    },
     IndexCreation {
         primary_key: Option<String>,
     },
@@ -180,6 +183,7 @@ impl From<KindWithContent> for KindDump {
                 ..
             } => KindDump::Settings { settings: new_settings, is_deletion, allow_index_creation },
             KindWithContent::IndexDeletion { .. } => KindDump::IndexDeletion,
+            KindWithContent::IndexClear { index_uids } => KindDump::IndexClear { index_uids },
             KindWithContent::IndexCreation { primary_key, .. } => {
                 KindDump::IndexCreation { primary_key }
             }
@@ -211,8 +215,8 @@ pub(crate) mod test {
     use maplit::btreeset;
     use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
+    use meilisearch_types::milli;
     use meilisearch_types::milli::update::Setting;
-    use meilisearch_types::milli::{self};
     use meilisearch_types::settings::{Checked, Settings};
     use meilisearch_types::tasks::{Details, Status};
     use serde_json::{json, Map, Value};

index-scheduler/src/autobatcher.rs

@@ -32,6 +32,7 @@ enum AutobatchKind {
     },
     IndexCreation,
     IndexDeletion,
+    IndexClear,
     IndexUpdate,
     IndexSwap,
 }
@@ -74,6 +75,7 @@ impl From<KindWithContent> for AutobatchKind {
                 }
             }
             KindWithContent::IndexDeletion { .. } => AutobatchKind::IndexDeletion,
+            KindWithContent::IndexClear { .. } => AutobatchKind::IndexClear,
             KindWithContent::IndexCreation { .. } => AutobatchKind::IndexCreation,
             KindWithContent::IndexUpdate { .. } => AutobatchKind::IndexUpdate,
             KindWithContent::IndexSwap { .. } => AutobatchKind::IndexSwap,
@@ -123,6 +125,9 @@ pub enum BatchKind {
     IndexDeletion {
         ids: Vec<TaskId>,
     },
+    IndexClear {
+        id: TaskId,
+    },
     IndexCreation {
         id: TaskId,
     },
@@ -173,6 +178,7 @@ impl BatchKind {
         match AutobatchKind::from(kind) {
             K::IndexCreation => (Break(BatchKind::IndexCreation { id: task_id }), true),
             K::IndexDeletion => (Break(BatchKind::IndexDeletion { ids: vec![task_id] }), false),
+            K::IndexClear => (Break(BatchKind::IndexClear { id: task_id }), false),
             K::IndexUpdate => (Break(BatchKind::IndexUpdate { id: task_id }), false),
             K::IndexSwap => (Break(BatchKind::IndexSwap { id: task_id }), false),
             K::DocumentClear => (Continue(BatchKind::DocumentClear { ids: vec![task_id] }), false),
@@ -222,7 +228,7 @@ impl BatchKind {
 
         match (self, kind) {
             // We don't batch any of these operations
-            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentDeletionByFilter) => Break(this),
+            (this, K::IndexCreation | K::IndexUpdate | K::IndexClear | K::IndexSwap | K::DocumentDeletionByFilter) => Break(this),
             // We must not batch tasks that don't have the same index creation rights if the index doesn't already exists.
             (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
                 Break(this)
@@ -480,6 +486,7 @@ impl BatchKind {
             (
                 BatchKind::IndexCreation { .. }
                 | BatchKind::IndexDeletion { .. }
+                | BatchKind::IndexClear { .. }
                 | BatchKind::IndexUpdate { .. }
                 | BatchKind::IndexSwap { .. }
                 | BatchKind::DocumentDeletionByFilter { .. },

index-scheduler/src/batch.rs

@@ -24,7 +24,6 @@ use std::io::BufWriter;
 
 use dump::IndexMetadata;
 use log::{debug, error, info};
-use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
 use meilisearch_types::milli::heed::CompactionOption;
@@ -86,6 +85,10 @@ pub(crate) enum Batch {
         tasks: Vec<Task>,
         index_has_been_created: bool,
     },
+    IndexClear {
+        index_uids: Vec<String>,
+        task: Task,
+    },
     IndexSwap {
         task: Task,
     },
@@ -155,6 +158,7 @@ impl Batch {
             | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
+            | Batch::IndexClear { task, .. }
             | Batch::IndexDocumentDeletionByFilter { task, .. }
             | Batch::IndexUpdate { task, .. } => vec![task.uid],
             Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
@@ -190,6 +194,7 @@ impl Batch {
             | TaskDeletion(_)
             | SnapshotCreation(_)
             | Dump(_)
+            | IndexClear { .. }
             | IndexSwap { .. } => None,
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
@@ -454,6 +459,14 @@ impl IndexScheduler {
                 index_has_been_created: must_create_index,
                 tasks: self.get_existing_tasks(rtxn, ids)?,
             })),
+            BatchKind::IndexClear { id } => {
+                let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
+                let index_uids = match &task.kind {
+                    KindWithContent::IndexClear { index_uids } => index_uids.clone(),
+                    _ => unreachable!(),
+                };
+                Ok(Some(Batch::IndexClear { index_uids, task }))
+            }
             BatchKind::IndexSwap { id } => {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 Ok(Some(Batch::IndexSwap { task }))
@@ -1018,6 +1031,13 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            Batch::IndexClear { index_uids, mut task } => {
+                let wtxn = self.env.write_txn()?;
+                self.index_mapper.delete_indexes(wtxn, index_uids, false)?;
+                task.status = Status::Succeeded;
+
+                Ok(vec![task])
+            }
             Batch::IndexSwap { mut task } => {
                 let mut wtxn = self.env.write_txn()?;
                 let swaps = if let KindWithContent::IndexSwap { swaps } = &task.kind {
@@ -1492,12 +1512,7 @@ fn delete_document_by_filter(filter: &serde_json::Value, index: Index) -> Result
     Ok(if let Some(filter) = filter {
         let mut wtxn = index.write_txn()?;
 
-        let candidates = filter.evaluate(&wtxn, &index).map_err(|err| match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            e => e.into(),
-        })?;
+        let candidates = filter.evaluate(&wtxn, &index)?;
         let mut delete_operation = DeleteDocuments::new(&mut wtxn, &index)?;
         delete_operation.delete_documents(&candidates);
         let deleted_documents =

index-scheduler/src/error.rs

@@ -46,8 +46,6 @@ impl From<DateField> for Code {
 #[allow(clippy::large_enum_variant)]
 #[derive(Error, Debug)]
 pub enum Error {
-    #[error("{1}")]
-    WithCustomErrorCode(Code, Box<Self>),
     #[error("Index `{0}` not found.")]
     IndexNotFound(String),
     #[error("Index `{0}` already exists.")]
@@ -146,7 +144,6 @@ impl Error {
     pub fn is_recoverable(&self) -> bool {
         match self {
             Error::IndexNotFound(_)
-            | Error::WithCustomErrorCode(_, _)
             | Error::IndexAlreadyExists(_)
             | Error::SwapDuplicateIndexFound(_)
             | Error::SwapDuplicateIndexesFound(_)
@@ -179,16 +176,11 @@ impl Error {
             Error::PlannedFailure => false,
         }
     }
-
-    pub fn with_custom_error_code(self, code: Code) -> Self {
-        Self::WithCustomErrorCode(code, Box::new(self))
-    }
 }
 
 impl ErrorCode for Error {
     fn error_code(&self) -> Code {
         match self {
-            Error::WithCustomErrorCode(code, _) => *code,
             Error::IndexNotFound(_) => Code::IndexNotFound,
             Error::IndexAlreadyExists(_) => Code::IndexAlreadyExists,
             Error::SwapDuplicateIndexesFound(_) => Code::InvalidSwapDuplicateIndexFound,

index-scheduler/src/index_mapper/index_map.rs

@@ -5,7 +5,6 @@ use std::collections::BTreeMap;
 use std::path::Path;
 use std::time::Duration;
 
-use meilisearch_types::heed::flags::Flags;
 use meilisearch_types::heed::{EnvClosingEvent, EnvOpenOptions};
 use meilisearch_types::milli::Index;
 use time::OffsetDateTime;
@@ -54,7 +53,6 @@ pub struct IndexMap {
 pub struct ClosingIndex {
     uuid: Uuid,
     closing_event: EnvClosingEvent,
-    enable_mdb_writemap: bool,
     map_size: usize,
     generation: usize,
 }
@@ -70,7 +68,6 @@ impl ClosingIndex {
     pub fn wait_timeout(self, timeout: Duration) -> Option<ReopenableIndex> {
         self.closing_event.wait_timeout(timeout).then_some(ReopenableIndex {
             uuid: self.uuid,
-            enable_mdb_writemap: self.enable_mdb_writemap,
             map_size: self.map_size,
             generation: self.generation,
         })
@@ -79,7 +76,6 @@ impl ClosingIndex {
 
 pub struct ReopenableIndex {
     uuid: Uuid,
-    enable_mdb_writemap: bool,
     map_size: usize,
     generation: usize,
 }
@@ -107,7 +103,7 @@ impl ReopenableIndex {
                 return Ok(());
             }
             map.unavailable.remove(&self.uuid);
-            map.create(&self.uuid, path, None, self.enable_mdb_writemap, self.map_size)?;
+            map.create(&self.uuid, path, None, self.map_size)?;
         }
         Ok(())
     }
@@ -174,17 +170,16 @@ impl IndexMap {
         uuid: &Uuid,
         path: &Path,
         date: Option<(OffsetDateTime, OffsetDateTime)>,
-        enable_mdb_writemap: bool,
         map_size: usize,
     ) -> Result<Index> {
         if !matches!(self.get_unavailable(uuid), Missing) {
             panic!("Attempt to open an index that was unavailable");
         }
-        let index = create_or_open_index(path, date, enable_mdb_writemap, map_size)?;
+        let index = create_or_open_index(path, date, map_size)?;
         match self.available.insert(*uuid, index.clone()) {
             InsertionOutcome::InsertedNew => (),
             InsertionOutcome::Evicted(evicted_uuid, evicted_index) => {
-                self.close(evicted_uuid, evicted_index, enable_mdb_writemap, 0);
+                self.close(evicted_uuid, evicted_index, 0);
             }
             InsertionOutcome::Replaced(_) => {
                 panic!("Attempt to open an index that was already opened")
@@ -217,30 +212,17 @@ impl IndexMap {
     /// | Closing         | Closing       |
     /// | Available       | Closing       |
     ///
-    pub fn close_for_resize(
-        &mut self,
-        uuid: &Uuid,
-        enable_mdb_writemap: bool,
-        map_size_growth: usize,
-    ) {
+    pub fn close_for_resize(&mut self, uuid: &Uuid, map_size_growth: usize) {
         let Some(index) = self.available.remove(uuid) else { return; };
-        self.close(*uuid, index, enable_mdb_writemap, map_size_growth);
+        self.close(*uuid, index, map_size_growth);
     }
 
-    fn close(
-        &mut self,
-        uuid: Uuid,
-        index: Index,
-        enable_mdb_writemap: bool,
-        map_size_growth: usize,
-    ) {
+    fn close(&mut self, uuid: Uuid, index: Index, map_size_growth: usize) {
         let map_size = index.map_size().unwrap_or(DEFAULT_MAP_SIZE) + map_size_growth;
         let closing_event = index.prepare_for_closing();
         let generation = self.next_generation();
-        self.unavailable.insert(
-            uuid,
-            Some(ClosingIndex { uuid, closing_event, enable_mdb_writemap, map_size, generation }),
-        );
+        self.unavailable
+            .insert(uuid, Some(ClosingIndex { uuid, closing_event, map_size, generation }));
     }
 
     /// Attempts to delete and index.
@@ -300,15 +282,11 @@ impl IndexMap {
 fn create_or_open_index(
     path: &Path,
     date: Option<(OffsetDateTime, OffsetDateTime)>,
-    enable_mdb_writemap: bool,
     map_size: usize,
 ) -> Result<Index> {
     let mut options = EnvOpenOptions::new();
     options.map_size(clamp_to_page_size(map_size));
     options.max_readers(1024);
-    if enable_mdb_writemap {
-        unsafe { options.flag(Flags::MdbWriteMap) };
-    }
 
     if let Some((created, updated)) = date {
         Ok(Index::new_with_creation_dates(options, path, created, updated)?)

index-scheduler/src/index_mapper/mod.rs

@@ -66,8 +66,6 @@ pub struct IndexMapper {
     index_base_map_size: usize,
     /// The quantity by which the map size of an index is incremented upon reopening, in bytes.
     index_growth_amount: usize,
-    /// Whether we open a meilisearch index with the MDB_WRITEMAP option or not.
-    enable_mdb_writemap: bool,
     pub indexer_config: Arc<IndexerConfig>,
 }
 
@@ -125,22 +123,15 @@ impl IndexMapper {
         index_base_map_size: usize,
         index_growth_amount: usize,
         index_count: usize,
-        enable_mdb_writemap: bool,
         indexer_config: IndexerConfig,
     ) -> Result<Self> {
-        let mut wtxn = env.write_txn()?;
-        let index_mapping = env.create_database(&mut wtxn, Some(INDEX_MAPPING))?;
-        let index_stats = env.create_database(&mut wtxn, Some(INDEX_STATS))?;
-        wtxn.commit()?;
-
         Ok(Self {
             index_map: Arc::new(RwLock::new(IndexMap::new(index_count))),
-            index_mapping,
-            index_stats,
+            index_mapping: env.create_database(Some(INDEX_MAPPING))?,
+            index_stats: env.create_database(Some(INDEX_STATS))?,
             base_path,
             index_base_map_size,
             index_growth_amount,
-            enable_mdb_writemap,
             indexer_config: Arc::new(indexer_config),
         })
     }
@@ -171,7 +162,6 @@ impl IndexMapper {
                     &uuid,
                     &index_path,
                     date,
-                    self.enable_mdb_writemap,
                     self.index_base_map_size,
                 )?;
 
@@ -183,19 +173,37 @@ impl IndexMapper {
         }
     }
 
+    pub fn delete_index(&self, wtxn: RwTxn, name: &str) -> Result<()> {
+        self.delete_indexes(wtxn, Some(name), true)
+    }
+
     /// Removes the index from the mapping table and the in-memory index map
     /// but keeps the associated tasks.
-    pub fn delete_index(&self, mut wtxn: RwTxn, name: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(&wtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+    pub fn delete_indexes(
+        &self,
+        mut wtxn: RwTxn,
+        names: impl IntoIterator<Item = impl AsRef<str>>,
+        error_on_missing_index: bool,
+    ) -> Result<()> {
+        let indexes = names
+            .into_iter()
+            .map(|name| {
+                let name = name.as_ref().to_string();
+                let uuid = self
+                    .index_mapping
+                    .get(&wtxn, &name)?
+                    .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+                Ok((name, uuid))
+            })
+            .filter(|res| error_on_missing_index || res.is_ok())
+            .collect::<Result<Vec<_>>>()?;
 
