searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-03 11:57:07 +02:00
Code Issues Releases Wiki Activity

Merge branch 'main' into release-v1.14.0-tmp

Browse source
This commit is contained in:
Tamo 2025-04-14 12:35:47 +02:00 • committed by GitHub
commit b025f1bcf1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
113 changed files with 1268 additions and 852 deletions
Download patch file Download diff file Expand all files Collapse all files

9
crates/milli/src/update/facet/incremental.rs
View file

@ -101,8 +101,7 @@ impl FacetsUpdateIncremental {
let key = FacetGroupKeyCodec::<BytesRefCodec>::bytes_decode(key)
.map_err(heed::Error::Encoding)?;
if facet_level_may_be_updated
&& current_field_id.map_or(false, |fid| fid != key.field_id)
if facet_level_may_be_updated && current_field_id.is_some_and(|fid| fid != key.field_id)
{
// Only add or remove a level after making all the field modifications.
self.inner.add_or_delete_level(wtxn, current_field_id.unwrap())?;
@ -530,8 +529,8 @@ impl FacetsUpdateIncrementalInner {
add_docids: Option<&RoaringBitmap>,
del_docids: Option<&RoaringBitmap>,
) -> Result<bool> {
if add_docids.map_or(true, RoaringBitmap::is_empty)
&& del_docids.map_or(true, RoaringBitmap::is_empty)
if add_docids.is_none_or(RoaringBitmap::is_empty)
&& del_docids.is_none_or(RoaringBitmap::is_empty)
{
return Ok(false);
}
@ -670,7 +669,7 @@ impl FacetsUpdateIncrementalInner {
}
}
impl<'a> FacetGroupKey<&'a [u8]> {
impl FacetGroupKey<&[u8]> {
pub fn into_owned(self) -> FacetGroupKey<Vec<u8>> {
FacetGroupKey {
field_id: self.field_id,

2
crates/milli/src/update/index_documents/enrich.rs
View file

@ -115,7 +115,7 @@ pub fn enrich_documents_batch<R: Read + Seek>(
if let Some(geo_value) = geo_field_id.and_then(|fid| document.get(fid)) {
if let Err(user_error) = validate_geo_from_json(&document_id, geo_value)? {
return Ok(Err(UserError::from(user_error)));
return Ok(Err(UserError::from(Box::new(user_error))));
}
}

4
crates/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
View file

@ -160,11 +160,11 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
let del_geo_support = settings_diff
.old
.geo_fields_ids
.map_or(false, |(lat, lng)| field_id == lat || field_id == lng);
.is_some_and(|(lat, lng)| field_id == lat || field_id == lng);
let add_geo_support = settings_diff
.new
.geo_fields_ids
.map_or(false, |(lat, lng)| field_id == lat || field_id == lng);
.is_some_and(|(lat, lng)| field_id == lat || field_id == lng);
let del_filterable_values =
del_value.map(|value| extract_facet_values(&value, del_geo_support));
let add_filterable_values =

14
crates/milli/src/update/index_documents/extract/extract_geo_points.rs
View file

@ -80,22 +80,28 @@ fn extract_lat_lng(
let (lat, lng) = match (lat, lng) {
(Some(lat), Some(lng)) => (lat, lng),
(Some(_), None) => {
return Err(GeoError::MissingLatitude { document_id: document_id() }.into())
return Err(
Box::new(GeoError::MissingLatitude { document_id: document_id() }).into()
)
}
(None, Some(_)) => {
return Err(GeoError::MissingLongitude { document_id: document_id() }.into())
return Err(
Box::new(GeoError::MissingLongitude { document_id: document_id() }).into()
)
}
(None, None) => return Ok(None),
};
let lat = extract_finite_float_from_value(
serde_json::from_slice(lat).map_err(InternalError::SerdeJson)?,
)
.map_err(|lat| GeoError::BadLatitude { document_id: document_id(), value: lat })?;
.map_err(|lat| GeoError::BadLatitude { document_id: document_id(), value: lat })
.map_err(Box::new)?;
let lng = extract_finite_float_from_value(
serde_json::from_slice(lng).map_err(InternalError::SerdeJson)?,
)
.map_err(|lng| GeoError::BadLongitude { document_id: document_id(), value: lng })?;
.map_err(|lng| GeoError::BadLongitude { document_id: document_id(), value: lng })
.map_err(Box::new)?;
Ok(Some([lat, lng]))
}
None => Ok(None),

