increase rust version from 1.85 to 1.89

Dockerfile

@@ -1,5 +1,5 @@
 # Compile
-FROM    rust:1.85-alpine3.20 AS compiler
+FROM    rust:1.89-alpine3.20 AS compiler
 
 RUN     apk add -q --no-cache build-base openssl-dev
 

crates/dump/src/reader/compat/v2_to_v3.rs

@@ -97,6 +97,7 @@ impl CompatV2ToV3 {
     }
 }
 
+#[allow(clippy::large_enum_variant)]
 pub enum CompatIndexV2ToV3 {
     V2(v2::V2IndexReader),
     Compat(Box<CompatIndexV1ToV2>),

crates/filter-parser/src/condition.rs

@@ -124,7 +124,7 @@ pub fn parse_not_exists(input: Span) -> IResult<FilterCondition> {
     Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Exists }))))
 }
 
-fn parse_vectors(input: Span) -> IResult<(Token, Option<Token>, VectorFilter<'_>)> {
+fn parse_vectors(input: Span) -> IResult<(Token, Option<Token>, VectorFilter)> {
     let (input, _) = multispace0(input)?;
     let (input, fid) = tag("_vectors")(input)?;
 

crates/filter-parser/src/lib.rs

@@ -116,7 +116,7 @@ impl<'a> Token<'a> {
         self.span
     }
 
-    pub fn parse_finite_float(&self) -> Result<f64, Error> {
+    pub fn parse_finite_float(&self) -> Result<f64, Error<'a>> {
         let value: f64 = self.value().parse().map_err(|e| self.as_external_error(e))?;
         if value.is_finite() {
             Ok(value)
@@ -166,7 +166,7 @@ pub enum TraversedElement<'a> {
 }
 
 impl<'a> FilterCondition<'a> {
-    pub fn use_contains_operator(&self) -> Option<&Token> {
+    pub fn use_contains_operator(&self) -> Option<&Token<'a>> {
         match self {
             FilterCondition::Condition { fid: _, op } => match op {
                 Condition::GreaterThan(_)
@@ -193,7 +193,7 @@ impl<'a> FilterCondition<'a> {
         }
     }
 
-    pub fn use_vector_filter(&self) -> Option<&Token> {
+    pub fn use_vector_filter(&self) -> Option<&Token<'a>> {
         match self {
             FilterCondition::Condition { .. } => None,
             FilterCondition::Not(this) => this.use_vector_filter(),
@@ -207,7 +207,7 @@ impl<'a> FilterCondition<'a> {
         }
     }
 
-    pub fn fids(&self, depth: usize) -> Box<dyn Iterator<Item = &Token> + '_> {
+    pub fn fids(&self, depth: usize) -> Box<dyn Iterator<Item = &Token<'a>> + '_> {
         if depth == 0 {
             return Box::new(std::iter::empty());
         }
@@ -228,7 +228,7 @@ impl<'a> FilterCondition<'a> {
     }
 
     /// Returns the first token found at the specified depth, `None` if no token at this depth.
-    pub fn token_at_depth(&self, depth: usize) -> Option<&Token> {
+    pub fn token_at_depth(&self, depth: usize) -> Option<&Token<'a>> {
         match self {
             FilterCondition::Condition { fid, .. } if depth == 0 => Some(fid),
             FilterCondition::Or(subfilters) => {
@@ -651,7 +651,7 @@ pub mod tests {
     /// Create a raw [Token]. You must specify the string that appear BEFORE your element followed by your element
     pub fn rtok<'a>(before: &'a str, value: &'a str) -> Token<'a> {
         // if the string is empty we still need to return 1 for the line number
-        let lines = before.is_empty().then_some(1).unwrap_or_else(|| before.lines().count());
+        let lines = if before.is_empty() { 1 } else { before.lines().count() };
         let offset = before.chars().count();
         // the extra field is not checked in the tests so we can set it to nothing
         unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into()

crates/index-scheduler/src/dump.rs

@@ -1,3 +1,5 @@
+#![allow(clippy::result_large_err)]
+
 use std::collections::HashMap;
 use std::io;
 