-        // Not an error if the index had no stats in cache.
-        self.index_stats.delete(&mut wtxn, &uuid)?;
-
-        // Once we retrieved the UUID of the index we remove it from the mapping table.
-        assert!(self.index_mapping.delete(&mut wtxn, name)?);
+        for (name, uuid) in indexes.iter() {
+            // Not an error if the index had no stats in cache.
+            self.index_stats.delete(&mut wtxn, uuid)?;
+            // Once we retrieved the UUID of the index we remove it from the mapping table.
+            assert!(self.index_mapping.delete(&mut wtxn, name)?);
+        }
 
         wtxn.commit()?;
 
@@ -213,51 +221,63 @@ impl IndexMapper {
         //    This can not be caused by indexation because deleting an index happens in the scheduler itself, so cannot be concurrent with indexation.
         //
         // In these situations, reporting the error through a panic is in order.
-        let closing_event = loop {
-            let mut lock = self.index_map.write().unwrap();
-            match lock.start_deletion(&uuid) {
-                Ok(env_closing) => break env_closing,
-                Err(Some(reopen)) => {
-                    // drop the lock here so that we don't synchronously wait for the index to close.
-                    drop(lock);
-                    tries += 1;
-                    if tries >= 100 {
-                        panic!("Too many attempts to close index {name} prior to deletion.")
+        let indexes = indexes
+            .into_iter()
+            .map(|(name, uuid)| {
+                let closing_event = loop {
+                    let mut lock = self.index_map.write().unwrap();
+                    match lock.start_deletion(&uuid) {
+                        Ok(env_closing) => break env_closing,
+                        Err(Some(reopen)) => {
+                            // drop the lock here so that we don't synchronously wait for the index to close.
+                            drop(lock);
+                            tries += 1;
+                            if tries >= 100 {
+                                panic!("Too many attempts to close index {name} prior to deletion.")
+                            }
+                            let reopen =
+                                if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
+                                    reopen
+                                } else {
+                                    continue;
+                                };
+                            reopen.close(&mut self.index_map.write().unwrap());
+                            continue;
+                        }
+                        // TODO: what is this case, what does that mean?
+                        Err(None) => return None,
                     }
-                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
-                        reopen
-                    } else {
-                        continue;
-                    };
-                    reopen.close(&mut self.index_map.write().unwrap());
-                    continue;
-                }
-                Err(None) => return Ok(()),
-            }
-        };
+                };
+                Some((name, uuid, closing_event))
+            })
+            .filter_map(|thingy| thingy)
+            .map(|(name, uuid, closing)| {
+                (name.to_string(), uuid, self.base_path.join(uuid.to_string()), closing)
+            })
+            .collect::<Vec<_>>();
 
         let index_map = self.index_map.clone();
-        let index_path = self.base_path.join(uuid.to_string());
-        let index_name = name.to_string();
         thread::Builder::new()
             .name(String::from("index_deleter"))
             .spawn(move || {
-                // We first wait to be sure that the previously opened index is effectively closed.
-                // This can take a lot of time, this is why we do that in a separate thread.
-                if let Some(closing_event) = closing_event {
-                    closing_event.wait();
-                }
+                for (name, uuid, index_path, closing_event) in indexes {
+                    // We first wait to be sure that the previously opened index is effectively closed.
+                    // This can take a lot of time, this is why we do that in a separate thread.
+                    if let Some(closing_event) = closing_event {
+                        closing_event.wait();
+                    }
 
-                // Then we remove the content from disk.
-                if let Err(e) = fs::remove_dir_all(&index_path) {
-                    error!(
-                        "An error happened when deleting the index {} ({}): {}",
-                        index_name, uuid, e
-                    );
-                }
+                    // Then we remove the content from disk.
+                    if let Err(e) = fs::remove_dir_all(&index_path) {
+                        error!(
+                            "An error happened when deleting the index {} ({}): {}",
+                            name, uuid, e
+                        );
+                    }
 
-                // Finally we remove the entry from the index map.
-                index_map.write().unwrap().end_deletion(&uuid);
+                    // Finally we remove the entry from the index map.
+                    index_map.write().unwrap().end_deletion(&uuid);
+                }
             })
             .unwrap();
 
@@ -283,11 +303,7 @@ impl IndexMapper {
             .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
 
         // We remove the index from the in-memory index map.
-        self.index_map.write().unwrap().close_for_resize(
-            &uuid,
-            self.enable_mdb_writemap,
-            self.index_growth_amount,
-        );
+        self.index_map.write().unwrap().close_for_resize(&uuid, self.index_growth_amount);
 
         Ok(())
     }
@@ -352,7 +368,6 @@ impl IndexMapper {
                                 &uuid,
                                 &index_path,
                                 None,
-                                self.enable_mdb_writemap,
                                 self.index_base_map_size,
                             )?;
                         }

index-scheduler/src/lib.rs

@@ -233,8 +233,6 @@ pub struct IndexSchedulerOptions {
     pub task_db_size: usize,
     /// The size, in bytes, with which a meilisearch index is opened the first time of each meilisearch index.
     pub index_base_map_size: usize,
-    /// Whether we open a meilisearch index with the MDB_WRITEMAP option or not.
-    pub enable_mdb_writemap: bool,
     /// The size, in bytes, by which the map size of an index is increased when it resized due to being full.
     pub index_growth_amount: usize,
     /// The number of indexes that can be concurrently opened in memory.
@@ -376,11 +374,6 @@ impl IndexScheduler {
         std::fs::create_dir_all(&options.indexes_path)?;
         std::fs::create_dir_all(&options.dumps_path)?;
 
-        if cfg!(windows) && options.enable_mdb_writemap {
-            // programmer error if this happens: in normal use passing the option on Windows is an error in main
-            panic!("Windows doesn't support the MDB_WRITEMAP LMDB option");
-        }
-
         let task_db_size = clamp_to_page_size(options.task_db_size);
         let budget = if options.indexer_config.skip_index_budget {
             IndexBudget {
@@ -403,37 +396,25 @@ impl IndexScheduler {
             .open(options.tasks_path)?;
         let file_store = FileStore::new(&options.update_file_path)?;
 
-        let mut wtxn = env.write_txn()?;
-        let all_tasks = env.create_database(&mut wtxn, Some(db_name::ALL_TASKS))?;
-        let status = env.create_database(&mut wtxn, Some(db_name::STATUS))?;
-        let kind = env.create_database(&mut wtxn, Some(db_name::KIND))?;
-        let index_tasks = env.create_database(&mut wtxn, Some(db_name::INDEX_TASKS))?;
-        let canceled_by = env.create_database(&mut wtxn, Some(db_name::CANCELED_BY))?;
-        let enqueued_at = env.create_database(&mut wtxn, Some(db_name::ENQUEUED_AT))?;
-        let started_at = env.create_database(&mut wtxn, Some(db_name::STARTED_AT))?;
-        let finished_at = env.create_database(&mut wtxn, Some(db_name::FINISHED_AT))?;
-        wtxn.commit()?;
-
         // allow unreachable_code to get rids of the warning in the case of a test build.
         let this = Self {
             must_stop_processing: MustStopProcessing::default(),
             processing_tasks: Arc::new(RwLock::new(ProcessingTasks::new())),
             file_store,
-            all_tasks,
-            status,
-            kind,
-            index_tasks,
-            canceled_by,
-            enqueued_at,
-            started_at,
-            finished_at,
+            all_tasks: env.create_database(Some(db_name::ALL_TASKS))?,
+            status: env.create_database(Some(db_name::STATUS))?,
+            kind: env.create_database(Some(db_name::KIND))?,
+            index_tasks: env.create_database(Some(db_name::INDEX_TASKS))?,
+            canceled_by: env.create_database(Some(db_name::CANCELED_BY))?,
+            enqueued_at: env.create_database(Some(db_name::ENQUEUED_AT))?,
+            started_at: env.create_database(Some(db_name::STARTED_AT))?,
+            finished_at: env.create_database(Some(db_name::FINISHED_AT))?,
             index_mapper: IndexMapper::new(
                 &env,
                 options.indexes_path,
                 budget.map_size,
                 options.index_growth_amount,
                 budget.index_count,
-                options.enable_mdb_writemap,
                 options.indexer_config,
             )?,
             env,
@@ -1303,6 +1284,7 @@ impl<'a> Dump<'a> {
                 KindDump::IndexDeletion => KindWithContent::IndexDeletion {
                     index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
                 },
+                KindDump::IndexClear { index_uids } => KindWithContent::IndexClear { index_uids },
                 KindDump::IndexCreation { primary_key } => KindWithContent::IndexCreation {
                     index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
                     primary_key,
@@ -1490,7 +1472,6 @@ mod tests {
                 dumps_path: tempdir.path().join("dumps"),
                 task_db_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
                 index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
-                enable_mdb_writemap: false,
                 index_growth_amount: 1000 * 1000, // 1 MB
                 index_count: 5,
                 indexer_config,

index-scheduler/src/utils.rs

@@ -258,6 +258,7 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
         K::TaskCancelation { .. }
         | K::TaskDeletion { .. }
         | K::DumpCreation { .. }
+        | K::IndexClear { .. }
         | K::SnapshotCreation => (),
     };
     if let Some(Details::IndexSwap { swaps }) = &mut task.details {

meilisearch-auth/src/store.rs

@@ -55,11 +55,9 @@ impl HeedAuthStore {
         let path = path.as_ref().join(AUTH_DB_PATH);
         create_dir_all(&path)?;
         let env = Arc::new(open_auth_store_env(path.as_ref())?);
-        let mut wtxn = env.write_txn()?;
-        let keys = env.create_database(&mut wtxn, Some(KEY_DB_NAME))?;
+        let keys = env.create_database(Some(KEY_DB_NAME))?;
         let action_keyid_index_expiration =
-            env.create_database(&mut wtxn, Some(KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME))?;
-        wtxn.commit()?;
+            env.create_database(Some(KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME))?;
         Ok(Self { env, keys, action_keyid_index_expiration, should_close_on_drop: true })
     }
 

meilisearch-types/Cargo.toml

@@ -22,7 +22,7 @@ file-store = { path = "../file-store" }
 flate2 = "1.0.25"
 fst = "0.4.7"
 memmap2 = "0.5.10"
-milli = { path = "../milli" }
+milli = { path = "../milli", default-features = false }
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde-cs = "0.2.4"
@@ -40,7 +40,7 @@ meili-snap = { path = "../meili-snap" }
 
 [features]
 # all specialized tokenizations
-all-tokenizations = ["milli/all-tokenizations"]
+default = ["milli/default"]
 
 # chinese specialized tokenization
 chinese = ["milli/chinese"]

meilisearch-types/src/deserr/mod.rs

@@ -150,7 +150,6 @@ make_missing_field_convenience_builder!(MissingApiKeyActions, missing_api_key_ac
 make_missing_field_convenience_builder!(MissingApiKeyExpiresAt, missing_api_key_expires_at);
 make_missing_field_convenience_builder!(MissingApiKeyIndexes, missing_api_key_indexes);
 make_missing_field_convenience_builder!(MissingSwapIndexes, missing_swap_indexes);
-make_missing_field_convenience_builder!(MissingDocumentFilter, missing_document_filter);
 
 // Integrate a sub-error into a [`DeserrError`] by taking its error message but using
 // the default error code (C) from `Self`

meilisearch-types/src/error.rs

@@ -214,12 +214,12 @@ InvalidApiKeyUid                      , InvalidRequest       , BAD_REQUEST ;
 InvalidContentType                    , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
 InvalidDocumentCsvDelimiter           , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentFields                 , InvalidRequest       , BAD_REQUEST ;
-MissingDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentGeoField               , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentDeleteFilter           , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;

meilisearch-types/src/tasks.rs

@@ -46,6 +46,7 @@ impl Task {
             | SnapshotCreation
             | TaskCancelation { .. }
             | TaskDeletion { .. }
+            | IndexClear { .. }
             | IndexSwap { .. } => None,
             DocumentAdditionOrUpdate { index_uid, .. }
             | DocumentDeletion { index_uid, .. }
@@ -72,6 +73,7 @@ impl Task {
             | KindWithContent::DocumentClear { .. }
             | KindWithContent::SettingsUpdate { .. }
             | KindWithContent::IndexDeletion { .. }
+            | KindWithContent::IndexClear { .. }
             | KindWithContent::IndexCreation { .. }
             | KindWithContent::IndexUpdate { .. }
             | KindWithContent::IndexSwap { .. }
@@ -111,6 +113,9 @@ pub enum KindWithContent {
         is_deletion: bool,
         allow_index_creation: bool,
     },
+    IndexClear {
+        index_uids: Vec<String>,
+    },
     IndexDeletion {
         index_uid: String,
     },
@@ -156,6 +161,7 @@ impl KindWithContent {
             KindWithContent::SettingsUpdate { .. } => Kind::SettingsUpdate,
             KindWithContent::IndexCreation { .. } => Kind::IndexCreation,
             KindWithContent::IndexDeletion { .. } => Kind::IndexDeletion,
+            KindWithContent::IndexClear { .. } => Kind::IndexDeletion,
             KindWithContent::IndexUpdate { .. } => Kind::IndexUpdate,
             KindWithContent::IndexSwap { .. } => Kind::IndexSwap,
             KindWithContent::TaskCancelation { .. } => Kind::TaskCancelation,
@@ -181,6 +187,7 @@ impl KindWithContent {
             | IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
             | IndexDeletion { index_uid } => vec![index_uid],
+            IndexClear { index_uids } => index_uids.into_iter().map(|s| s.as_ref()).collect(),
             IndexSwap { swaps } => {
                 let mut indexes = HashSet::<&str>::default();
                 for swap in swaps {
@@ -214,7 +221,9 @@ impl KindWithContent {
                     deleted_documents: None,
                 })
             }
-            KindWithContent::DocumentClear { .. } | KindWithContent::IndexDeletion { .. } => {
+            KindWithContent::DocumentClear { .. }
+            | KindWithContent::IndexDeletion { .. }
+            | KindWithContent::IndexClear { .. } => {
                 Some(Details::ClearAll { deleted_documents: None })
             }
             KindWithContent::SettingsUpdate { new_settings, .. } => {
@@ -268,7 +277,7 @@ impl KindWithContent {
             KindWithContent::SettingsUpdate { new_settings, .. } => {
                 Some(Details::SettingsUpdate { settings: new_settings.clone() })
             }
-            KindWithContent::IndexDeletion { .. } => None,
+            KindWithContent::IndexDeletion { .. } | KindWithContent::IndexClear { .. } => None,
             KindWithContent::IndexCreation { primary_key, .. }
             | KindWithContent::IndexUpdate { primary_key, .. } => {
                 Some(Details::IndexInfo { primary_key: primary_key.clone() })
@@ -307,7 +316,7 @@ impl From<&KindWithContent> for Option<Details> {
             KindWithContent::SettingsUpdate { new_settings, .. } => {
                 Some(Details::SettingsUpdate { settings: new_settings.clone() })
             }
-            KindWithContent::IndexDeletion { .. } => None,
+            KindWithContent::IndexDeletion { .. } | KindWithContent::IndexClear { .. } => None,
             KindWithContent::IndexCreation { primary_key, .. } => {
                 Some(Details::IndexInfo { primary_key: primary_key.clone() })
             }

meilisearch/Cargo.toml

@@ -106,7 +106,7 @@ vergen = { version = "7.5.1", default-features = false, features = ["git"] }
 zip = { version = "0.6.4", optional = true }
 