6
crates/milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs
View file

@ -69,7 +69,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
let document_id = u32::from_be_bytes(document_id_bytes);
// if we change document, we fill the sorter
if current_document_id.map_or(false, |id| id != document_id) {
if current_document_id.is_some_and(|id| id != document_id) {
// FIXME: span inside of a hot loop might degrade performance and create big reports
let span = tracing::trace_span!(target: "indexing::details", "document_into_sorter");
let _entered = span.enter();
@ -96,7 +96,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
if let Some(deletion) = KvReaderDelAdd::from_slice(value).get(DelAdd::Deletion) {
for (position, word) in KvReaderU16::from_slice(deletion).iter() {
// drain the proximity window until the head word is considered close to the word we are inserting.
while del_word_positions.front().map_or(false, |(_w, p)| {
while del_word_positions.front().is_some_and(|(_w, p)| {
index_proximity(*p as u32, position as u32) >= MAX_DISTANCE
}) {
word_positions_into_word_pair_proximity(
@ -129,7 +129,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
if let Some(addition) = KvReaderDelAdd::from_slice(value).get(DelAdd::Addition) {
for (position, word) in KvReaderU16::from_slice(addition).iter() {
// drain the proximity window until the head word is considered close to the word we are inserting.
while add_word_positions.front().map_or(false, |(_w, p)| {
while add_word_positions.front().is_some_and(|(_w, p)| {
index_proximity(*p as u32, position as u32) >= MAX_DISTANCE
}) {
word_positions_into_word_pair_proximity(

2
crates/milli/src/update/index_documents/extract/extract_word_position_docids.rs
View file

@ -46,7 +46,7 @@ pub fn extract_word_position_docids<R: io::Read + io::Seek>(
.ok_or(SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
let document_id = DocumentId::from_be_bytes(document_id_bytes);
if current_document_id.map_or(false, |id| document_id != id) {
if current_document_id.is_some_and(|id| document_id != id) {
words_position_into_sorter(
current_document_id.unwrap(),
&mut key_buffer,

2
crates/milli/src/update/index_documents/extract/mod.rs
View file

@ -281,7 +281,7 @@ fn send_original_documents_data(
};
if !(remove_vectors.is_empty()
&& manual_vectors.is_empty()
&& embeddings.as_ref().map_or(true, |e| e.is_empty()))
&& embeddings.as_ref().is_none_or(|e| e.is_empty()))
{
let _ = lmdb_writer_sx.send(Ok(TypedChunk::VectorPoints {
remove_vectors,

9
crates/milli/src/update/index_documents/mod.rs
View file

@ -514,12 +514,9 @@ where
InternalError::DatabaseMissingEntry { db_name: "embedder_category_id", key: None },
)?;
let embedder_config = settings_diff.embedding_config_updates.get(&embedder_name);
let was_quantized = settings_diff
.old
.embedding_configs
.get(&embedder_name)
.map_or(false, |conf| conf.2);
let is_quantizing = embedder_config.map_or(false, |action| action.is_being_quantized);
let was_quantized =
settings_diff.old.embedding_configs.get(&embedder_name).is_some_and(|conf| conf.2);
let is_quantizing = embedder_config.is_some_and(|action| action.is_being_quantized);
pool.install(|| {
let mut writer = ArroyWrapper::new(vector_arroy, embedder_index, was_quantized);

2
crates/milli/src/update/index_documents/transform.rs
View file

@ -197,7 +197,7 @@ impl<'a, 'i> Transform<'a, 'i> {
// drop_and_reuse is called instead of .clear() to communicate to the compiler that field_buffer
// does not keep references from the cursor between loop iterations
let mut field_buffer_cache = drop_and_reuse(field_buffer);
if self.indexer_settings.log_every_n.map_or(false, |len| documents_count % len == 0) {
if self.indexer_settings.log_every_n.is_some_and(|len| documents_count % len == 0) {
progress_callback(UpdateIndexingStep::RemapDocumentAddition {
documents_seen: documents_count,
});