crates/index-scheduler/src/error.rs

@@ -45,7 +45,6 @@ impl From<DateField> for Code {
     }
 }
 
-#[allow(clippy::large_enum_variant)]
 #[derive(Error, Debug)]
 pub enum Error {
     #[error("{1}")]

crates/index-scheduler/src/lib.rs

@@ -1,3 +1,6 @@
+// The main Error type is large and boxing the large variant make the pattern matching fails
+#![allow(clippy::result_large_err)]
+
 /*!
 This crate defines the index scheduler, which is responsible for:
 1. Keeping references to meilisearch's indexes and mapping them to their
@@ -344,7 +347,7 @@ impl IndexScheduler {
         Ok(this)
     }
 
-    fn read_txn(&self) -> Result<RoTxn<WithoutTls>> {
+    fn read_txn(&self) -> Result<RoTxn<'_, WithoutTls>> {
         self.env.read_txn().map_err(|e| e.into())
     }
 
@@ -757,7 +760,7 @@ impl IndexScheduler {
 
     /// Register a new task coming from a dump in the scheduler.
     /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
-    pub fn register_dumped_task(&mut self) -> Result<Dump> {
+    pub fn register_dumped_task(&mut self) -> Result<Dump<'_>> {
         Dump::new(self)
     }
 
@@ -806,10 +809,8 @@ impl IndexScheduler {
                                 .queue
                                 .tasks
                                 .get_task(self.rtxn, task_id)
-                                .map_err(|err| io::Error::new(io::ErrorKind::Other, err))?
-                                .ok_or_else(|| {
-                                    io::Error::new(io::ErrorKind::Other, Error::CorruptedTaskQueue)
-                                })?;
+                                .map_err(io::Error::other)?
+                                .ok_or_else(|| io::Error::other(Error::CorruptedTaskQueue))?;
 
                             serde_json::to_writer(&mut self.buffer, &TaskView::from_task(&task))?;
                             self.buffer.push(b'\n');

crates/index-scheduler/src/queue/mod.rs

@@ -326,7 +326,7 @@ impl Queue {
         );
 
         // it's safe to unwrap here because we checked the len above
-        let newest_task_id = to_delete.iter().last().unwrap();
+        let newest_task_id = to_delete.iter().next_back().unwrap();
         let last_task_to_delete =
             self.tasks.get_task(wtxn, newest_task_id)?.ok_or(Error::CorruptedTaskQueue)?;
 

crates/index-scheduler/src/scheduler/create_batch.rs

@@ -66,6 +66,7 @@ pub(crate) enum DocumentOperation {
 
 /// A [batch](Batch) that combines multiple tasks operating on an index.
 #[derive(Debug)]
+#[allow(clippy::large_enum_variant)]
 pub(crate) enum IndexOperation {
     DocumentOperation {
         index_uid: String,

crates/index-scheduler/src/scheduler/process_export.rs

@@ -370,7 +370,7 @@ fn ureq_error_into_error(error: ureq::Error) -> Error {
             }
             Err(e) => e.into(),
         },
-        ureq::Error::Transport(transport) => io::Error::new(io::ErrorKind::Other, transport).into(),
+        ureq::Error::Transport(transport) => io::Error::other(transport).into(),
     }
 }
 

crates/index-scheduler/src/uuid_codec.rs

@@ -17,7 +17,7 @@ impl<'a> BytesDecode<'a> for UuidCodec {
 impl BytesEncode<'_> for UuidCodec {
     type EItem = Uuid;
 
-    fn bytes_encode(item: &Self::EItem) -> Result<Cow<[u8]>, BoxedError> {
+    fn bytes_encode(item: &Self::EItem) -> Result<Cow<'_, [u8]>, BoxedError> {
         Ok(Cow::Borrowed(item.as_bytes()))
     }
 }

crates/meilisearch-auth/src/store.rs

@@ -315,7 +315,9 @@ impl<'a> heed::BytesDecode<'a> for KeyIdActionCodec {
 impl<'a> heed::BytesEncode<'a> for KeyIdActionCodec {
     type EItem = (&'a KeyId, &'a Action, Option<&'a [u8]>);
 