 [features]
-default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
+default = ["analytics", "meilisearch-types/default", "mini-dashboard"]
 analytics = ["segment"]
 mini-dashboard = ["actix-web-static-files", "static-files", "anyhow", "cargo_toml", "hex", "reqwest", "sha-1", "tempfile", "zip"]
 chinese = ["meilisearch-types/chinese"]

meilisearch/src/analytics/mock_analytics.rs

@@ -5,7 +5,7 @@ use actix_web::HttpRequest;
 use meilisearch_types::InstanceUid;
 use serde_json::Value;
 
-use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
+use super::{find_user_id, Analytics, DocumentDeletionKind};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
 use crate::routes::tasks::TasksFilterQuery;
 use crate::Opt;
@@ -71,8 +71,6 @@ impl Analytics for MockAnalytics {
         _request: &HttpRequest,
     ) {
     }
-    fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-    fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
     fn get_tasks(&self, _query: &TasksFilterQuery, _request: &HttpRequest) {}
     fn health_seen(&self, _request: &HttpRequest) {}
 }

meilisearch/src/analytics/mod.rs

@@ -67,12 +67,6 @@ pub enum DocumentDeletionKind {
     PerFilter,
 }
 
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum DocumentFetchKind {
-    PerDocumentId,
-    Normal { with_filter: bool, limit: usize, offset: usize },
-}
-
 pub trait Analytics: Sync + Send {
     fn instance_uid(&self) -> Option<&InstanceUid>;
 
@@ -96,12 +90,6 @@ pub trait Analytics: Sync + Send {
         request: &HttpRequest,
     );
 
-    // this method should be called to aggregate a fetch documents request
-    fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
-
-    // this method should be called to aggregate a fetch documents request
-    fn post_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
-
     // this method should be called to aggregate a add documents request
     fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest);
 

meilisearch/src/analytics/segment_analytics.rs

@@ -23,9 +23,7 @@ use tokio::select;
 use tokio::sync::mpsc::{self, Receiver, Sender};
 use uuid::Uuid;
 
-use super::{
-    config_user_id_path, DocumentDeletionKind, DocumentFetchKind, MEILISEARCH_CONFIG_PATH,
-};
+use super::{config_user_id_path, DocumentDeletionKind, MEILISEARCH_CONFIG_PATH};
 use crate::analytics::Analytics;
 use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
@@ -74,8 +72,6 @@ pub enum AnalyticsMsg {
     AggregateAddDocuments(DocumentsAggregator),
     AggregateDeleteDocuments(DocumentsDeletionAggregator),
     AggregateUpdateDocuments(DocumentsAggregator),
-    AggregateGetFetchDocuments(DocumentsFetchAggregator),
-    AggregatePostFetchDocuments(DocumentsFetchAggregator),
     AggregateTasks(TasksAggregator),
     AggregateHealth(HealthAggregator),
 }
@@ -143,8 +139,6 @@ impl SegmentAnalytics {
             add_documents_aggregator: DocumentsAggregator::default(),
             delete_documents_aggregator: DocumentsDeletionAggregator::default(),
             update_documents_aggregator: DocumentsAggregator::default(),
-            get_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
-            post_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
             get_tasks_aggregator: TasksAggregator::default(),
             health_aggregator: HealthAggregator::default(),
         });
@@ -211,16 +205,6 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregateUpdateDocuments(aggregate));
     }
 
-    fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) {
-        let aggregate = DocumentsFetchAggregator::from_query(documents_query, request);
-        let _ = self.sender.try_send(AnalyticsMsg::AggregateGetFetchDocuments(aggregate));
-    }
-
-    fn post_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) {
-        let aggregate = DocumentsFetchAggregator::from_query(documents_query, request);
-        let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFetchDocuments(aggregate));
-    }
-
     fn get_tasks(&self, query: &TasksFilterQuery, request: &HttpRequest) {
         let aggregate = TasksAggregator::from_query(query, request);
         let _ = self.sender.try_send(AnalyticsMsg::AggregateTasks(aggregate));
@@ -241,7 +225,6 @@ impl super::Analytics for SegmentAnalytics {
 struct Infos {
     env: String,
     experimental_enable_metrics: bool,
-    experimental_reduce_indexing_memory_usage: bool,
     db_path: bool,
     import_dump: bool,
     dump_dir: bool,
@@ -275,7 +258,6 @@ impl From<Opt> for Infos {
         let Opt {
             db_path,
             experimental_enable_metrics,
-            experimental_reduce_indexing_memory_usage,
             http_addr,
             master_key: _,
             env,
@@ -318,7 +300,6 @@ impl From<Opt> for Infos {
         Self {
             env,
             experimental_enable_metrics,
-            experimental_reduce_indexing_memory_usage,
             db_path: db_path != PathBuf::from("./data.ms"),
             import_dump: import_dump.is_some(),
             dump_dir: dump_dir != PathBuf::from("dumps/"),
@@ -357,8 +338,6 @@ pub struct Segment {
     add_documents_aggregator: DocumentsAggregator,
     delete_documents_aggregator: DocumentsDeletionAggregator,
     update_documents_aggregator: DocumentsAggregator,
-    get_fetch_documents_aggregator: DocumentsFetchAggregator,
-    post_fetch_documents_aggregator: DocumentsFetchAggregator,
     get_tasks_aggregator: TasksAggregator,
     health_aggregator: HealthAggregator,
 }
@@ -421,8 +400,6 @@ impl Segment {
                         Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
-                        Some(AnalyticsMsg::AggregateGetFetchDocuments(agreg)) => self.get_fetch_documents_aggregator.aggregate(agreg),
-                        Some(AnalyticsMsg::AggregatePostFetchDocuments(agreg)) => self.post_fetch_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateTasks(agreg)) => self.get_tasks_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateHealth(agreg)) => self.health_aggregator.aggregate(agreg),
                         None => (),
@@ -473,10 +450,6 @@ impl Segment {
             .into_event(&self.user, "Documents Deleted");
         let update_documents = std::mem::take(&mut self.update_documents_aggregator)
             .into_event(&self.user, "Documents Updated");
-        let get_fetch_documents = std::mem::take(&mut self.get_fetch_documents_aggregator)
-            .into_event(&self.user, "Documents Fetched GET");
-        let post_fetch_documents = std::mem::take(&mut self.post_fetch_documents_aggregator)
-            .into_event(&self.user, "Documents Fetched POST");
         let get_tasks =
             std::mem::take(&mut self.get_tasks_aggregator).into_event(&self.user, "Tasks Seen");
         let health =
@@ -500,12 +473,6 @@ impl Segment {
         if let Some(update_documents) = update_documents {
             let _ = self.batcher.push(update_documents).await;
         }
-        if let Some(get_fetch_documents) = get_fetch_documents {
-            let _ = self.batcher.push(get_fetch_documents).await;
-        }
-        if let Some(post_fetch_documents) = post_fetch_documents {
-            let _ = self.batcher.push(post_fetch_documents).await;
-        }
         if let Some(get_tasks) = get_tasks {
             let _ = self.batcher.push(get_tasks).await;
         }
@@ -1168,76 +1135,3 @@ impl HealthAggregator {
         })
     }
 }
-
-#[derive(Default, Serialize)]
-pub struct DocumentsFetchAggregator {
-    #[serde(skip)]
-    timestamp: Option<OffsetDateTime>,
-
-    // context
-    #[serde(rename = "user-agent")]
-    user_agents: HashSet<String>,
-
-    #[serde(rename = "requests.max_limit")]
-    total_received: usize,
-
-    // a call on ../documents/:doc_id
-    per_document_id: bool,
-    // if a filter was used
-    per_filter: bool,
-
-    // pagination
-    #[serde(rename = "pagination.max_limit")]
-    max_limit: usize,
-    #[serde(rename = "pagination.max_offset")]
-    max_offset: usize,
-}
-
-impl DocumentsFetchAggregator {
-    pub fn from_query(query: &DocumentFetchKind, request: &HttpRequest) -> Self {
-        let (limit, offset) = match query {
-            DocumentFetchKind::PerDocumentId => (1, 0),
-            DocumentFetchKind::Normal { limit, offset, .. } => (*limit, *offset),
-        };
-        Self {
-            timestamp: Some(OffsetDateTime::now_utc()),
-            user_agents: extract_user_agents(request).into_iter().collect(),
-            total_received: 1,
-            per_document_id: matches!(query, DocumentFetchKind::PerDocumentId),
-            per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
-            max_limit: limit,
-            max_offset: offset,
-        }
-    }
-
-    /// Aggregate one [DocumentsFetchAggregator] into another.
-    pub fn aggregate(&mut self, other: Self) {
-        if self.timestamp.is_none() {
-            self.timestamp = other.timestamp;
-        }
-        for user_agent in other.user_agents {
-            self.user_agents.insert(user_agent);
-        }
-
-        self.total_received = self.total_received.saturating_add(other.total_received);
-        self.per_document_id |= other.per_document_id;
-        self.per_filter |= other.per_filter;
-
-        self.max_limit = self.max_limit.max(other.max_limit);
-        self.max_offset = self.max_offset.max(other.max_offset);
-    }
-
-    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
-        // if we had no timestamp it means we never encountered any events and
-        // thus we don't need to send this event.
-        let timestamp = self.timestamp?;
-
-        Some(Track {
-            timestamp: Some(timestamp),
-            user: user.clone(),
-            event: event_name.to_string(),
-            properties: serde_json::to_value(self).ok()?,
-            ..Default::default()
-        })
-    }
-}

meilisearch/src/error.rs

@@ -1,6 +1,5 @@
 use actix_web as aweb;
 use aweb::error::{JsonPayloadError, QueryPayloadError};
-use byte_unit::Byte;
 use meilisearch_types::document_formats::{DocumentFormatError, PayloadType};
 use meilisearch_types::error::{Code, ErrorCode, ResponseError};
 use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError};
@@ -27,8 +26,8 @@ pub enum MeilisearchHttpError {
     InvalidExpression(&'static [&'static str], Value),
     #[error("A {0} payload is missing.")]
     MissingPayload(PayloadType),
-    #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.",  Byte::from_bytes(*.0 as u64).get_appropriate_unit(true))]
-    PayloadTooLarge(usize),
+    #[error("The provided payload reached the size limit.")]
+    PayloadTooLarge,
     #[error("Two indexes must be given for each swap. The list `[{}]` contains {} indexes.",
         .0.iter().map(|uid| format!("\"{uid}\"")).collect::<Vec<_>>().join(", "), .0.len()
     )]
@@ -61,9 +60,9 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::MissingPayload(_) => Code::MissingPayload,
             MeilisearchHttpError::InvalidContentType(_, _) => Code::InvalidContentType,
             MeilisearchHttpError::DocumentNotFound(_) => Code::DocumentNotFound,
-            MeilisearchHttpError::EmptyFilter => Code::InvalidDocumentFilter,
+            MeilisearchHttpError::EmptyFilter => Code::InvalidDocumentDeleteFilter,
             MeilisearchHttpError::InvalidExpression(_, _) => Code::InvalidSearchFilter,
-            MeilisearchHttpError::PayloadTooLarge(_) => Code::PayloadTooLarge,
+            MeilisearchHttpError::PayloadTooLarge => Code::PayloadTooLarge,
             MeilisearchHttpError::SwapIndexPayloadWrongLength(_) => Code::InvalidSwapIndexes,
             MeilisearchHttpError::IndexUid(e) => e.error_code(),
             MeilisearchHttpError::SerdeJson(_) => Code::Internal,

meilisearch/src/extractors/payload.rs

@@ -11,7 +11,6 @@ use crate::error::MeilisearchHttpError;
 pub struct Payload {
     payload: Decompress<dev::Payload>,
     limit: usize,
-    remaining: usize,
 }
 
 pub struct PayloadConfig {
@@ -44,7 +43,6 @@ impl FromRequest for Payload {
         ready(Ok(Payload {
             payload: Decompress::from_headers(payload.take(), req.headers()),
             limit,
-            remaining: limit,
         }))
     }
 }
@@ -56,14 +54,12 @@ impl Stream for Payload {
     fn poll_next(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
         match Pin::new(&mut self.payload).poll_next(cx) {
             Poll::Ready(Some(result)) => match result {
-                Ok(bytes) => match self.remaining.checked_sub(bytes.len()) {
+                Ok(bytes) => match self.limit.checked_sub(bytes.len()) {
                     Some(new_limit) => {
-                        self.remaining = new_limit;
+                        self.limit = new_limit;
                         Poll::Ready(Some(Ok(bytes)))
                     }
-                    None => {
-                        Poll::Ready(Some(Err(MeilisearchHttpError::PayloadTooLarge(self.limit))))
-                    }
+                    None => Poll::Ready(Some(Err(MeilisearchHttpError::PayloadTooLarge))),
                 },
                 x => Poll::Ready(Some(x.map_err(MeilisearchHttpError::from))),
             },

meilisearch/src/lib.rs

@@ -232,7 +232,6 @@ fn open_or_create_database_unchecked(
             dumps_path: opt.dump_dir.clone(),
             task_db_size: opt.max_task_db_size.get_bytes() as usize,
             index_base_map_size: opt.max_index_size.get_bytes() as usize,
-            enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
             indexer_config: (&opt.indexer_options).try_into()?,
             autobatching_enabled: true,
             max_number_of_tasks: 1_000_000,

meilisearch/src/main.rs

@@ -29,11 +29,6 @@ fn setup(opt: &Opt) -> anyhow::Result<()> {
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
-    anyhow::ensure!(
-        !(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
-        "The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"
-    );
-
     setup(&opt)?;
 
     match (opt.env.as_ref(), &opt.master_key) {

meilisearch/src/option.rs

@@ -48,8 +48,6 @@ const MEILI_IGNORE_DUMP_IF_DB_EXISTS: &str = "MEILI_IGNORE_DUMP_IF_DB_EXISTS";
 const MEILI_DUMP_DIR: &str = "MEILI_DUMP_DIR";
 const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
-const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
-    "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
 
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
@@ -295,11 +293,6 @@ pub struct Opt {
     #[serde(default)]
     pub experimental_enable_metrics: bool,
 
-    /// Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
-    #[clap(long, env = MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE)]
-    #[serde(default)]
-    pub experimental_reduce_indexing_memory_usage: bool,
-
     #[serde(flatten)]
     #[clap(flatten)]
     pub indexer_options: IndexerOpts,
@@ -392,7 +385,6 @@ impl Opt {
             #[cfg(all(not(debug_assertions), feature = "analytics"))]
             no_analytics,
             experimental_enable_metrics: enable_metrics_route,
-            experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -434,10 +426,6 @@ impl Opt {
             MEILI_EXPERIMENTAL_ENABLE_METRICS,
             enable_metrics_route.to_string(),
         );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
-            reduce_indexing_memory_usage.to_string(),
-        );
         indexer_options.export_to_env();
     }
 

meilisearch/src/routes/indexes/documents.rs

@@ -29,7 +29,7 @@ use tempfile::tempfile;
 use tokio::fs::File;
 use tokio::io::{AsyncSeekExt, AsyncWriteExt, BufWriter};
 