9
crates/milli/src/update/index_documents/typed_chunk.rs
View file

@ -55,7 +55,7 @@ impl ChunkAccumulator {
match self
.inner
.iter()
.position(|right| right.first().map_or(false, |right| chunk.mergeable_with(right)))
.position(|right| right.first().is_some_and(|right| chunk.mergeable_with(right)))
{
Some(position) => {
let v = self.inner.get_mut(position).unwrap();
@ -664,11 +664,8 @@ pub(crate) fn write_typed_chunk_into_index(
let embedder_index = index.embedder_category_id.get(wtxn, &embedder_name)?.ok_or(
InternalError::DatabaseMissingEntry { db_name: "embedder_category_id", key: None },
)?;
let binary_quantized = settings_diff
.old
.embedding_configs
.get(&embedder_name)
.map_or(false, |conf| conf.2);
let binary_quantized =
settings_diff.old.embedding_configs.get(&embedder_name).is_some_and(|conf| conf.2);
// FIXME: allow customizing distance
let writer = ArroyWrapper::new(index.vector_arroy, embedder_index, binary_quantized);

6
crates/milli/src/update/new/document.rs
View file

@ -56,13 +56,13 @@ where
content: &'t KvReaderFieldId,
}
impl<'t, Mapper: FieldIdMapper> Clone for DocumentFromDb<'t, Mapper> {
impl<Mapper: FieldIdMapper> Clone for DocumentFromDb<'_, Mapper> {
#[inline]
fn clone(&self) -> Self {
*self
}
}
impl<'t, Mapper: FieldIdMapper> Copy for DocumentFromDb<'t, Mapper> {}
impl<Mapper: FieldIdMapper> Copy for DocumentFromDb<'_, Mapper> {}
impl<'t, Mapper: FieldIdMapper> Document<'t> for DocumentFromDb<'t, Mapper> {
fn iter_top_level_fields(&self) -> impl Iterator<Item = Result<(&'t str, &'t RawValue)>> {
@ -154,7 +154,7 @@ impl<'a, 'doc> DocumentFromVersions<'a, 'doc> {
}
}
impl<'a, 'doc> Document<'doc> for DocumentFromVersions<'a, 'doc> {
impl<'doc> Document<'doc> for DocumentFromVersions<'_, 'doc> {
fn iter_top_level_fields(&self) -> impl Iterator<Item = Result<(&'doc str, &'doc RawValue)>> {
self.versions.iter_top_level_fields().map(Ok)
}

6
crates/milli/src/update/new/extract/cache.rs
View file

@ -121,7 +121,7 @@ impl<'extractor> BalancedCaches<'extractor> {
}
pub fn insert_del_u32(&mut self, key: &[u8], n: u32) -> Result<()> {
if self.max_memory.map_or(false, |mm| self.alloc.allocated_bytes() >= mm) {
if self.max_memory.is_some_and(|mm| self.alloc.allocated_bytes() >= mm) {
self.start_spilling()?;
}
@ -138,7 +138,7 @@ impl<'extractor> BalancedCaches<'extractor> {
}
pub fn insert_add_u32(&mut self, key: &[u8], n: u32) -> Result<()> {
if self.max_memory.map_or(false, |mm| self.alloc.allocated_bytes() >= mm) {
if self.max_memory.is_some_and(|mm| self.alloc.allocated_bytes() >= mm) {
self.start_spilling()?;
}
@ -623,7 +623,7 @@ pub struct FrozenDelAddBbbul<'bump, B> {
pub add: Option<FrozenBbbul<'bump, B>>,
}
impl<'bump, B> FrozenDelAddBbbul<'bump, B> {
impl<B> FrozenDelAddBbbul<'_, B> {
fn is_empty(&self) -> bool {
self.del.is_none() && self.add.is_none()
}

2
crates/milli/src/update/new/extract/documents.rs
View file

@ -31,7 +31,7 @@ pub struct DocumentExtractorData {
pub field_distribution_delta: HashMap<String, i64>,
}
impl<'a, 'b, 'extractor> Extractor<'extractor> for DocumentsExtractor<'a, 'b> {
impl<'extractor> Extractor<'extractor> for DocumentsExtractor<'_, '_> {
type Data = FullySend<RefCell<DocumentExtractorData>>;
fn init_data(&self, _extractor_alloc: &'extractor Bump) -> Result<Self::Data> {