-    fn bytes_encode((key_id, action, index): &Self::EItem) -> StdResult<Cow<[u8]>, BoxedError> {
+    fn bytes_encode(
+        (key_id, action, index): &'_ Self::EItem,
+    ) -> StdResult<Cow<'_, [u8]>, BoxedError> {
         let mut bytes = Vec::new();
 
         bytes.extend_from_slice(key_id.as_bytes());

crates/meilisearch/src/error.rs

@@ -12,6 +12,7 @@ use tokio::task::JoinError;
 use crate::routes::indexes::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
 
 #[derive(Debug, thiserror::Error)]
+#[allow(clippy::large_enum_variant)]
 pub enum MeilisearchHttpError {
     #[error("A Content-Type header is missing. Accepted values for the Content-Type header are: {}",
             .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", "))]

crates/meilisearch/src/lib.rs

@@ -1,4 +1,6 @@
+#![allow(clippy::result_large_err)]
 #![allow(rustdoc::private_intra_doc_links)]
+
 #[macro_use]
 pub mod error;
 pub mod analytics;

crates/meilisearch/src/search/federated/perform.rs

@@ -219,7 +219,7 @@ struct SearchResultByQueryIterItem<'a> {
 
 fn merge_index_local_results(
     results_by_query: Vec<SearchResultByQuery<'_>>,
-) -> impl Iterator<Item = SearchResultByQueryIterItem> + '_ {
+) -> impl Iterator<Item = SearchResultByQueryIterItem<'_>> + '_ {
     itertools::kmerge_by(
         results_by_query.into_iter().map(SearchResultByQueryIter::new),
         |left: &SearchResultByQueryIterItem, right: &SearchResultByQueryIterItem| {

crates/meilisearch/src/search/mod.rs

@@ -2080,7 +2080,7 @@ pub(crate) fn parse_filter(
     facets: &Value,
     filter_parsing_error_code: Code,
     features: RoFeatures,
-) -> Result<Option<Filter>, ResponseError> {
+) -> Result<Option<Filter<'_>>, ResponseError> {
     let filter = match facets {
         Value::String(expr) => Filter::from_str(expr).map_err(|e| e.into()),
         Value::Array(arr) => parse_filter_array(arr).map_err(|e| e.into()),
@@ -2117,7 +2117,7 @@ pub(crate) fn parse_filter(
     Ok(filter)
 }
 
-fn parse_filter_array(arr: &[Value]) -> Result<Option<Filter>, MeilisearchHttpError> {
+fn parse_filter_array(arr: &'_ [Value]) -> Result<Option<Filter<'_>>, MeilisearchHttpError> {
     let mut ands = Vec::new();
     for value in arr {
         match value {

crates/meilisearch/src/search_queue.rs

@@ -13,9 +13,9 @@
 //! What is going to happen at this point is that you're going to send a oneshot::Sender over an async mpsc channel.
 //! Then, the queue/scheduler is going to either:
 //! - Drop your oneshot channel => that means there are too many searches going on, and yours won't be executed.
-//!                                You should exit and free all the RAM you use ASAP.
+//!   You should exit and free all the RAM you use ASAP.
 //! - Sends you a Permit => that will unlock the method, and you will be able to process your search.
-//!                         And should drop the Permit only once you have freed all the RAM consumed by the method.
+//!   And should drop the Permit only once you have freed all the RAM consumed by the method.
 
 use std::num::NonZeroUsize;
 use std::sync::atomic::{AtomicUsize, Ordering};

crates/meilisearch/tests/auth/tenant_token_multi_search.rs

@@ -1040,7 +1040,7 @@ async fn error_single_search_forbidden_token() {
     ];
 
     let failed_query_indexes: Vec<_> =
-        std::iter::repeat(Some(0)).take(5).chain(std::iter::repeat(None).take(6)).collect();
+        std::iter::repeat_n(Some(0), 5).chain(std::iter::repeat_n(None, 6)).collect();
 
     let failed_query_indexes = vec![failed_query_indexes; ACCEPTED_KEYS_SINGLE.len()];
 