-use crate::analytics::{Analytics, DocumentDeletionKind, DocumentFetchKind};
+use crate::analytics::{Analytics, DocumentDeletionKind};
 use crate::error::MeilisearchHttpError;
 use crate::error::PayloadError::ReceivePayload;
 use crate::extractors::authentication::policies::*;
@@ -97,14 +97,10 @@ pub async fn get_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
     document_param: web::Path<DocumentParam>,
     params: AwebQueryParameter<GetDocument, DeserrQueryParamError>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = document_param.into_inner();
     let index_uid = IndexUid::try_from(index_uid)?;
 
-    analytics.get_fetch_documents(&DocumentFetchKind::PerDocumentId, &req);
-
     let GetDocument { fields } = params.into_inner();
     let attributes_to_retrieve = fields.merge_star_and_none();
 
@@ -165,31 +161,16 @@ pub async fn documents_by_query_post(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     body: AwebJson<BrowseQuery, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with body: {:?}", body);
 
-    let body = body.into_inner();
-
-    analytics.post_fetch_documents(
-        &DocumentFetchKind::Normal {
-            with_filter: body.filter.is_some(),
-            limit: body.limit,
-            offset: body.offset,
-        },
-        &req,
-    );
-
-    documents_by_query(&index_scheduler, index_uid, body)
+    documents_by_query(&index_scheduler, index_uid, body.into_inner())
 }
 
 pub async fn get_documents(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     params: AwebQueryParameter<BrowseQueryGet, DeserrQueryParamError>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!("called with params: {:?}", params);
 
@@ -210,15 +191,6 @@ pub async fn get_documents(
         filter,
     };
 
-    analytics.get_fetch_documents(
-        &DocumentFetchKind::Normal {
-            with_filter: query.filter.is_some(),
-            limit: query.limit,
-            offset: query.offset,
-        },
-        &req,
-    );
-
     documents_by_query(&index_scheduler, index_uid, query)
 }
 
@@ -486,7 +458,7 @@ pub async fn delete_documents_batch(
 #[derive(Debug, Deserr)]
 #[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
 pub struct DocumentDeletionByFilter {
-    #[deserr(error = DeserrJsonError<InvalidDocumentFilter>, missing_field_error = DeserrJsonError::missing_document_filter)]
+    #[deserr(error = DeserrJsonError<InvalidDocumentDeleteFilter>)]
     filter: Value,
 }
 
@@ -508,8 +480,8 @@ pub async fn delete_documents_by_filter(
     || -> Result<_, ResponseError> {
         Ok(crate::search::parse_filter(&filter)?.ok_or(MeilisearchHttpError::EmptyFilter)?)
     }()
-    // and whatever was the error, the error code should always be an InvalidDocumentFilter
-    .map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
+    // and whatever was the error, the error code should always be an InvalidDocumentDeleteFilter
+    .map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentDeleteFilter))?;
     let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
 
     let task: SummarizedTaskView =
@@ -568,12 +540,7 @@ fn retrieve_documents<S: AsRef<str>>(
     };
 
     let candidates = if let Some(filter) = filter {
-        filter.evaluate(&rtxn, index).map_err(|err| match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                ResponseError::from_msg(err.to_string(), Code::InvalidDocumentFilter)
-            }
-            e => e.into(),
-        })?
+        filter.evaluate(&rtxn, index)?
     } else {
         index.documents_ids(&rtxn)?
     };

meilisearch/src/routes/indexes/mod.rs

@@ -31,7 +31,8 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
         web::resource("")
             .route(web::get().to(list_indexes))
-            .route(web::post().to(SeqHandler(create_index))),
+            .route(web::post().to(SeqHandler(create_index)))
+            .route(web::delete().to(SeqHandler(delete_all_indexes))),
     )
     .service(
         web::scope("/{index_uid}")
@@ -107,6 +108,22 @@ pub async fn list_indexes(
     Ok(HttpResponse::Ok().json(ret))
 }
 
+pub async fn delete_all_indexes(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_DELETE }>, Data<IndexScheduler>>,
+    _req: HttpRequest,
+    _analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let filters = index_scheduler.filters();
+    let indexes = index_scheduler.index_names()?;
+    let indexes = indexes.into_iter().filter(|uid| filters.is_index_authorized(uid)).collect();
+
+    let task = KindWithContent::IndexClear { index_uids: indexes };
+    let task: SummarizedTaskView =
+        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+
+    Ok(HttpResponse::Accepted().json(task))
+}
+
 #[derive(Deserr, Debug)]
 #[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
 pub struct IndexCreateRequest {

meilisearch/src/routes/tasks.rs

@@ -99,7 +99,7 @@ pub struct DetailsView {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub deleted_tasks: Option<Option<u64>>,
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub original_filter: Option<Option<String>>,
+    pub original_filter: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub dump_uid: Option<Option<String>>,
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -131,13 +131,12 @@ impl From<Details> for DetailsView {
             } => DetailsView {
                 provided_ids: Some(received_document_ids),
                 deleted_documents: Some(deleted_documents),
-                original_filter: Some(None),
                 ..DetailsView::default()
             },
             Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
                 DetailsView {
                     provided_ids: Some(0),
-                    original_filter: Some(Some(original_filter)),
+                    original_filter: Some(original_filter),
                     deleted_documents: Some(deleted_documents),
                     ..DetailsView::default()
                 }
@@ -149,7 +148,7 @@ impl From<Details> for DetailsView {
                 DetailsView {
                     matched_tasks: Some(matched_tasks),
                     canceled_tasks: Some(canceled_tasks),
-                    original_filter: Some(Some(original_filter)),
+                    original_filter: Some(original_filter),
                     ..DetailsView::default()
                 }
             }
@@ -157,7 +156,7 @@ impl From<Details> for DetailsView {
                 DetailsView {
                     matched_tasks: Some(matched_tasks),
                     deleted_tasks: Some(deleted_tasks),
-                    original_filter: Some(Some(original_filter)),
+                    original_filter: Some(original_filter),
                     ..DetailsView::default()
                 }
             }

meilisearch/tests/auth/authorization.rs

@@ -16,11 +16,8 @@ pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'
             ("GET",     "/indexes/products/search") =>                         hashset!{"search", "*"},
             ("POST",    "/indexes/products/documents") =>                      hashset!{"documents.add", "documents.*", "*"},
             ("GET",     "/indexes/products/documents") =>                      hashset!{"documents.get", "documents.*", "*"},
-            ("POST",    "/indexes/products/documents/fetch") =>                hashset!{"documents.get", "documents.*", "*"},
             ("GET",     "/indexes/products/documents/0") =>                    hashset!{"documents.get", "documents.*", "*"},
             ("DELETE",  "/indexes/products/documents/0") =>                    hashset!{"documents.delete", "documents.*", "*"},
-            ("POST",    "/indexes/products/documents/delete-batch") =>         hashset!{"documents.delete", "documents.*", "*"},
-            ("POST",    "/indexes/products/documents/delete") =>               hashset!{"documents.delete", "documents.*", "*"},
             ("GET",     "/tasks") =>                                           hashset!{"tasks.get", "tasks.*", "*"},
             ("DELETE",  "/tasks") =>                                           hashset!{"tasks.delete", "tasks.*", "*"},
             ("GET",     "/tasks?indexUid=products") =>                         hashset!{"tasks.get", "tasks.*", "*"},

meilisearch/tests/documents/add_documents.rs

@@ -1781,7 +1781,7 @@ async fn error_add_documents_payload_size() {
     snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
         @r###"
     {
-      "message": "The provided payload reached the size limit. The maximum accepted payload size is 10.00 MiB.",
+      "message": "The provided payload reached the size limit.",
       "code": "payload_too_large",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#payload_too_large"

meilisearch/tests/documents/errors.rs

@@ -180,9 +180,9 @@ async fn get_all_documents_bad_filter() {
     snapshot!(json_string!(response), @r###"
     {
       "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo=bernese",
-      "code": "invalid_document_filter",
+      "code": "invalid_search_filter",
       "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
+      "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
     }
     "###);
 }
@@ -547,9 +547,9 @@ async fn delete_document_by_filter() {
     snapshot!(json_string!(response), @r###"
     {
       "message": "Invalid syntax for the filter parameter: `expected String, Array, found: true`.",
-      "code": "invalid_document_filter",
+      "code": "invalid_document_delete_filter",
       "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
+      "link": "https://docs.meilisearch.com/errors#invalid_document_delete_filter"
     }
     "###);
 
@@ -559,9 +559,9 @@ async fn delete_document_by_filter() {
     snapshot!(json_string!(response), @r###"
     {
       "message": "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 `hello`.\n1:6 hello",
-      "code": "invalid_document_filter",
+      "code": "invalid_document_delete_filter",
       "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
+      "link": "https://docs.meilisearch.com/errors#invalid_document_delete_filter"
     }
     "###);
 
@@ -571,21 +571,9 @@ async fn delete_document_by_filter() {
     snapshot!(json_string!(response), @r###"
     {
       "message": "Sending an empty filter is forbidden.",
-      "code": "invalid_document_filter",
+      "code": "invalid_document_delete_filter",
       "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
-    }
-    "###);
-
-    // do not send any filter
-    let (response, code) = index.delete_document_by_filter(json!({})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Missing field `filter`",
-      "code": "missing_document_filter",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#missing_document_filter"
+      "link": "https://docs.meilisearch.com/errors#invalid_document_delete_filter"
     }
     "###);
 
@@ -642,9 +630,9 @@ async fn delete_document_by_filter() {
       },
       "error": {
         "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
-        "code": "invalid_document_filter",
+        "code": "invalid_search_filter",
         "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
+        "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
       },
       "duration": "[duration]",
       "enqueuedAt": "[date]",
@@ -676,9 +664,9 @@ async fn delete_document_by_filter() {
       },
       "error": {
         "message": "Attribute `catto` is not filterable. Available filterable attributes are: `doggo`.\n1:6 catto = jorts",
-        "code": "invalid_document_filter",
+        "code": "invalid_search_filter",
         "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
+        "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
       },
       "duration": "[duration]",
       "enqueuedAt": "[date]",
@@ -760,27 +748,4 @@ async fn fetch_document_by_filter() {
       "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
     }
     "###);
-
-    let (response, code) = index.get_document_by_filter(json!({ "filter": "cool doggo" })).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "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 `cool doggo`.\n1:11 cool doggo",
-      "code": "invalid_document_filter",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
-    }
-    "###);
-
-    let (response, code) =
-        index.get_document_by_filter(json!({ "filter": "doggo = bernese" })).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Attribute `doggo` is not filterable. Available filterable attributes are: `color`.\n1:6 doggo = bernese",
-      "code": "invalid_document_filter",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
-    }
-    "###);
 }

meilisearch/tests/search/errors.rs

@@ -946,7 +946,7 @@ async fn sort_unset_ranking_rule() {
     index.wait_task(1).await;
 
     let expected_response = json!({
-        "message": "You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.",
+        "message": "The sort ranking rule must be specified in the ranking rules settings to use the sort parameter at search time.",
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"

meilisearch/tests/tasks/mod.rs

@@ -413,7 +413,7 @@ async fn test_summarized_document_addition_or_update() {
 }
 
 #[actix_web::test]
-async fn test_summarized_delete_documents_by_batch() {
+async fn test_summarized_delete_batch() {
     let server = Server::new().await;
     let index = server.index("test");
     index.delete_batch(vec![1, 2, 3]).await;
@@ -430,8 +430,7 @@ async fn test_summarized_delete_documents_by_batch() {
       "canceledBy": null,
       "details": {
         "providedIds": 3,
-        "deletedDocuments": 0,
-        "originalFilter": null
+        "deletedDocuments": 0
       },
       "error": {
         "message": "Index `test` not found.",
@@ -461,8 +460,7 @@ async fn test_summarized_delete_documents_by_batch() {
       "canceledBy": null,
       "details": {
         "providedIds": 1,
-        "deletedDocuments": 0,
-        "originalFilter": null
+        "deletedDocuments": 0
       },
       "error": null,
       "duration": "[duration]",
@@ -474,100 +472,7 @@ async fn test_summarized_delete_documents_by_batch() {
 }
 
 #[actix_web::test]
-async fn test_summarized_delete_documents_by_filter() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.delete_document_by_filter(json!({ "filter": "doggo = bernese" })).await;
-    index.wait_task(0).await;
-    let (task, _) = index.get_task(0).await;
-    assert_json_snapshot!(task,
-        { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" },
-        @r###"
-    {
-      "uid": 0,
-      "indexUid": "test",
-      "status": "failed",
-      "type": "documentDeletion",
-      "canceledBy": null,
-      "details": {
-        "providedIds": 0,
-        "deletedDocuments": 0,
-        "originalFilter": "\"doggo = bernese\""
-      },
-      "error": {
-        "message": "Index `test` not found.",
-        "code": "index_not_found",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#index_not_found"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    index.create(None).await;
-    index.delete_document_by_filter(json!({ "filter": "doggo = bernese" })).await;
-    index.wait_task(2).await;
-    let (task, _) = index.get_task(2).await;
-    assert_json_snapshot!(task,
-        { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" },
-        @r###"
-    {
-      "uid": 2,
-      "indexUid": "test",
-      "status": "failed",
-      "type": "documentDeletion",
-      "canceledBy": null,
-      "details": {
-        "providedIds": 0,
-        "deletedDocuments": 0,
-        "originalFilter": "\"doggo = bernese\""
-      },
-      "error": {
-        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
-        "code": "invalid_document_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    index.update_settings(json!({ "filterableAttributes": ["doggo"] })).await;
-    index.delete_document_by_filter(json!({ "filter": "doggo = bernese" })).await;
-    index.wait_task(4).await;
-    let (task, _) = index.get_task(4).await;
-    assert_json_snapshot!(task,
-        { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" },
-        @r###"
-    {
-      "uid": 4,
-      "indexUid": "test",
-      "status": "succeeded",
-      "type": "documentDeletion",
-      "canceledBy": null,
-      "details": {
-        "providedIds": 0,
-        "deletedDocuments": 0,
-        "originalFilter": "\"doggo = bernese\""
-      },
-      "error": null,
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-}
-
-#[actix_web::test]
-async fn test_summarized_delete_document_by_id() {
+async fn test_summarized_delete_document() {
     let server = Server::new().await;
     let index = server.index("test");
     index.delete_document(1).await;
@@ -584,8 +489,7 @@ async fn test_summarized_delete_document_by_id() {
       "canceledBy": null,
       "details": {
         "providedIds": 1,
-        "deletedDocuments": 0,
-        "originalFilter": null
+        "deletedDocuments": 0
       },
       "error": {
         "message": "Index `test` not found.",
@@ -615,8 +519,7 @@ async fn test_summarized_delete_document_by_id() {
       "canceledBy": null,
       "details": {
         "providedIds": 1,
-        "deletedDocuments": 0,
-        "originalFilter": null
+        "deletedDocuments": 0
       },
       "error": null,
       "duration": "[duration]",

milli/Cargo.toml

@@ -25,13 +25,8 @@ flatten-serde-json = { path = "../flatten-serde-json" }
 fst = "0.4.7"
 fxhash = "0.2.1"
 geoutils = "0.5.1"
-grenad = { version = "0.4.4", default-features = false, features = [
-    "tempfile",
-] }
-heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.6", default-features = false, features = [
-    "lmdb",
-    "sync-read-txn",
-] }
+grenad = { version = "0.4.4", default-features = false, features = ["tempfile"] }
+heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.5", default-features = false, features = ["lmdb", "sync-read-txn"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 memmap2 = "0.5.10"
@@ -44,17 +39,12 @@ rstar = { version = "0.10.0", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
 slice-group-by = "0.3.0"
-smallstr = { version = "0.3.0", features = ["serde"] }
+smallstr =  { version = "0.3.0", features = ["serde"] }
 smallvec = "1.10.0"
 smartstring = "1.0.1"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
-time = { version = "0.3.20", features = [
-    "serde-well-known",
-    "formatting",
-    "parsing",
-    "macros",
-] }
+time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 uuid = { version = "1.3.1", features = ["v4"] }
 
 filter-parser = { path = "../filter-parser" }
@@ -73,13 +63,13 @@ big_s = "1.0.2"
 insta = "1.29.0"
 maplit = "1.0.2"
 md5 = "0.7.0"
-rand = { version = "0.8.5", features = ["small_rng"] }
+rand = {version = "0.8.5", features = ["small_rng"] }
 