2
crates/milli/src/update/new/extract/faceted/extract_facets.rs
View file

@ -37,7 +37,7 @@ pub struct FacetedExtractorData<'a, 'b> {
is_geo_enabled: bool,
}
impl<'a, 'b, 'extractor> Extractor<'extractor> for FacetedExtractorData<'a, 'b> {
impl<'extractor> Extractor<'extractor> for FacetedExtractorData<'_, '_> {
type Data = RefCell<BalancedCaches<'extractor>>;
fn init_data(&self, extractor_alloc: &'extractor Bump) -> Result<Self::Data> {

40
crates/milli/src/update/new/extract/geo/mod.rs
View file

@ -92,7 +92,7 @@ pub struct FrozenGeoExtractorData<'extractor> {
pub spilled_inserted: Option<BufReader<File>>,
}
impl<'extractor> FrozenGeoExtractorData<'extractor> {
impl FrozenGeoExtractorData<'_> {
pub fn iter_and_clear_removed(
&mut self,
) -> io::Result<impl IntoIterator<Item = io::Result<ExtractedGeoPoint>> + '_> {
@ -160,7 +160,7 @@ impl<'extractor> Extractor<'extractor> for GeoExtractor {
for change in changes {
if data_ref.spilled_removed.is_none()
&& max_memory.map_or(false, |mm| context.extractor_alloc.allocated_bytes() >= mm)
&& max_memory.is_some_and(|mm| context.extractor_alloc.allocated_bytes() >= mm)
{
// We must spill as we allocated too much memory
data_ref.spilled_removed = tempfile::tempfile().map(BufWriter::new).map(Some)?;
@ -258,9 +258,11 @@ pub fn extract_geo_coordinates(
Value::Null => return Ok(None),
Value::Object(map) => map,
value => {
return Err(
GeoError::NotAnObject { document_id: Value::from(external_id), value }.into()
)
return Err(Box::new(GeoError::NotAnObject {
document_id: Value::from(external_id),
value,
})
.into())
}
};
@ -269,23 +271,29 @@ pub fn extract_geo_coordinates(
if geo.is_empty() {
[lat, lng]
} else {
return Err(GeoError::UnexpectedExtraFields {
return Err(Box::new(GeoError::UnexpectedExtraFields {
document_id: Value::from(external_id),
value: Value::from(geo),
}
})
.into());
}
}
(Some(_), None) => {
return Err(GeoError::MissingLongitude { document_id: Value::from(external_id) }.into())
return Err(Box::new(GeoError::MissingLongitude {
document_id: Value::from(external_id),
})
.into())
}
(None, Some(_)) => {
return Err(GeoError::MissingLatitude { document_id: Value::from(external_id) }.into())
return Err(Box::new(GeoError::MissingLatitude {
document_id: Value::from(external_id),
})
.into())
}
(None, None) => {
return Err(GeoError::MissingLatitudeAndLongitude {
return Err(Box::new(GeoError::MissingLatitudeAndLongitude {
document_id: Value::from(external_id),
}
})
.into())
}
};
@ -293,16 +301,18 @@ pub fn extract_geo_coordinates(
match (extract_finite_float_from_value(lat), extract_finite_float_from_value(lng)) {
(Ok(lat), Ok(lng)) => Ok(Some([lat, lng])),
(Ok(_), Err(value)) => {
Err(GeoError::BadLongitude { document_id: Value::from(external_id), value }.into())
Err(Box::new(GeoError::BadLongitude { document_id: Value::from(external_id), value })
.into())
}
(Err(value), Ok(_)) => {
Err(GeoError::BadLatitude { document_id: Value::from(external_id), value }.into())
Err(Box::new(GeoError::BadLatitude { document_id: Value::from(external_id), value })
.into())
}
(Err(lat), Err(lng)) => Err(GeoError::BadLatitudeAndLongitude {
(Err(lat), Err(lng)) => Err(Box::new(GeoError::BadLatitudeAndLongitude {
document_id: Value::from(external_id),
lat,
lng,
}
})
.into()),
}
}