@@ -1118,10 +1118,9 @@ async fn error_multi_search_forbidden_token() {
         },
     ];
 
-    let failed_query_indexes: Vec<_> = std::iter::repeat(Some(0))
-        .take(5)
-        .chain(std::iter::repeat(Some(1)).take(5))
-        .chain(std::iter::repeat(None).take(6))
+    let failed_query_indexes: Vec<_> = std::iter::repeat_n(Some(0), 5)
+        .chain(std::iter::repeat_n(Some(1), 5))
+        .chain(std::iter::repeat_n(None, 6))
         .collect();
 
     let failed_query_indexes = vec![failed_query_indexes; ACCEPTED_KEYS_BOTH.len()];

crates/meilisearch/tests/vector/mod.rs

@@ -249,7 +249,7 @@ async fn user_provide_mismatched_embedding_dimension() {
     "###);
 }
 
-async fn generate_default_user_provided_documents(server: &Server) -> Index {
+async fn generate_default_user_provided_documents(server: &Server) -> Index<'_> {
     let index = server.index("doggo");
 
     let (response, code) = index

crates/meilitool/src/uuid_codec.rs

@@ -17,7 +17,7 @@ impl<'a> BytesDecode<'a> for UuidCodec {
 impl BytesEncode<'_> for UuidCodec {
     type EItem = Uuid;
 
-    fn bytes_encode(item: &Self::EItem) -> Result<Cow<[u8]>, BoxedError> {
+    fn bytes_encode(item: &'_ Self::EItem) -> Result<Cow<'_, [u8]>, BoxedError> {
         Ok(Cow::Borrowed(item.as_bytes()))
     }
 }

crates/milli/src/error.rs

@@ -621,7 +621,7 @@ impl From<HeedError> for Error {
             // TODO use the encoding
             HeedError::Encoding(_) => InternalError(Serialization(Encoding { db_name: None })),
             HeedError::Decoding(_) => InternalError(Serialization(Decoding { db_name: None })),
-            HeedError::EnvAlreadyOpened { .. } => UserError(EnvAlreadyOpened),
+            HeedError::EnvAlreadyOpened => UserError(EnvAlreadyOpened),
         }
     }
 }

crates/milli/src/heed_codec/roaring_bitmap_length/roaring_bitmap_len_codec.rs

@@ -19,14 +19,14 @@ impl RoaringBitmapLenCodec {
             if cookie == SERIAL_COOKIE_NO_RUNCONTAINER {
                 (bytes.read_u32::<LittleEndian>()? as usize, true)
             } else if (cookie as u16) == SERIAL_COOKIE {
-                return Err(io::Error::new(io::ErrorKind::Other, "run containers are unsupported"));
+                return Err(io::Error::other("run containers are unsupported"));
             } else {
-                return Err(io::Error::new(io::ErrorKind::Other, "unknown cookie value"));
+                return Err(io::Error::other("unknown cookie value"));
             }
         };
 
         if size > u16::MAX as usize + 1 {
-            return Err(io::Error::new(io::ErrorKind::Other, "size is greater than supported"));
+            return Err(io::Error::other("size is greater than supported"));
         }
 
         let mut description_bytes = vec![0u8; size * 4];

crates/milli/src/lib.rs

@@ -1,4 +1,5 @@
 #![allow(clippy::type_complexity)]
+#![allow(clippy::result_large_err)]
 
 #[cfg(not(windows))]
 #[cfg(test)]

crates/milli/src/search/facet/facet_distribution_iter.rs

@@ -38,7 +38,7 @@ where
     let highest_level = get_highest_level(rtxn, db, field_id)?;
 
     if let Some(first_bound) = get_first_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)? {
-        fd.iterate(candidates, highest_level, first_bound, usize::MAX)?;
+        let _ = fd.iterate(candidates, highest_level, first_bound, usize::MAX)?;
         Ok(())
     } else {
         Ok(())

crates/milli/src/search/facet/filter.rs

@@ -225,11 +225,11 @@ impl<'a> Filter<'a> {
         Ok(Some(Self { condition }))
     }
 