 [target.'cfg(fuzzing)'.dev-dependencies]
 fuzzcheck = "0.12.1"
 
 [features]
-all-tokenizations = ["charabia/default"]
+default = [ "charabia/default" ]
 
 # Use POSIX semaphores instead of SysV semaphores in LMDB
 # For more information on this feature, see heed's Cargo.toml

milli/src/error.rs

@@ -126,7 +126,7 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
     InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
     #[error("{}", HeedError::BadOpenOptions)]
     InvalidLmdbOpenOptions,
-    #[error("You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.")]
+    #[error("The sort ranking rule must be specified in the ranking rules settings to use the sort parameter at search time.")]
     SortRankingRuleMissing,
     #[error("The database file is in an invalid state.")]
     InvalidStoreFile,

milli/src/index.rs

@@ -170,46 +170,33 @@ impl Index {
         unsafe { options.flag(Flags::MdbAlwaysFreePages) };
 
         let env = options.open(path)?;
-        let mut wtxn = env.write_txn()?;
-        let main = env.create_poly_database(&mut wtxn, Some(MAIN))?;
-        let word_docids = env.create_database(&mut wtxn, Some(WORD_DOCIDS))?;
-        let exact_word_docids = env.create_database(&mut wtxn, Some(EXACT_WORD_DOCIDS))?;
-        let word_prefix_docids = env.create_database(&mut wtxn, Some(WORD_PREFIX_DOCIDS))?;
-        let exact_word_prefix_docids =
-            env.create_database(&mut wtxn, Some(EXACT_WORD_PREFIX_DOCIDS))?;
-        let docid_word_positions = env.create_database(&mut wtxn, Some(DOCID_WORD_POSITIONS))?;
-        let word_pair_proximity_docids =
-            env.create_database(&mut wtxn, Some(WORD_PAIR_PROXIMITY_DOCIDS))?;
-        let script_language_docids =
-            env.create_database(&mut wtxn, Some(SCRIPT_LANGUAGE_DOCIDS))?;
+        let main = env.create_poly_database(Some(MAIN))?;
+        let word_docids = env.create_database(Some(WORD_DOCIDS))?;
+        let exact_word_docids = env.create_database(Some(EXACT_WORD_DOCIDS))?;
+        let word_prefix_docids = env.create_database(Some(WORD_PREFIX_DOCIDS))?;
+        let exact_word_prefix_docids = env.create_database(Some(EXACT_WORD_PREFIX_DOCIDS))?;
+        let docid_word_positions = env.create_database(Some(DOCID_WORD_POSITIONS))?;
+        let word_pair_proximity_docids = env.create_database(Some(WORD_PAIR_PROXIMITY_DOCIDS))?;
+        let script_language_docids = env.create_database(Some(SCRIPT_LANGUAGE_DOCIDS))?;
         let word_prefix_pair_proximity_docids =
-            env.create_database(&mut wtxn, Some(WORD_PREFIX_PAIR_PROXIMITY_DOCIDS))?;
+            env.create_database(Some(WORD_PREFIX_PAIR_PROXIMITY_DOCIDS))?;
         let prefix_word_pair_proximity_docids =
-            env.create_database(&mut wtxn, Some(PREFIX_WORD_PAIR_PROXIMITY_DOCIDS))?;
-        let word_position_docids = env.create_database(&mut wtxn, Some(WORD_POSITION_DOCIDS))?;
-        let word_fid_docids = env.create_database(&mut wtxn, Some(WORD_FIELD_ID_DOCIDS))?;
-        let field_id_word_count_docids =
-            env.create_database(&mut wtxn, Some(FIELD_ID_WORD_COUNT_DOCIDS))?;
-        let word_prefix_position_docids =
-            env.create_database(&mut wtxn, Some(WORD_PREFIX_POSITION_DOCIDS))?;
-        let word_prefix_fid_docids =
-            env.create_database(&mut wtxn, Some(WORD_PREFIX_FIELD_ID_DOCIDS))?;
-        let facet_id_f64_docids = env.create_database(&mut wtxn, Some(FACET_ID_F64_DOCIDS))?;
-        let facet_id_string_docids =
-            env.create_database(&mut wtxn, Some(FACET_ID_STRING_DOCIDS))?;
-        let facet_id_exists_docids =
-            env.create_database(&mut wtxn, Some(FACET_ID_EXISTS_DOCIDS))?;
-        let facet_id_is_null_docids =
-            env.create_database(&mut wtxn, Some(FACET_ID_IS_NULL_DOCIDS))?;
-        let facet_id_is_empty_docids =
-            env.create_database(&mut wtxn, Some(FACET_ID_IS_EMPTY_DOCIDS))?;
+            env.create_database(Some(PREFIX_WORD_PAIR_PROXIMITY_DOCIDS))?;
+        let word_position_docids = env.create_database(Some(WORD_POSITION_DOCIDS))?;
+        let word_fid_docids = env.create_database(Some(WORD_FIELD_ID_DOCIDS))?;
+        let field_id_word_count_docids = env.create_database(Some(FIELD_ID_WORD_COUNT_DOCIDS))?;
+        let word_prefix_position_docids = env.create_database(Some(WORD_PREFIX_POSITION_DOCIDS))?;
+        let word_prefix_fid_docids = env.create_database(Some(WORD_PREFIX_FIELD_ID_DOCIDS))?;
+        let facet_id_f64_docids = env.create_database(Some(FACET_ID_F64_DOCIDS))?;
+        let facet_id_string_docids = env.create_database(Some(FACET_ID_STRING_DOCIDS))?;
+        let facet_id_exists_docids = env.create_database(Some(FACET_ID_EXISTS_DOCIDS))?;
+        let facet_id_is_null_docids = env.create_database(Some(FACET_ID_IS_NULL_DOCIDS))?;
+        let facet_id_is_empty_docids = env.create_database(Some(FACET_ID_IS_EMPTY_DOCIDS))?;
 
-        let field_id_docid_facet_f64s =
-            env.create_database(&mut wtxn, Some(FIELD_ID_DOCID_FACET_F64S))?;
+        let field_id_docid_facet_f64s = env.create_database(Some(FIELD_ID_DOCID_FACET_F64S))?;
         let field_id_docid_facet_strings =
-            env.create_database(&mut wtxn, Some(FIELD_ID_DOCID_FACET_STRINGS))?;
-        let documents = env.create_database(&mut wtxn, Some(DOCUMENTS))?;
-        wtxn.commit()?;
+            env.create_database(Some(FIELD_ID_DOCID_FACET_STRINGS))?;
+        let documents = env.create_database(Some(DOCUMENTS))?;
 
         Index::set_creation_dates(&env, main, created_at, updated_at)?;
 

milli/src/search/mod.rs

@@ -201,14 +201,12 @@ pub fn build_dfa(word: &str, typos: u8, is_prefix: bool) -> DFA {
 
 #[cfg(test)]
 mod test {
-    #[allow(unused_imports)]
     use super::*;
+    use crate::index::tests::TempIndex;
 
-    #[cfg(feature = "japanese")]
+    #[cfg(feature = "default")]
     #[test]
     fn test_kanji_language_detection() {
-        use crate::index::tests::TempIndex;
-
         let index = TempIndex::new();
 
         index

milli/src/search/new/bucket_sort.rs

@@ -116,15 +116,16 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     }
 
     while valid_docids.len() < length {
-        // The universe for this bucket is zero element, so we don't need to sort
-        // anything, just go back to the parent ranking rule.
-        if ranking_rule_universes[cur_ranking_rule_index].is_empty() {
+        // The universe for this bucket is zero or one element, so we don't need to sort
+        // anything, just extend the results and go back to the parent ranking rule.
+        if ranking_rule_universes[cur_ranking_rule_index].len() <= 1 {
+            let bucket = std::mem::take(&mut ranking_rule_universes[cur_ranking_rule_index]);
+            maybe_add_to_results!(bucket);
             back!();
             continue;
         }
 
-        let Some(next_bucket) = ranking_rules[cur_ranking_rule_index].next_bucket(ctx, logger, &ranking_rule_universes[cur_ranking_rule_index])?
-        else {
+        let Some(next_bucket) = ranking_rules[cur_ranking_rule_index].next_bucket(ctx, logger, &ranking_rule_universes[cur_ranking_rule_index])? else {
             back!();
             continue;
         };

milli/src/search/new/graph_based_ranking_rule.rs

@@ -46,7 +46,7 @@ use super::logger::SearchLogger;
 use super::query_graph::QueryNode;
 use super::ranking_rule_graph::{
     ConditionDocIdsCache, DeadEndsCache, ExactnessGraph, FidGraph, PositionGraph, ProximityGraph,
-    RankingRuleGraph, RankingRuleGraphTrait, TypoGraph, WordsGraph,
+    RankingRuleGraph, RankingRuleGraphTrait, TypoGraph,
 };
 use super::small_bitmap::SmallBitmap;
 use super::{QueryGraph, RankingRule, RankingRuleOutput, SearchContext};
@@ -54,12 +54,6 @@ use crate::search::new::query_term::LocatedQueryTermSubset;
 use crate::search::new::ranking_rule_graph::PathVisitor;
 use crate::{Result, TermsMatchingStrategy};
 
-pub type Words = GraphBasedRankingRule<WordsGraph>;
-impl GraphBasedRankingRule<WordsGraph> {
-    pub fn new(terms_matching_strategy: TermsMatchingStrategy) -> Self {
-        Self::new_with_id("words".to_owned(), Some(terms_matching_strategy))
-    }
-}
 pub type Proximity = GraphBasedRankingRule<ProximityGraph>;
 impl GraphBasedRankingRule<ProximityGraph> {
     pub fn new(terms_matching_strategy: Option<TermsMatchingStrategy>) -> Self {
@@ -181,6 +175,9 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
         logger: &mut dyn SearchLogger<QueryGraph>,
         universe: &RoaringBitmap,
     ) -> Result<Option<RankingRuleOutput<QueryGraph>>> {
+        // If universe.len() <= 1, the bucket sort algorithm
+        // should not have called this function.
+        assert!(universe.len() > 1);
         // Will crash if `next_bucket` is called before `start_iteration` or after `end_iteration`,
         // should never happen
         let mut state = self.state.take().unwrap();

milli/src/search/new/logger/visual.rs

@@ -4,6 +4,7 @@ use std::io::{BufWriter, Write};
 use std::path::{Path, PathBuf};
 use std::time::Instant;
 
+// use rand::random;
 use roaring::RoaringBitmap;
 
 use crate::search::new::interner::Interned;
@@ -12,7 +13,6 @@ use crate::search::new::query_term::LocatedQueryTermSubset;
 use crate::search::new::ranking_rule_graph::{
     Edge, FidCondition, FidGraph, PositionCondition, PositionGraph, ProximityCondition,
     ProximityGraph, RankingRuleGraph, RankingRuleGraphTrait, TypoCondition, TypoGraph,
-    WordsCondition, WordsGraph,
 };
 use crate::search::new::ranking_rules::BoxRankingRule;
 use crate::search::new::{QueryGraph, QueryNode, RankingRule, SearchContext, SearchLogger};
@@ -24,12 +24,11 @@ pub enum SearchEvents {
     RankingRuleSkipBucket { ranking_rule_idx: usize, bucket_len: u64 },
     RankingRuleEndIteration { ranking_rule_idx: usize, universe_len: u64 },
     ExtendResults { new: Vec<u32> },
+    WordsGraph { query_graph: QueryGraph },
     ProximityGraph { graph: RankingRuleGraph<ProximityGraph> },
     ProximityPaths { paths: Vec<Vec<Interned<ProximityCondition>>> },
     TypoGraph { graph: RankingRuleGraph<TypoGraph> },
     TypoPaths { paths: Vec<Vec<Interned<TypoCondition>>> },
-    WordsGraph { graph: RankingRuleGraph<WordsGraph> },
-    WordsPaths { paths: Vec<Vec<Interned<WordsCondition>>> },
     FidGraph { graph: RankingRuleGraph<FidGraph> },
     FidPaths { paths: Vec<Vec<Interned<FidCondition>>> },
     PositionGraph { graph: RankingRuleGraph<PositionGraph> },
@@ -140,11 +139,8 @@ impl SearchLogger<QueryGraph> for VisualSearchLogger {
         let Some(location) = self.location.last() else { return };
         match location {
             Location::Words => {
-                if let Some(graph) = state.downcast_ref::<RankingRuleGraph<WordsGraph>>() {
-                    self.events.push(SearchEvents::WordsGraph { graph: graph.clone() });
-                }
-                if let Some(paths) = state.downcast_ref::<Vec<Vec<Interned<WordsCondition>>>>() {
-                    self.events.push(SearchEvents::WordsPaths { paths: paths.clone() });
+                if let Some(query_graph) = state.downcast_ref::<QueryGraph>() {
+                    self.events.push(SearchEvents::WordsGraph { query_graph: query_graph.clone() });
                 }
             }
             Location::Typo => {
@@ -333,6 +329,7 @@ impl<'ctx> DetailedLoggerFinish<'ctx> {
             SearchEvents::ExtendResults { new } => {
                 self.write_extend_results(new)?;
             }
+            SearchEvents::WordsGraph { query_graph } => self.write_words_graph(query_graph)?,
             SearchEvents::ProximityGraph { graph } => self.write_rr_graph(&graph)?,
             SearchEvents::ProximityPaths { paths } => {
                 self.write_rr_graph_paths::<ProximityGraph>(paths)?;
@@ -341,10 +338,6 @@ impl<'ctx> DetailedLoggerFinish<'ctx> {
             SearchEvents::TypoPaths { paths } => {
                 self.write_rr_graph_paths::<TypoGraph>(paths)?;
             }
-            SearchEvents::WordsGraph { graph } => self.write_rr_graph(&graph)?,
-            SearchEvents::WordsPaths { paths } => {
-                self.write_rr_graph_paths::<WordsGraph>(paths)?;
-            }
             SearchEvents::FidGraph { graph } => self.write_rr_graph(&graph)?,
             SearchEvents::FidPaths { paths } => {
                 self.write_rr_graph_paths::<FidGraph>(paths)?;
@@ -462,7 +455,7 @@ fill: \"#B6E2D3\"
                 shape: class
                 max_nbr_typo: {}",
                     term_subset.description(ctx),
-                    term_subset.max_typo_cost(ctx)
+                    term_subset.max_nbr_typos(ctx)
                 )?;
 