8
crates/milli/src/update/new/extract/searchable/extract_word_docids.rs
View file

@ -31,7 +31,7 @@ pub struct WordDocidsBalancedCaches<'extractor> {
current_docid: Option<DocumentId>,
}
unsafe impl<'extractor> MostlySend for WordDocidsBalancedCaches<'extractor> {}
unsafe impl MostlySend for WordDocidsBalancedCaches<'_> {}
impl<'extractor> WordDocidsBalancedCaches<'extractor> {
pub fn new_in(buckets: usize, max_memory: Option<usize>, alloc: &'extractor Bump) -> Self {
@ -78,7 +78,7 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
buffer.extend_from_slice(&position.to_be_bytes());
self.word_position_docids.insert_add_u32(&buffer, docid)?;
if self.current_docid.map_or(false, |id| docid != id) {
if self.current_docid.is_some_and(|id| docid != id) {
self.flush_fid_word_count(&mut buffer)?;
}
@ -123,7 +123,7 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
buffer.extend_from_slice(&position.to_be_bytes());
self.word_position_docids.insert_del_u32(&buffer, docid)?;
if self.current_docid.map_or(false, |id| docid != id) {
if self.current_docid.is_some_and(|id| docid != id) {
self.flush_fid_word_count(&mut buffer)?;
}
@ -212,7 +212,7 @@ pub struct WordDocidsExtractorData<'a> {
searchable_attributes: Option<Vec<&'a str>>,
}
impl<'a, 'extractor> Extractor<'extractor> for WordDocidsExtractorData<'a> {
impl<'extractor> Extractor<'extractor> for WordDocidsExtractorData<'_> {
type Data = RefCell<Option<WordDocidsBalancedCaches<'extractor>>>;
fn init_data(&self, extractor_alloc: &'extractor Bump) -> Result<Self::Data> {

4
crates/milli/src/update/new/extract/searchable/extract_word_pair_proximity_docids.rs
View file

@ -25,7 +25,7 @@ pub struct WordPairProximityDocidsExtractorData<'a> {
buckets: usize,
}
impl<'a, 'extractor> Extractor<'extractor> for WordPairProximityDocidsExtractorData<'a> {
impl<'extractor> Extractor<'extractor> for WordPairProximityDocidsExtractorData<'_> {
type Data = RefCell<BalancedCaches<'extractor>>;
fn init_data(&self, extractor_alloc: &'extractor Bump) -> Result<Self::Data> {
@ -270,7 +270,7 @@ fn process_document_tokens<'doc>(
// drain the proximity window until the head word is considered close to the word we are inserting.
while word_positions
.front()
.map_or(false, |(_w, p)| index_proximity(*p as u32, pos as u32) >= MAX_DISTANCE)
.is_some_and(|(_w, p)| index_proximity(*p as u32, pos as u32) >= MAX_DISTANCE)
{
word_positions_into_word_pair_proximity(word_positions, word_pair_proximity);
}

2
crates/milli/src/update/new/extract/searchable/tokenize_document.rs
View file

@ -22,7 +22,7 @@ pub struct DocumentTokenizer<'a> {
pub max_positions_per_attributes: u32,
}
impl<'a> DocumentTokenizer<'a> {
impl DocumentTokenizer<'_> {
pub fn tokenize_document<'doc>(
&self,
document: impl Document<'doc>,

2
crates/milli/src/update/new/extract/vectors/mod.rs
View file

@ -43,7 +43,7 @@ pub struct EmbeddingExtractorData<'extractor>(
unsafe impl MostlySend for EmbeddingExtractorData<'_> {}
impl<'a, 'b, 'extractor> Extractor<'extractor> for EmbeddingExtractor<'a, 'b> {
impl<'extractor> Extractor<'extractor> for EmbeddingExtractor<'_, '_> {
type Data = RefCell<EmbeddingExtractorData<'extractor>>;
fn init_data<'doc>(&'doc self, extractor_alloc: &'extractor Bump) -> crate::Result<Self::Data> {