-    pub fn use_contains_operator(&self) -> Option<&Token> {
+    pub fn use_contains_operator(&self) -> Option<&Token<'_>> {
         self.condition.use_contains_operator()
     }
 
-    pub fn use_vector_filter(&self) -> Option<&Token> {
+    pub fn use_vector_filter(&self) -> Option<&Token<'_>> {
         self.condition.use_vector_filter()
     }
 }

crates/milli/src/search/facet/search.rs

@@ -137,7 +137,7 @@ impl<'a> SearchForFacetValues<'a> {
                     let exact_words_fst = self.search_query.index.exact_words(rtxn)?;
                     if exact_words_fst.is_some_and(|fst| fst.contains(query)) {
                         if fst.contains(query) {
-                            self.fetch_original_facets_using_normalized(
+                            let _ = self.fetch_original_facets_using_normalized(
                                 fid,
                                 query,
                                 query,

crates/milli/src/search/new/bucket_sort.rs

@@ -354,15 +354,14 @@ fn maybe_add_to_results<'ctx, Q: RankingRuleQueryTrait>(
             logger.add_to_results(&candidates);
             valid_docids.extend_from_slice(&candidates);
             valid_scores
-                .extend(std::iter::repeat(ranking_rule_scores.to_owned()).take(candidates.len()));
+                .extend(std::iter::repeat_n(ranking_rule_scores.to_owned(), candidates.len()));
         }
     } else {
         // if we have passed the offset already, add some of the documents (up to the limit)
         let candidates = candidates.iter().take(length - valid_docids.len()).collect::<Vec<u32>>();
         logger.add_to_results(&candidates);
         valid_docids.extend_from_slice(&candidates);
-        valid_scores
-            .extend(std::iter::repeat(ranking_rule_scores.to_owned()).take(candidates.len()));
+        valid_scores.extend(std::iter::repeat_n(ranking_rule_scores.to_owned(), candidates.len()));
     }
 
     *cur_offset += candidates.len() as usize;

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

@@ -193,6 +193,7 @@ impl<G: RankingRuleGraphTrait> VisitorState<G> {
         visit: VisitFn<'_, G>,
         ctx: &mut VisitorContext<'_, G>,
     ) -> Result<ControlFlow<(), bool>> {
+        #[allow(clippy::manual_contains)] // there is no method contains on mapped interner
         if !ctx
             .all_costs_from_node
             .get(dest_node)
@@ -243,6 +244,8 @@ impl<G: RankingRuleGraphTrait> VisitorState<G> {
 
         // Checking that from the destination node, there is at least
         // one cost that we can visit that corresponds to our remaining budget.
+
+        #[allow(clippy::manual_contains)] // there is no contains on MappedInterner
         if !ctx
             .all_costs_from_node
             .get(dest_node)

crates/milli/src/search/new/small_bitmap.rs

@@ -401,7 +401,7 @@ impl Iterator for SmallBitmapInternalIter<'_> {
                     *cur &= *cur - 1;
                     Some(idx + *base)
                 } else if next.is_empty() {
-                    return None;
+                    None
                 } else {
                     *base += 64;
                     *cur = next[0];

crates/milli/src/search/new/sort.rs

@@ -79,7 +79,7 @@ impl<'ctx, Query> Sort<'ctx, Query> {
             return Ok(false);
         };
 
-        Ok(!displayed_fields.iter().any(|&field| field == field_name))
+        Ok(!displayed_fields.contains(&field_name))
     }
 }
 

crates/milli/src/update/new/channel.rs

@@ -52,10 +52,10 @@ const MAX_FRAME_HEADER_SIZE: usize = 9;
 /// a message in this queue only if it is empty to avoid filling
 /// the channel *and* the BBQueue.
 pub fn extractor_writer_bbqueue(
-    bbbuffers: &mut Vec<BBBuffer>,
+    bbbuffers: &'_ mut Vec<BBBuffer>,
     total_bbbuffer_capacity: usize,
     channel_capacity: usize,
-) -> (ExtractorBbqueueSender, WriterBbqueueReceiver) {
+) -> (ExtractorBbqueueSender<'_>, WriterBbqueueReceiver<'_>) {
     let current_num_threads = rayon::current_num_threads();
     let bbbuffer_capacity = total_bbbuffer_capacity.checked_div(current_num_threads).unwrap();
     bbbuffers.resize_with(current_num_threads, || BBBuffer::new(bbbuffer_capacity));