                 for w in term_subset.all_single_words_except_prefix_db(ctx)? {
@@ -489,6 +482,13 @@ fill: \"#B6E2D3\"
         }
         Ok(())
     }
+    fn write_words_graph(&mut self, qg: QueryGraph) -> Result<()> {
+        self.make_new_file_for_internal_state_if_needed()?;
+
+        self.write_query_graph(&qg)?;
+
+        Ok(())
+    }
     fn write_rr_graph<R: RankingRuleGraphTrait>(
         &mut self,
         graph: &RankingRuleGraph<R>,

milli/src/search/new/matches/matching_words.rs

@@ -52,7 +52,7 @@ impl MatchingWords {
             words.push(LocatedMatchingWords {
                 value: matching_words,
                 positions: located_term.positions.clone(),
-                is_prefix: term.is_prefix(),
+                is_prefix: term.is_cached_prefix(),
                 original_char_count: term.original_word(&ctx).chars().count(),
             });
         }
@@ -244,8 +244,6 @@ pub(crate) mod tests {
         temp_index
             .add_documents(documents!([
                 { "id": 1, "name": "split this world westfali westfalia the Ŵôřlḑôle" },
-                { "id": 2, "name": "Westfália" },
-                { "id": 3, "name": "Ŵôřlḑôle" },
             ]))
             .unwrap();
         temp_index
@@ -307,7 +305,7 @@ pub(crate) mod tests {
                     ..Default::default()
                 })
                 .next(),
-            Some(MatchType::Full { char_len: 5, ids: &(2..=2) })
+            None
         );
         assert_eq!(
             matching_words

milli/src/search/new/matches/mod.rs

@@ -499,36 +499,17 @@ mod tests {
     use charabia::TokenizerBuilder;
     use matching_words::tests::temp_index_with_documents;
 
+    use super::super::located_query_terms_from_tokens;
     use super::*;
-    use crate::index::tests::TempIndex;
-    use crate::{execute_search, SearchContext};
+    use crate::SearchContext;
 
     impl<'a> MatcherBuilder<'a, &[u8]> {
-        fn new_test(rtxn: &'a heed::RoTxn, index: &'a TempIndex, query: &str) -> Self {
-            let mut ctx = SearchContext::new(index, rtxn);
-            let crate::search::PartialSearchResult { located_query_terms, .. } = execute_search(
-                &mut ctx,
-                &Some(query.to_string()),
-                crate::TermsMatchingStrategy::default(),
-                false,
-                &None,
-                &None,
-                crate::search::new::GeoSortStrategy::default(),
-                0,
-                100,
-                Some(10),
-                &mut crate::DefaultSearchLogger,
-                &mut crate::DefaultSearchLogger,
-            )
-            .unwrap();
-
-            // consume context and located_query_terms to build MatchingWords.
-            let matching_words = match located_query_terms {
-                Some(located_query_terms) => MatchingWords::new(ctx, located_query_terms),
-                None => MatchingWords::default(),
-            };
-
-            MatcherBuilder::new(matching_words, TokenizerBuilder::new().build())
+        pub fn new_test(mut ctx: SearchContext, query: &'a str) -> Self {
+            let tokenizer = TokenizerBuilder::new().build();
+            let tokens = tokenizer.tokenize(query);
+            let query_terms = located_query_terms_from_tokens(&mut ctx, tokens, None).unwrap();
+            let matching_words = MatchingWords::new(ctx, query_terms);
+            Self::new(matching_words, TokenizerBuilder::new().build())
         }
     }
 
@@ -536,7 +517,8 @@ mod tests {
     fn format_identity() {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "split the world");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "split the world");
 
         let format_options = FormatOptions { highlight: false, crop: None };
 
@@ -563,7 +545,8 @@ mod tests {
     fn format_highlight() {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "split the world");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "split the world");
 
         let format_options = FormatOptions { highlight: true, crop: None };
 
@@ -606,7 +589,8 @@ mod tests {
     fn highlight_unicode() {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "world");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "world");
         let format_options = FormatOptions { highlight: true, crop: None };
 
         // Text containing prefix match.
@@ -615,7 +599,7 @@ mod tests {
         // no crop should return complete text with highlighted matches.
         insta::assert_snapshot!(
             matcher.format(format_options),
-            @"<em>Ŵôřlḑ</em>ôle"
+            @"<em>Ŵôřlḑôle</em>"
         );
 
         // Text containing unicode match.
@@ -627,7 +611,8 @@ mod tests {
             @"<em>Ŵôřlḑ</em>"
         );
 
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "westfali");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "westfali");
         let format_options = FormatOptions { highlight: true, crop: None };
 
         // Text containing unicode match.
@@ -636,7 +621,7 @@ mod tests {
         // no crop should return complete text with highlighted matches.
         insta::assert_snapshot!(
             matcher.format(format_options),
-            @"<em>Westfáli</em>a"
+            @"<em>Westfália</em>"
         );
     }
 
@@ -644,7 +629,8 @@ mod tests {
     fn format_crop() {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "split the world");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "split the world");
 
         let format_options = FormatOptions { highlight: false, crop: Some(10) };
 
@@ -741,7 +727,8 @@ mod tests {
     fn format_highlight_crop() {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "split the world");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "split the world");
 
         let format_options = FormatOptions { highlight: true, crop: Some(10) };
 
@@ -803,7 +790,8 @@ mod tests {
         //! testing: https://github.com/meilisearch/specifications/pull/120#discussion_r836536295
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "split the world");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let builder = MatcherBuilder::new_test(ctx, "split the world");
 
         let text = "void void split the world void void.";
 
@@ -839,8 +827,8 @@ mod tests {
     fn partial_matches() {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
-        let mut builder =
-            MatcherBuilder::new_test(&rtxn, &temp_index, "the \"t he\" door \"do or\"");
+        let ctx = SearchContext::new(&temp_index, &rtxn);
+        let mut builder = MatcherBuilder::new_test(ctx, "the \"t he\" door \"do or\"");
         builder.highlight_prefix("_".to_string());
         builder.highlight_suffix("_".to_string());
 

milli/src/search/new/mod.rs

@@ -15,7 +15,11 @@ mod resolve_query_graph;
 mod small_bitmap;
 
 mod exact_attribute;
+// TODO: documentation + comments
+// implementation is currently an adaptation of the previous implementation to fit with the new model
 mod sort;
+// TODO: documentation + comments
+mod words;
 
 #[cfg(test)]
 mod tests;
@@ -39,10 +43,10 @@ use ranking_rules::{
 use resolve_query_graph::{compute_query_graph_docids, PhraseDocIdsCache};
 use roaring::RoaringBitmap;
 use sort::Sort;
+use words::Words;
 
 use self::geo_sort::GeoSort;
 pub use self::geo_sort::Strategy as GeoSortStrategy;
-use self::graph_based_ranking_rule::Words;
 use self::interner::Interned;
 use crate::search::new::distinct::apply_distinct_rule;
 use crate::{AscDesc, DocumentId, Filter, Index, Member, Result, TermsMatchingStrategy, UserError};
@@ -198,11 +202,6 @@ fn get_ranking_rules_for_query_graph_search<'ctx>(
     let mut sorted_fields = HashSet::new();
     let mut geo_sorted = false;
 
-    // Don't add the `words` ranking rule if the term matching strategy is `All`
-    if matches!(terms_matching_strategy, TermsMatchingStrategy::All) {
-        words = true;
-    }
-
     let mut ranking_rules: Vec<BoxRankingRule<QueryGraph>> = vec![];
     let settings_ranking_rules = ctx.index.criteria(ctx.txn)?;
     for rr in settings_ranking_rules {
@@ -398,8 +397,8 @@ pub fn execute_search(
         None
     };
     let bucket_sort_output = if let Some(query_terms) = query_terms {
-        let (graph, new_located_query_terms) = QueryGraph::from_query(ctx, &query_terms)?;
-        located_query_terms = Some(new_located_query_terms);
+        let graph = QueryGraph::from_query(ctx, &query_terms)?;
+        located_query_terms = Some(query_terms);
 
         let ranking_rules = get_ranking_rules_for_query_graph_search(
             ctx,

milli/src/search/new/query_graph.rs

@@ -88,15 +88,12 @@ pub struct QueryGraph {
 }
 
 impl QueryGraph {
-    /// Build the query graph from the parsed user search query, return an updated list of the located query terms
-    /// which contains ngrams.
+    /// Build the query graph from the parsed user search query.
     pub fn from_query(
         ctx: &mut SearchContext,
         // NOTE: the terms here must be consecutive
         terms: &[LocatedQueryTerm],
-    ) -> Result<(QueryGraph, Vec<LocatedQueryTerm>)> {
-        let mut new_located_query_terms = terms.to_vec();
-
+    ) -> Result<QueryGraph> {
         let nbr_typos = number_of_typos_allowed(ctx)?;
 
         let mut nodes_data: Vec<QueryNodeData> = vec![QueryNodeData::Start, QueryNodeData::End];
@@ -110,11 +107,10 @@ impl QueryGraph {
         let original_terms_len = terms.len();
         for term_idx in 0..original_terms_len {
             let mut new_nodes = vec![];
-
             let new_node_idx = add_node(
                 &mut nodes_data,
                 QueryNodeData::Term(LocatedQueryTermSubset {
-                    term_subset: QueryTermSubset::full(terms[term_idx].value),
+                    term_subset: QueryTermSubset::full(Interned::from_raw(term_idx as u16)),
                     positions: terms[term_idx].positions.clone(),
                     term_ids: term_idx as u8..=term_idx as u8,
                 }),
@@ -125,7 +121,6 @@ impl QueryGraph {
                 if let Some(ngram) =
                     query_term::make_ngram(ctx, &terms[term_idx - 1..=term_idx], &nbr_typos)?
                 {
-                    new_located_query_terms.push(ngram.clone());
                     let ngram_idx = add_node(
                         &mut nodes_data,
                         QueryNodeData::Term(LocatedQueryTermSubset {
@@ -141,7 +136,6 @@ impl QueryGraph {
                 if let Some(ngram) =
                     query_term::make_ngram(ctx, &terms[term_idx - 2..=term_idx], &nbr_typos)?
                 {
-                    new_located_query_terms.push(ngram.clone());
                     let ngram_idx = add_node(
                         &mut nodes_data,
                         QueryNodeData::Term(LocatedQueryTermSubset {
@@ -173,7 +167,7 @@ impl QueryGraph {
         let mut graph = QueryGraph { root_node, end_node, nodes };
         graph.build_initial_edges();
 
-        Ok((graph, new_located_query_terms))
+        Ok(graph)
     }
 
     /// Remove the given nodes, connecting all their predecessors to all their successors.

milli/src/search/new/query_term/compute_derivations.rs

@@ -28,14 +28,16 @@ pub enum ZeroOrOneTypo {
 impl Interned<QueryTerm> {
     pub fn compute_fully_if_needed(self, ctx: &mut SearchContext) -> Result<()> {
         let s = ctx.term_interner.get_mut(self);
-        if s.max_levenshtein_distance <= 1 && s.one_typo.is_uninit() {
+        if s.max_nbr_typos == 0 {
+            s.one_typo = Lazy::Init(OneTypoTerm::default());
+            s.two_typo = Lazy::Init(TwoTypoTerm::default());
+        } else if s.max_nbr_typos == 1 && s.one_typo.is_uninit() {
             assert!(s.two_typo.is_uninit());
-            // Initialize one_typo subterm even if max_nbr_typo is 0 because of split words
             self.initialize_one_typo_subterm(ctx)?;
             let s = ctx.term_interner.get_mut(self);
             assert!(s.one_typo.is_init());
             s.two_typo = Lazy::Init(TwoTypoTerm::default());
-        } else if s.max_levenshtein_distance > 1 && s.two_typo.is_uninit() {
+        } else if s.max_nbr_typos > 1 && s.two_typo.is_uninit() {
             assert!(s.two_typo.is_uninit());
             self.initialize_one_and_two_typo_subterm(ctx)?;
             let s = ctx.term_interner.get_mut(self);
@@ -185,7 +187,7 @@ pub fn partially_initialized_term_from_word(
                 original: ctx.word_interner.insert(word.to_owned()),
                 ngram_words: None,
                 is_prefix: false,
-                max_levenshtein_distance: 0,
+                max_nbr_typos: 0,
                 zero_typo: <_>::default(),
                 one_typo: Lazy::Init(<_>::default()),
                 two_typo: Lazy::Init(<_>::default()),
@@ -256,7 +258,7 @@ pub fn partially_initialized_term_from_word(
     Ok(QueryTerm {
         original: word_interned,
         ngram_words: None,
-        max_levenshtein_distance: max_typo,
+        max_nbr_typos: max_typo,
         is_prefix,
         zero_typo,
         one_typo: Lazy::Uninit,
@@ -275,16 +277,7 @@ fn find_split_words(ctx: &mut SearchContext, word: &str) -> Result<Option<Intern
 impl Interned<QueryTerm> {
     fn initialize_one_typo_subterm(self, ctx: &mut SearchContext) -> Result<()> {
         let self_mut = ctx.term_interner.get_mut(self);
-
-        let allows_split_words = self_mut.allows_split_words();
-        let QueryTerm {
-            original,
-            is_prefix,
-            one_typo,
-            max_levenshtein_distance: max_nbr_typos,
-            ..
-        } = self_mut;
-
+        let QueryTerm { original, is_prefix, one_typo, .. } = self_mut;
         let original = *original;
         let is_prefix = *is_prefix;
         // let original_str = ctx.word_interner.get(*original).to_owned();
@@ -293,33 +286,26 @@ impl Interned<QueryTerm> {
         }
         let mut one_typo_words = BTreeSet::new();
 
-        if *max_nbr_typos > 0 {
-            find_zero_one_typo_derivations(ctx, original, is_prefix, |derived_word, nbr_typos| {
-                match nbr_typos {
-                    ZeroOrOneTypo::Zero => {}
-                    ZeroOrOneTypo::One => {
-                        if one_typo_words.len() < limits::MAX_ONE_TYPO_COUNT {
-                            one_typo_words.insert(derived_word);
-                        } else {
-                            return Ok(ControlFlow::Break(()));
-                        }
+        find_zero_one_typo_derivations(ctx, original, is_prefix, |derived_word, nbr_typos| {
+            match nbr_typos {
+                ZeroOrOneTypo::Zero => {}
+                ZeroOrOneTypo::One => {
+                    if one_typo_words.len() < limits::MAX_ONE_TYPO_COUNT {
+                        one_typo_words.insert(derived_word);
+                    } else {
+                        return Ok(ControlFlow::Break(()));
                     }
                 }
-                Ok(ControlFlow::Continue(()))
-            })?;
-        }
-
-        let split_words = if allows_split_words {
-            let original_str = ctx.word_interner.get(original).to_owned();
-            find_split_words(ctx, original_str.as_str())?
-        } else {
-            None
-        };
+            }
+            Ok(ControlFlow::Continue(()))
+        })?;
+        let original_str = ctx.word_interner.get(original).to_owned();
+        let split_words = find_split_words(ctx, original_str.as_str())?;
 
         let self_mut = ctx.term_interner.get_mut(self);
 