8
crates/milli/src/update/new/indexer/de.rs
View file

@ -29,8 +29,8 @@ impl<'p, 'indexer, Mapper: MutFieldIdMapper> FieldAndDocidExtractor<'p, 'indexer
}
}
impl<'de, 'p, 'indexer: 'de, Mapper: MutFieldIdMapper> Visitor<'de>
for FieldAndDocidExtractor<'p, 'indexer, Mapper>
impl<'de, 'indexer: 'de, Mapper: MutFieldIdMapper> Visitor<'de>
for FieldAndDocidExtractor<'_, 'indexer, Mapper>
{
type Value =
Result<Result<DeOrBumpStr<'de, 'indexer>, DocumentIdExtractionError>, crate::UserError>;
@ -98,7 +98,7 @@ struct NestedPrimaryKeyVisitor<'a, 'bump> {
bump: &'bump Bump,
}
impl<'de, 'a, 'bump: 'de> Visitor<'de> for NestedPrimaryKeyVisitor<'a, 'bump> {
impl<'de, 'bump: 'de> Visitor<'de> for NestedPrimaryKeyVisitor<'_, 'bump> {
type Value = std::result::Result<Option<DeOrBumpStr<'de, 'bump>>, DocumentIdExtractionError>;
fn expecting(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
@ -237,7 +237,7 @@ impl<'de, 'a, Mapper: MutFieldIdMapper> Visitor<'de> for MutFieldIdMapVisitor<'a
pub struct FieldIdMapVisitor<'a, Mapper: FieldIdMapper>(pub &'a Mapper);
impl<'de, 'a, Mapper: FieldIdMapper> Visitor<'de> for FieldIdMapVisitor<'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 {

26
crates/milli/src/update/new/indexer/document_changes.rs
View file

@ -149,16 +149,11 @@ pub struct IndexingContext<
pub grenad_parameters: &'indexer GrenadParameters,
}
impl<
'fid, // invariant lifetime of fields ids map
'indexer, // covariant lifetime of objects that are borrowed during the entire indexing operation
'index, // covariant lifetime of the index
MSP,
> Copy
impl<MSP> Copy
for IndexingContext<
'fid, // invariant lifetime of fields ids map
'indexer, // covariant lifetime of objects that are borrowed during the entire indexing operation
'index, // covariant lifetime of the index
'_, // invariant lifetime of fields ids map
'_, // covariant lifetime of objects that are borrowed during the entire indexing operation
'_, // covariant lifetime of the index
MSP,
>
where
@ -166,16 +161,11 @@ where
{
}
impl<
'fid, // invariant lifetime of fields ids map
'indexer, // covariant lifetime of objects that are borrowed during the entire indexing operation
'index, // covariant lifetime of the index
MSP,
> Clone
impl<MSP> Clone
for IndexingContext<
'fid, // invariant lifetime of fields ids map
'indexer, // covariant lifetime of objects that are borrowed during the entire indexing operation
'index, // covariant lifetime of the index
'_, // invariant lifetime of fields ids map
'_, // covariant lifetime of objects that are borrowed during the entire indexing operation
'_, // covariant lifetime of the index
MSP,
>
where

2
crates/milli/src/update/new/indexer/document_deletion.rs
View file

@ -110,7 +110,7 @@ mod test {
>,
}
unsafe impl<'extractor> MostlySend for DeletionWithData<'extractor> {}
unsafe impl MostlySend for DeletionWithData<'_> {}
struct TrackDeletion<'extractor>(PhantomData<&'extractor ()>);

14
crates/milli/src/update/new/indexer/document_operation.rs
View file

@ -210,14 +210,8 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
primary_key.as_ref().unwrap()
};
let external_id = match retrieved_primary_key.extract_fields_and_docid(
doc,
new_fields_ids_map,
indexer,
) {
Ok(edi) => edi,
Err(e) => return Err(e),
};
let external_id =
retrieved_primary_key.extract_fields_and_docid(doc, new_fields_ids_map, indexer)?;
let external_id = external_id.to_de();
let current_offset = iter.byte_offset();
@ -580,12 +574,12 @@ impl<'pl> PayloadOperations<'pl> {
}
}
Some(InnerDocOp::Deletion) => {
return if self.is_new {
if self.is_new {
Ok(None)
} else {
let deletion = Deletion::create(self.docid, external_doc);
Ok(Some(DocumentChange::Deletion(deletion)))
};
}
}
None => unreachable!("We must not have an empty set of operations on a document"),
}