crates/milli/src/update/new/indexer/de.rs

@@ -6,9 +6,7 @@ use rustc_hash::FxBuildHasher;
 use serde::de::{DeserializeSeed, Deserializer as _, Visitor};
 use serde_json::value::RawValue;
 
-use crate::documents::{
-    validate_document_id_str, DocumentIdExtractionError, FieldIdMapper, PrimaryKey,
-};
+use crate::documents::{validate_document_id_str, DocumentIdExtractionError, PrimaryKey};
 use crate::fields_ids_map::MutFieldIdMapper;
 use crate::{FieldId, UserError};
 
@@ -235,28 +233,6 @@ impl<'de, 'a, Mapper: MutFieldIdMapper> Visitor<'de> for MutFieldIdMapVisitor<'a
     }
 }
 
-pub struct FieldIdMapVisitor<'a, Mapper: FieldIdMapper>(pub &'a Mapper);
-
-impl<'de, Mapper: FieldIdMapper> Visitor<'de> for FieldIdMapVisitor<'_, Mapper> {
-    type Value = Option<FieldId>;
-
-    fn expecting(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
-        write!(formatter, "expecting a string")
-    }
-    fn visit_borrowed_str<E>(self, v: &'de str) -> std::result::Result<Self::Value, E>
-    where
-        E: serde::de::Error,
-    {
-        Ok(self.0.id(v))
-    }
-
-    fn visit_str<E>(self, v: &str) -> std::result::Result<Self::Value, E>
-    where
-        E: serde::de::Error,
-    {
-        Ok(self.0.id(v))
-    }
-}
 pub struct DocumentIdVisitor<'indexer>(pub &'indexer Bump);
 
 impl<'de, 'indexer: 'de> Visitor<'de> for DocumentIdVisitor<'indexer> {

crates/milli/src/update/new/thread_local.rs

@@ -138,7 +138,7 @@ impl<T: MostlySend> ThreadLocal<T> {
         self.inner.get_or_default().as_ref()
     }
 
-    pub fn iter_mut(&mut self) -> IterMut<T> {
+    pub fn iter_mut(&mut self) -> IterMut<'_, T> {
         IterMut(self.inner.iter_mut())
     }
 }

crates/milli/src/vector/embedder/composite.rs

@@ -11,6 +11,7 @@ use crate::ThreadPoolNoAbort;
 pub(in crate::vector) const MAX_COMPOSITE_DISTANCE: f32 = 0.01;
 
 #[derive(Debug)]
+#[allow(clippy::large_enum_variant)]
 pub enum SubEmbedder {
     /// An embedder based on running local models, fetched from the Hugging Face Hub.
     HuggingFace(hf::Embedder),

crates/milli/src/vector/embedder/mod.rs

@@ -19,6 +19,7 @@ use crate::ThreadPoolNoAbort;
 
 /// An embedder can be used to transform text into embeddings.
 #[derive(Debug)]
+#[allow(clippy::large_enum_variant)]
 pub enum Embedder {
     /// An embedder based on running local models, fetched from the Hugging Face Hub.
     HuggingFace(hf::Embedder),
@@ -64,6 +65,7 @@ impl EmbeddingConfig {
 /// This type is serialized in and deserialized from the DB, any modification should either go
 /// through dumpless upgrade or be backward-compatible
 #[derive(Debug, Clone, Hash, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+#[allow(clippy::large_enum_variant)]
 pub enum EmbedderOptions {
     HuggingFace(hf::EmbedderOptions),
     OpenAi(openai::EmbedderOptions),

rust-toolchain.toml

@@ -1,3 +1,3 @@
 [toolchain]
-channel = "1.85.1"
+channel = "1.89.0"
 components = ["clippy"]