         // Only add the split words to the derivations if:
-        // 1. the term is neither an ngram nor a phrase; OR
+        // 1. the term is not an ngram; OR
         // 2. the term is an ngram, but the split words are different from the ngram's component words
         let split_words = if let Some((ngram_words, split_words)) =
             self_mut.ngram_words.as_ref().zip(split_words.as_ref())
@@ -341,13 +327,7 @@ impl Interned<QueryTerm> {
     }
     fn initialize_one_and_two_typo_subterm(self, ctx: &mut SearchContext) -> Result<()> {
         let self_mut = ctx.term_interner.get_mut(self);
-        let QueryTerm {
-            original,
-            is_prefix,
-            two_typo,
-            max_levenshtein_distance: max_nbr_typos,
-            ..
-        } = self_mut;
+        let QueryTerm { original, is_prefix, two_typo, .. } = self_mut;
         let original_str = ctx.word_interner.get(*original).to_owned();
         if two_typo.is_init() {
             return Ok(());
@@ -355,37 +335,34 @@ impl Interned<QueryTerm> {
         let mut one_typo_words = BTreeSet::new();
         let mut two_typo_words = BTreeSet::new();
 
-        if *max_nbr_typos > 0 {
-            find_zero_one_two_typo_derivations(
-                *original,
-                *is_prefix,
-                ctx.index.words_fst(ctx.txn)?,
-                &mut ctx.word_interner,
-                |derived_word, nbr_typos| {
-                    if one_typo_words.len() >= limits::MAX_ONE_TYPO_COUNT
-                        && two_typo_words.len() >= limits::MAX_TWO_TYPOS_COUNT
-                    {
-                        // No chance we will add either one- or two-typo derivations anymore, stop iterating.
-                        return Ok(ControlFlow::Break(()));
-                    }
-                    match nbr_typos {
-                        NumberOfTypos::Zero => {}
-                        NumberOfTypos::One => {
-                            if one_typo_words.len() < limits::MAX_ONE_TYPO_COUNT {
-                                one_typo_words.insert(derived_word);
-                            }
-                        }
-                        NumberOfTypos::Two => {
-                            if two_typo_words.len() < limits::MAX_TWO_TYPOS_COUNT {
-                                two_typo_words.insert(derived_word);
-                            }
+        find_zero_one_two_typo_derivations(
+            *original,
+            *is_prefix,
+            ctx.index.words_fst(ctx.txn)?,
+            &mut ctx.word_interner,
+            |derived_word, nbr_typos| {
+                if one_typo_words.len() >= limits::MAX_ONE_TYPO_COUNT
+                    && two_typo_words.len() >= limits::MAX_TWO_TYPOS_COUNT
+                {
+                    // No chance we will add either one- or two-typo derivations anymore, stop iterating.
+                    return Ok(ControlFlow::Break(()));
+                }
+                match nbr_typos {
+                    NumberOfTypos::Zero => {}
+                    NumberOfTypos::One => {
+                        if one_typo_words.len() < limits::MAX_ONE_TYPO_COUNT {
+                            one_typo_words.insert(derived_word);
                         }
                     }
-                    Ok(ControlFlow::Continue(()))
-                },
-            )?;
-        }
-
+                    NumberOfTypos::Two => {
+                        if two_typo_words.len() < limits::MAX_TWO_TYPOS_COUNT {
+                            two_typo_words.insert(derived_word);
+                        }
+                    }
+                }
+                Ok(ControlFlow::Continue(()))
+            },
+        )?;
         let split_words = find_split_words(ctx, original_str.as_str())?;
         let self_mut = ctx.term_interner.get_mut(self);
 

milli/src/search/new/query_term/mod.rs

@@ -43,7 +43,7 @@ pub struct QueryTermSubset {
 pub struct QueryTerm {
     original: Interned<String>,
     ngram_words: Option<Vec<Interned<String>>>,
-    max_levenshtein_distance: u8,
+    max_nbr_typos: u8,
     is_prefix: bool,
     zero_typo: ZeroTypoTerm,
     // May not be computed yet
@@ -342,16 +342,10 @@ impl QueryTermSubset {
         }
         None
     }
-    pub fn max_typo_cost(&self, ctx: &SearchContext) -> u8 {
+    pub fn max_nbr_typos(&self, ctx: &SearchContext) -> u8 {
         let t = ctx.term_interner.get(self.original);
-        match t.max_levenshtein_distance {
-            0 => {
-                if t.allows_split_words() {
-                    1
-                } else {
-                    0
-                }
-            }
+        match t.max_nbr_typos {
+            0 => 0,
             1 => {
                 if self.one_typo_subset.is_empty() {
                     0
@@ -444,9 +438,6 @@ impl QueryTerm {
 
         self.zero_typo.is_empty() && one_typo.is_empty() && two_typo.is_empty()
     }
-    fn allows_split_words(&self) -> bool {
-        self.zero_typo.phrase.is_none()
-    }
 }
 
 impl Interned<QueryTerm> {
@@ -479,9 +470,6 @@ impl QueryTerm {
     pub fn is_cached_prefix(&self) -> bool {
         self.zero_typo.use_prefix_db.is_some()
     }
-    pub fn is_prefix(&self) -> bool {
-        self.is_prefix
-    }
     pub fn original_word(&self, ctx: &SearchContext) -> String {
         ctx.word_interner.get(self.original).clone()
     }

milli/src/search/new/query_term/parse_query.rs

@@ -77,9 +77,13 @@ pub fn located_query_terms_from_tokens(
                 }
             }
             TokenKind::Separator(separator_kind) => {
-                // add penalty for hard separators
-                if let SeparatorKind::Hard = separator_kind {
-                    position = position.wrapping_add(1);
+                match separator_kind {
+                    SeparatorKind::Hard => {
+                        position += 1;
+                    }
+                    SeparatorKind::Soft => {
+                        position += 0;
+                    }
                 }
 
                 phrase = 'phrase: {
@@ -213,7 +217,7 @@ pub fn make_ngram(
         original: ngram_str_interned,
         ngram_words: Some(words_interned),
         is_prefix,
-        max_levenshtein_distance: max_nbr_typos,
+        max_nbr_typos,
         zero_typo: term.zero_typo,
         one_typo: Lazy::Uninit,
         two_typo: Lazy::Uninit,
@@ -267,7 +271,7 @@ impl PhraseBuilder {
                 QueryTerm {
                     original: ctx.word_interner.insert(phrase_desc),
                     ngram_words: None,
-                    max_levenshtein_distance: 0,
+                    max_nbr_typos: 0,
                     is_prefix: false,
                     zero_typo: ZeroTypoTerm {
                         phrase: Some(phrase),
@@ -284,36 +288,3 @@ impl PhraseBuilder {
         })
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use charabia::TokenizerBuilder;
-
-    use super::*;
-    use crate::index::tests::TempIndex;
-
-    fn temp_index_with_documents() -> TempIndex {
-        let temp_index = TempIndex::new();
-        temp_index
-            .add_documents(documents!([
-                { "id": 1, "name": "split this world westfali westfalia the Ŵôřlḑôle" },
-                { "id": 2, "name": "Westfália" },
-                { "id": 3, "name": "Ŵôřlḑôle" },
-            ]))
-            .unwrap();
-        temp_index
-    }
-
-    #[test]
-    fn start_with_hard_separator() -> Result<()> {
-        let tokenizer = TokenizerBuilder::new().build();
-        let tokens = tokenizer.tokenize(".");
-        let index = temp_index_with_documents();
-        let rtxn = index.read_txn()?;
-        let mut ctx = SearchContext::new(&index, &rtxn);
-        // panics with `attempt to add with overflow` before <https://github.com/meilisearch/meilisearch/issues/3785>
-        let located_query_terms = located_query_terms_from_tokens(&mut ctx, tokens, None)?;
-        assert!(located_query_terms.is_empty());
-        Ok(())
-    }
-}

milli/src/search/new/ranking_rule_graph/cheapest_paths.rs

@@ -205,12 +205,18 @@ impl<G: RankingRuleGraphTrait> VisitorState<G> {
 impl<G: RankingRuleGraphTrait> RankingRuleGraph<G> {
     pub fn find_all_costs_to_end(&self) -> MappedInterner<QueryNode, Vec<u64>> {
         let mut costs_to_end = self.query_graph.nodes.map(|_| vec![]);
+        let mut enqueued = SmallBitmap::new(self.query_graph.nodes.len());
 
-        self.traverse_breadth_first_backward(self.query_graph.end_node, |cur_node| {
-            if cur_node == self.query_graph.end_node {
-                *costs_to_end.get_mut(self.query_graph.end_node) = vec![0];
-                return;
-            }
+        let mut node_stack = VecDeque::new();
+
+        *costs_to_end.get_mut(self.query_graph.end_node) = vec![0];
+
+        for prev_node in self.query_graph.nodes.get(self.query_graph.end_node).predecessors.iter() {
+            node_stack.push_back(prev_node);
+            enqueued.insert(prev_node);
+        }
+
+        while let Some(cur_node) = node_stack.pop_front() {
             let mut self_costs = Vec::<u64>::new();
 
             let cur_node_edges = &self.edges_of_node.get(cur_node);
@@ -226,7 +232,13 @@ impl<G: RankingRuleGraphTrait> RankingRuleGraph<G> {
             self_costs.dedup();
 
             *costs_to_end.get_mut(cur_node) = self_costs;
-        });
+            for prev_node in self.query_graph.nodes.get(cur_node).predecessors.iter() {
+                if !enqueued.contains(prev_node) {
+                    node_stack.push_back(prev_node);
+                    enqueued.insert(prev_node);
+                }
+            }
+        }
         costs_to_end
     }
 
@@ -235,12 +247,17 @@ impl<G: RankingRuleGraphTrait> RankingRuleGraph<G> {
         node_with_removed_outgoing_conditions: Interned<QueryNode>,
         costs: &mut MappedInterner<QueryNode, Vec<u64>>,
     ) {
-        // Traverse the graph backward from the target node, recomputing the cost for each of its predecessors.
-        // We first check that no other node is contributing the same total cost to a predecessor before removing
-        // the cost from the predecessor.
-        self.traverse_breadth_first_backward(node_with_removed_outgoing_conditions, |cur_node| {
+        let mut enqueued = SmallBitmap::new(self.query_graph.nodes.len());
+        let mut node_stack = VecDeque::new();
+
+        enqueued.insert(node_with_removed_outgoing_conditions);
+        node_stack.push_back(node_with_removed_outgoing_conditions);
+
+        'main_loop: while let Some(cur_node) = node_stack.pop_front() {
             let mut costs_to_remove = FxHashSet::default();
-            costs_to_remove.extend(costs.get(cur_node).iter().copied());
+            for c in costs.get(cur_node) {
+                costs_to_remove.insert(*c);
+            }
 
             let cur_node_edges = &self.edges_of_node.get(cur_node);
             for edge_idx in cur_node_edges.iter() {
@@ -248,75 +265,22 @@ impl<G: RankingRuleGraphTrait> RankingRuleGraph<G> {
                 for cost in costs.get(edge.dest_node).iter() {
                     costs_to_remove.remove(&(*cost + edge.cost as u64));
                     if costs_to_remove.is_empty() {
-                        return;
+                        continue 'main_loop;
                     }
                 }
             }
             if costs_to_remove.is_empty() {
-                return;
+                continue 'main_loop;
             }
             let mut new_costs = BTreeSet::from_iter(costs.get(cur_node).iter().copied());
             for c in costs_to_remove {
                 new_costs.remove(&c);
             }
             *costs.get_mut(cur_node) = new_costs.into_iter().collect();
-        });
-    }
 
-    /// Traverse the graph backwards from the given node such that every time
-    /// a node is visited, we are guaranteed that all its successors either:
-    /// 1. have already been visited; OR
-    /// 2. were not reachable from the given node
-    pub fn traverse_breadth_first_backward(
-        &self,
-        from: Interned<QueryNode>,
-        mut visit: impl FnMut(Interned<QueryNode>),
-    ) {
-        let mut reachable = SmallBitmap::for_interned_values_in(&self.query_graph.nodes);
-        {
-            // go backward to get the set of all reachable nodes from the given node
-            // the nodes that are not reachable will be set as `visited`
-            let mut stack = VecDeque::new();
-            let mut enqueued = SmallBitmap::for_interned_values_in(&self.query_graph.nodes);
-            enqueued.insert(from);
-            stack.push_back(from);
-            while let Some(n) = stack.pop_front() {
-                if reachable.contains(n) {
-                    continue;
-                }
-                reachable.insert(n);
-                for prev_node in self.query_graph.nodes.get(n).predecessors.iter() {
-                    if !enqueued.contains(prev_node) && !reachable.contains(prev_node) {
-                        stack.push_back(prev_node);
-                        enqueued.insert(prev_node);
-                    }
-                }
-            }
-        };
-        let mut unreachable_or_visited =
-            SmallBitmap::for_interned_values_in(&self.query_graph.nodes);
-        for (n, _) in self.query_graph.nodes.iter() {
-            if !reachable.contains(n) {
-                unreachable_or_visited.insert(n);
-            }
-        }
-
-        let mut enqueued = SmallBitmap::for_interned_values_in(&self.query_graph.nodes);
-        let mut stack = VecDeque::new();
-
-        enqueued.insert(from);
-        stack.push_back(from);
-
-        while let Some(cur_node) = stack.pop_front() {
-            if !self.query_graph.nodes.get(cur_node).successors.is_subset(&unreachable_or_visited) {
-                stack.push_back(cur_node);
-                continue;
-            }
-            unreachable_or_visited.insert(cur_node);
-            visit(cur_node);
             for prev_node in self.query_graph.nodes.get(cur_node).predecessors.iter() {
-                if !enqueued.contains(prev_node) && !unreachable_or_visited.contains(prev_node) {
-                    stack.push_back(prev_node);
+                if !enqueued.contains(prev_node) {
+                    node_stack.push_back(prev_node);
                     enqueued.insert(prev_node);
                 }
             }

milli/src/search/new/ranking_rule_graph/mod.rs

@@ -20,8 +20,6 @@ mod position;
 mod proximity;
 /// Implementation of the `typo` ranking rule
 mod typo;
-/// Implementation of the `words` ranking rule
-mod words;
 
 use std::collections::BTreeSet;
 use std::hash::Hash;
@@ -35,7 +33,6 @@ pub use position::{PositionCondition, PositionGraph};
 pub use proximity::{ProximityCondition, ProximityGraph};
 use roaring::RoaringBitmap;
 pub use typo::{TypoCondition, TypoGraph};
-pub use words::{WordsCondition, WordsGraph};
 
 use super::interner::{DedupInterner, FixedSizeInterner, Interned, MappedInterner};
 use super::query_term::LocatedQueryTermSubset;

milli/src/search/new/ranking_rule_graph/position/mod.rs

@@ -111,16 +111,23 @@ impl RankingRuleGraphTrait for PositionGraph {
 
 fn cost_from_position(sum_positions: u32) -> u32 {
     match sum_positions {
-        0 => 0,
-        1 => 1,
-        2..=4 => 2,
-        5..=7 => 3,
-        8..=11 => 4,
-        12..=16 => 5,
-        17..=24 => 6,
-        25..=64 => 7,
-        65..=256 => 8,
-        257..=1024 => 9,
-        _ => 10,
+        0 | 1 | 2 | 3 => sum_positions,
+        4 | 5 => 4,
+        6 | 7 => 5,
+        8 | 9 => 6,
+        10 | 11 => 7,
+        12 | 13 => 8,
+        14 | 15 => 9,
+        16 | 17..=24 => 10,
+        25..=32 => 11,
+        33..=64 => 12,
+        65..=128 => 13,
+        129..=256 => 14,
+        257..=512 => 15,
+        513..=1024 => 16,
+        1025..=2048 => 17,
+        2049..=4096 => 18,
+        4097..=8192 => 19,
+        _ => 20,
     }
 }

milli/src/search/new/ranking_rule_graph/typo/mod.rs

@@ -50,7 +50,7 @@ impl RankingRuleGraphTrait for TypoGraph {
         // 3-gram -> equivalent to 2 typos
         let base_cost = if term.term_ids.len() == 1 { 0 } else { term.term_ids.len() as u32 };
 