9
crates/milli/src/update/new/indexer/write.rs
View file

@ -14,7 +14,7 @@ use crate::index::IndexEmbeddingConfig;
use crate::progress::Progress;
use crate::update::settings::InnerIndexSettings;
use crate::vector::{ArroyWrapper, Embedder, EmbeddingConfigs, Embeddings};
use crate::{Error, Index, InternalError, Result};
use crate::{Error, Index, InternalError, Result, UserError};
pub fn write_to_db(
mut writer_receiver: WriterBbqueueReceiver<'_>,
@ -219,7 +219,12 @@ pub fn write_from_bbqueue(
arroy_writers.get(&embedder_id).expect("requested a missing embedder");
let mut embeddings = Embeddings::new(*dimensions);
let all_embeddings = asvs.read_all_embeddings_into_vec(frame, aligned_embedding);
embeddings.append(all_embeddings.to_vec()).unwrap();
if embeddings.append(all_embeddings.to_vec()).is_err() {
return Err(Error::UserError(UserError::InvalidVectorDimensions {
expected: *dimensions,
found: all_embeddings.len(),
}));
}
writer.del_items(wtxn, *dimensions, docid)?;
writer.add_items(wtxn, docid, &embeddings)?;
}

4
crates/milli/src/update/new/words_prefix_docids.rs
View file

@ -149,7 +149,7 @@ impl<'a, 'rtxn> FrozenPrefixBitmaps<'a, 'rtxn> {
}
}
unsafe impl<'a, 'rtxn> Sync for FrozenPrefixBitmaps<'a, 'rtxn> {}
unsafe impl Sync for FrozenPrefixBitmaps<'_, '_> {}
struct WordPrefixIntegerDocids {
database: Database<Bytes, CboRoaringBitmapCodec>,
@ -302,7 +302,7 @@ impl<'a, 'rtxn> FrozenPrefixIntegerBitmaps<'a, 'rtxn> {
}
}
unsafe impl<'a, 'rtxn> Sync for FrozenPrefixIntegerBitmaps<'a, 'rtxn> {}
unsafe impl Sync for FrozenPrefixIntegerBitmaps<'_, '_> {}
#[tracing::instrument(level = "trace", skip_all, target = "indexing::prefix")]
fn delete_prefixes(

10
crates/milli/src/update/settings.rs
View file

@ -560,7 +560,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
// Does the new FST differ from the previous one?
if current
.map_or(true, |current| current.as_fst().as_bytes() != fst.as_fst().as_bytes())
.is_none_or(|current| current.as_fst().as_bytes() != fst.as_fst().as_bytes())
{
// we want to re-create our FST.
self.index.put_stop_words(self.wtxn, &fst)?;
@ -580,7 +580,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
let current = self.index.non_separator_tokens(self.wtxn)?;
// Does the new list differ from the previous one?
if current.map_or(true, |current| &current != non_separator_tokens) {
if current.is_none_or(|current| &current != non_separator_tokens) {
self.index.put_non_separator_tokens(self.wtxn, non_separator_tokens)?;
true
} else {
@ -605,7 +605,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
let current = self.index.separator_tokens(self.wtxn)?;
// Does the new list differ from the previous one?
if current.map_or(true, |current| &current != separator_tokens) {
if current.is_none_or(|current| &current != separator_tokens) {
self.index.put_separator_tokens(self.wtxn, separator_tokens)?;
true
} else {
@ -630,7 +630,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
let current = self.index.dictionary(self.wtxn)?;
// Does the new list differ from the previous one?
if current.map_or(true, |current| &current != dictionary) {
if current.is_none_or(|current| &current != dictionary) {
self.index.put_dictionary(self.wtxn, dictionary)?;
true
} else {
@ -1353,7 +1353,7 @@ impl InnerIndexSettingsDiff {
new_settings.embedding_configs.inner_as_ref()
{
let was_quantized =
old_settings.embedding_configs.get(embedder_name).map_or(false, |conf| conf.2);
old_settings.embedding_configs.get(embedder_name).is_some_and(|conf| conf.2);
// skip embedders that don't use document templates
if !config.uses_document_template() {
continue;