-        for nbr_typos in 0..=term.term_subset.max_typo_cost(ctx) {
+        for nbr_typos in 0..=term.term_subset.max_nbr_typos(ctx) {
             let mut term = term.clone();
             match nbr_typos {
                 0 => {

milli/src/search/new/ranking_rule_graph/words/mod.rs

@@ -1,49 +0,0 @@
-use roaring::RoaringBitmap;
-
-use super::{ComputedCondition, RankingRuleGraphTrait};
-use crate::search::new::interner::{DedupInterner, Interned};
-use crate::search::new::query_term::LocatedQueryTermSubset;
-use crate::search::new::resolve_query_graph::compute_query_term_subset_docids;
-use crate::search::new::SearchContext;
-use crate::Result;
-
-#[derive(Clone, PartialEq, Eq, Hash)]
-pub struct WordsCondition {
-    term: LocatedQueryTermSubset,
-}
-
-pub enum WordsGraph {}
-
-impl RankingRuleGraphTrait for WordsGraph {
-    type Condition = WordsCondition;
-
-    fn resolve_condition(
-        ctx: &mut SearchContext,
-        condition: &Self::Condition,
-        universe: &RoaringBitmap,
-    ) -> Result<ComputedCondition> {
-        let WordsCondition { term, .. } = condition;
-        // maybe compute_query_term_subset_docids should accept a universe as argument
-        let mut docids = compute_query_term_subset_docids(ctx, &term.term_subset)?;
-        docids &= universe;
-
-        Ok(ComputedCondition {
-            docids,
-            universe_len: universe.len(),
-            start_term_subset: None,
-            end_term_subset: term.clone(),
-        })
-    }
-
-    fn build_edges(
-        _ctx: &mut SearchContext,
-        conditions_interner: &mut DedupInterner<Self::Condition>,
-        _from: Option<&LocatedQueryTermSubset>,
-        to_term: &LocatedQueryTermSubset,
-    ) -> Result<Vec<(u32, Interned<Self::Condition>)>> {
-        Ok(vec![(
-            to_term.term_ids.len() as u32,
-            conditions_interner.insert(WordsCondition { term: to_term.clone() }),
-        )])
-    }
-}

milli/src/search/new/tests/attribute_position.rs

@@ -138,7 +138,7 @@ fn test_attribute_position_simple() {
     s.terms_matching_strategy(TermsMatchingStrategy::All);
     s.query("quick brown");
     let SearchResult { documents_ids, .. } = s.execute().unwrap();
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 11, 12, 13, 2, 3, 4, 1, 0, 6, 8, 7, 9, 5]");
+    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 11, 12, 13, 3, 4, 2, 1, 0, 6, 8, 7, 9, 5]");
 }
 #[test]
 fn test_attribute_position_repeated() {
@@ -163,7 +163,7 @@ fn test_attribute_position_different_fields() {
     s.terms_matching_strategy(TermsMatchingStrategy::All);
     s.query("quick brown");
     let SearchResult { documents_ids, .. } = s.execute().unwrap();
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 11, 12, 13, 2, 3, 4, 1, 0, 6, 8, 7, 9, 5]");
+    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 11, 12, 13, 3, 4, 2, 1, 0, 6, 8, 7, 9, 5]");
 }
 
 #[test]
@@ -176,5 +176,5 @@ fn test_attribute_position_ngrams() {
     s.terms_matching_strategy(TermsMatchingStrategy::All);
     s.query("quick brown");
     let SearchResult { documents_ids, .. } = s.execute().unwrap();
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 11, 12, 13, 2, 3, 4, 1, 0, 6, 8, 7, 9, 5]");
+    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 11, 12, 13, 3, 4, 2, 1, 0, 6, 8, 7, 9, 5]");
 }

milli/src/search/new/tests/mod.rs

@@ -4,7 +4,7 @@ pub mod distinct;
 pub mod exactness;
 pub mod geo_sort;
 pub mod integration;
-#[cfg(feature = "all-tokenizations")]
+#[cfg(feature = "default")]
 pub mod language;
 pub mod ngram_split_words;
 pub mod proximity;

milli/src/search/new/tests/ngram_split_words.rs

@@ -3,9 +3,9 @@ This module tests the following properties:
 
 1. Two consecutive words from a query can be combined into a "2gram"
 2. Three consecutive words from a query can be combined into a "3gram"
-3. A word from the query can be split into two consecutive words (split words), no matter how short it is
+3. A word from the query can be split into two consecutive words (split words)
 4. A 2gram can be split into two words
-5. A 3gram can be split into two words
+5. A 3gram cannot be split into two words
 6. 2grams can contain up to 1 typo
 7. 3grams cannot have typos
 8. 2grams and 3grams can be prefix tolerant
@@ -14,7 +14,6 @@ This module tests the following properties:
 11. Disabling typo tolerance does not disable ngram tolerance
 12. Prefix tolerance is disabled for the last word if a space follows it
 13. Ngrams cannot be formed by combining a phrase and a word or two phrases
-14. Split words are not disabled by the `disableOnAttribute` or `disableOnWords` typo settings
 */
 
 use crate::index::tests::TempIndex;
@@ -57,10 +56,6 @@ fn create_index() -> TempIndex {
             {
                 "id": 5,
                 "text": "sunflowering is not a verb"
-            },
-            {
-                "id": 6,
-                "text": "xy z"
             }
         ]))
         .unwrap();
@@ -268,11 +263,10 @@ fn test_disable_split_words() {
     s.query("sunflower ");
     let SearchResult { documents_ids, .. } = s.execute().unwrap();
     // no document containing `sun flower`
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 3]");
+    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3]");
     let texts = collect_field_values(&index, &txn, "text", &documents_ids);
     insta::assert_debug_snapshot!(texts, @r###"
     [
-        "\"the sun flower is tall\"",
         "\"the sunflower is tall\"",
     ]
     "###);
@@ -313,11 +307,10 @@ fn test_3gram_no_split_words() {
     let SearchResult { documents_ids, .. } = s.execute().unwrap();
 
     // no document with `sun flower`
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 2, 3, 5]");
+    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 3, 5]");
     let texts = collect_field_values(&index, &txn, "text", &documents_ids);
     insta::assert_debug_snapshot!(texts, @r###"
     [
-        "\"the sun flower is tall\"",
         "\"the sunflowers are pretty\"",
         "\"the sunflower is tall\"",
         "\"sunflowering is not a verb\"",
@@ -376,50 +369,3 @@ fn test_no_ngram_phrases() {
     ]
     "###);
 }
-
-#[test]
-fn test_short_split_words() {
-    let index = create_index();
-    let txn = index.read_txn().unwrap();
-
-    let mut s = Search::new(&txn, &index);
-    s.terms_matching_strategy(TermsMatchingStrategy::All);
-    s.query("xyz");
-    let SearchResult { documents_ids, .. } = s.execute().unwrap();
-
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
-    let texts = collect_field_values(&index, &txn, "text", &documents_ids);
-    insta::assert_debug_snapshot!(texts, @r###"
-    [
-        "\"xy z\"",
-    ]
-    "###);
-}
-
-#[test]
-fn test_split_words_never_disabled() {
-    let index = create_index();
-
-    index
-        .update_settings(|s| {
-            s.set_exact_words(["sunflower"].iter().map(ToString::to_string).collect());
-            s.set_exact_attributes(["text"].iter().map(ToString::to_string).collect());
-        })
-        .unwrap();
-
-    let txn = index.read_txn().unwrap();
-
-    let mut s = Search::new(&txn, &index);
-    s.terms_matching_strategy(TermsMatchingStrategy::All);
-    s.query("the sunflower is tall");
-    let SearchResult { documents_ids, .. } = s.execute().unwrap();
-
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 3]");
-    let texts = collect_field_values(&index, &txn, "text", &documents_ids);
-    insta::assert_debug_snapshot!(texts, @r###"
-    [
-        "\"the sun flower is tall\"",
-        "\"the sunflower is tall\"",
-    ]
-    "###);
-}

milli/src/search/new/tests/typo.rs

@@ -9,7 +9,7 @@ This module tests the following properties:
 6. A typo on the first letter of a word counts as two typos
 7. Phrases are not typo tolerant
 8. 2grams can have 1 typo if they are larger than `min_word_len_two_typos`
-9. 3grams are not typo tolerant (but they can be split into two words)
+9. 3grams are not typo tolerant
 10. The `typo` ranking rule assumes the role of the `words` ranking rule implicitly
 if `words` doesn't exist before it.
 11. The `typo` ranking rule places documents with the same number of typos in the same bucket
@@ -287,17 +287,16 @@ fn test_typo_exact_word() {
     ]
     "###);
 
-    // exact words do not disable prefix (sunflowering OK, but no sunflowar)
+    // exact words do not disable prefix (sunflowering OK, but no sunflowar or sun flower)
     let mut s = Search::new(&txn, &index);
     s.terms_matching_strategy(TermsMatchingStrategy::All);
     s.query("network interconnection sunflower");
     let SearchResult { documents_ids, .. } = s.execute().unwrap();
-    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[16, 17, 18]");
+    insta::assert_snapshot!(format!("{documents_ids:?}"), @"[16, 18]");
     let texts = collect_field_values(&index, &txn, "text", &documents_ids);
     insta::assert_debug_snapshot!(texts, @r###"
     [
         "\"network interconnection sunflower\"",
-        "\"network interconnection sun flower\"",
         "\"network interconnection sunflowering\"",
     ]
     "###);

milli/src/search/new/words.rs

@@ -0,0 +1,87 @@
+use roaring::RoaringBitmap;
+
+use super::logger::SearchLogger;
+use super::query_graph::QueryNode;
+use super::resolve_query_graph::compute_query_graph_docids;
+use super::small_bitmap::SmallBitmap;
+use super::{QueryGraph, RankingRule, RankingRuleOutput, SearchContext};
+use crate::{Result, TermsMatchingStrategy};
+
+pub struct Words {
+    exhausted: bool, // TODO: remove
+    query_graph: Option<QueryGraph>,
+    nodes_to_remove: Vec<SmallBitmap<QueryNode>>,
+    terms_matching_strategy: TermsMatchingStrategy,
+}
+impl Words {
+    pub fn new(terms_matching_strategy: TermsMatchingStrategy) -> Self {
+        Self {
+            exhausted: true,
+            query_graph: None,
+            nodes_to_remove: vec![],
+            terms_matching_strategy,
+        }
+    }
+}
+
+impl<'ctx> RankingRule<'ctx, QueryGraph> for Words {
+    fn id(&self) -> String {
+        "words".to_owned()
+    }
+    fn start_iteration(
+        &mut self,
+        ctx: &mut SearchContext<'ctx>,
+        _logger: &mut dyn SearchLogger<QueryGraph>,
+        _universe: &RoaringBitmap,
+        parent_query_graph: &QueryGraph,
+    ) -> Result<()> {
+        self.exhausted = false;
+        self.query_graph = Some(parent_query_graph.clone());
+        self.nodes_to_remove = match self.terms_matching_strategy {
+            TermsMatchingStrategy::Last => {
+                let mut ns = parent_query_graph.removal_order_for_terms_matching_strategy_last(ctx);
+                ns.reverse();
+                ns
+            }
+            TermsMatchingStrategy::All => {
+                vec![]
+            }
+        };
+        Ok(())
+    }
+
+    fn next_bucket(
+        &mut self,
+        ctx: &mut SearchContext<'ctx>,
+        logger: &mut dyn SearchLogger<QueryGraph>,
+        universe: &RoaringBitmap,
+    ) -> Result<Option<RankingRuleOutput<QueryGraph>>> {
+        if self.exhausted {
+            return Ok(None);
+        }
+        let Some(query_graph) = &mut self.query_graph else { panic!() };
+        logger.log_internal_state(query_graph);
+
+        let this_bucket = compute_query_graph_docids(ctx, query_graph, universe)?;
+
+        let child_query_graph = query_graph.clone();
+
+        if self.nodes_to_remove.is_empty() {
+            self.exhausted = true;
+        } else {
+            let nodes_to_remove = self.nodes_to_remove.pop().unwrap();
+            query_graph.remove_nodes_keep_edges(&nodes_to_remove.iter().collect::<Vec<_>>());
+        }
+        Ok(Some(RankingRuleOutput { query: child_query_graph, candidates: this_bucket }))
+    }
+
+    fn end_iteration(
+        &mut self,
+        _ctx: &mut SearchContext<'ctx>,
+        _logger: &mut dyn SearchLogger<QueryGraph>,
+    ) {
+        self.exhausted = true;
+        self.nodes_to_remove = vec![];
+        self.query_graph = None;
+    }
+}

milli/src/update/facet/mod.rs

@@ -261,9 +261,7 @@ pub(crate) mod test_helpers {
             let options = options.map_size(4096 * 4 * 1000 * 100);
             let tempdir = tempfile::TempDir::new().unwrap();
             let env = options.open(tempdir.path()).unwrap();
-            let mut wtxn = env.write_txn().unwrap();
-            let content = env.create_database(&mut wtxn, None).unwrap();
-            wtxn.commit().unwrap();
+            let content = env.create_database(None).unwrap();
 
             FacetIndex {
                 content,

milli/src/update/index_documents/mod.rs

@@ -1581,7 +1581,7 @@ mod tests {
         assert_eq!(count, 4);
     }
 
-    #[cfg(feature = "chinese")]
+    #[cfg(feature = "default")]
     #[test]
     fn test_meilisearch_1714() {
         let index = TempIndex::new();