fix PR comments

milli/src/update/facet/mod.rs

@@ -173,13 +173,23 @@ impl<'i> FacetsUpdate<'i> {
             incremental_update.execute(wtxn)?;
         }
 
-        if let Some(normalized_delta_data) = self.normalized_delta_data {
+        match self.normalized_delta_data {
+            Some(data) => index_facet_search(wtxn, data, self.index),
+            None => Ok(()),
+        }
+    }
+}
+
+fn index_facet_search(
+    wtxn: &mut heed::RwTxn,
+    normalized_delta_data: Merger<BufReader<File>, MergeFn>,
+    index: &Index,
+) -> Result<()> {
     let mut iter = normalized_delta_data.into_stream_merger_iter()?;
     while let Some((key_bytes, delta_bytes)) = iter.next()? {
         let deladd_reader = KvReaderDelAdd::new(delta_bytes);
 
-                let database_set = self
+        let database_set = index
-                    .index
             .facet_id_normalized_string_strings
             .remap_key_type::<Bytes>()
             .get(wtxn, key_bytes)?
@@ -199,10 +209,14 @@ impl<'i> FacetsUpdate<'i> {
                 let field_id = FieldId::from_be_bytes(field_id_bytes);
                 let mut set = BTreeSet::new();
                 for facet in del_set {
-                            let key =
+                    let key = FacetGroupKey { field_id, level: 0, left_bound: facet.as_str() };
-                                FacetGroupKey { field_id, level: 0, left_bound: facet.as_str() };
                     // Check if the referenced value doesn't exist anymore before deleting it.
-                            if self.index.facet_id_string_docids.get(wtxn, &key)?.remap_data::<DecodeIgnore>().is_none() {
+                    if index
+                        .facet_id_string_docids
+                        .remap_data_type::<DecodeIgnore>()
+                        .get(wtxn, &key)?
+                        .is_none()
+                    {
                         set.insert(facet);
                     }
                 }
@@ -215,12 +229,12 @@ impl<'i> FacetsUpdate<'i> {
             database_set.difference(&del_set).chain(add_set.iter()).cloned().collect();
 
         if set.is_empty() {
-                    self.index
+            index
                 .facet_id_normalized_string_strings
                 .remap_key_type::<Bytes>()
                 .delete(wtxn, key_bytes)?;
         } else {
-                    self.index
+            index
                 .facet_id_normalized_string_strings
                 .remap_key_type::<Bytes>()
                 .put(wtxn, key_bytes, &set)?;
@@ -228,12 +242,11 @@ impl<'i> FacetsUpdate<'i> {
     }
 
     // We clear the FST of normalized-for-search to compute everything from scratch.
-            self.index.facet_id_string_fst.clear(wtxn)?;
+    index.facet_id_string_fst.clear(wtxn)?;
     // We compute one FST by string facet
     let mut text_fsts = vec![];
     let mut current_fst: Option<(u16, fst::SetBuilder<Vec<u8>>)> = None;
-            let database =
+    let database = index.facet_id_normalized_string_strings.remap_data_type::<DecodeIgnore>();
-                self.index.facet_id_normalized_string_strings.remap_data_type::<DecodeIgnore>();
     for result in database.iter(wtxn)? {
         let ((field_id, normalized_facet), _) = result?;
         current_fst = match current_fst.take() {
@@ -258,12 +271,11 @@ impl<'i> FacetsUpdate<'i> {
 
     // We write those FSTs in LMDB now
     for (field_id, fst) in text_fsts {
-                self.index.facet_id_string_fst.put(wtxn, &field_id, &fst)?;
+        index.facet_id_string_fst.put(wtxn, &field_id, &fst)?;
-            }
     }
+
     Ok(())
 }
-}
 
 #[cfg(test)]
 pub(crate) mod test_helpers {

milli/src/update/index_documents/helpers/merge_functions.rs

@@ -223,27 +223,6 @@ pub fn merge_deladd_cbo_roaring_bitmaps_into_cbo_roaring_bitmap<'a>(
     )?)
 }
 
-pub fn merge_btreeset_string<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Result<Cow<'a, [u8]>> {
-    if values.len() == 1 {
-        Ok(values[0].clone())
-    } else {
-        // TODO improve the perf by using a `#[borrow] Cow<str>`.
-        let strings: BTreeSet<String> = values
-            .iter()
-            .map(AsRef::as_ref)
-            .map(serde_json::from_slice::<BTreeSet<String>>)
-            .map(StdResult::unwrap)
-            .reduce(|mut current, new| {
-                for x in new {
-                    current.insert(x);
-                }
-                current
-            })
-            .unwrap();
-        Ok(Cow::Owned(serde_json::to_vec(&strings).unwrap()))
-    }
-}
-
 /// Do a union of BtreeSet on both sides of a DelAdd obkv
 /// separately and outputs a new DelAdd with both unions.
 pub fn merge_deladd_btreeset_string<'a>(

milli/src/update/index_documents/helpers/mod.rs

@@ -13,10 +13,10 @@ pub use grenad_helpers::{
     GrenadParameters,
 };
 pub use merge_functions::{
-    keep_first, keep_latest_obkv, merge_btreeset_string, merge_cbo_roaring_bitmaps,
+    keep_first, keep_latest_obkv, merge_cbo_roaring_bitmaps, merge_deladd_btreeset_string,
-    merge_deladd_btreeset_string, merge_deladd_cbo_roaring_bitmaps,
+    merge_deladd_cbo_roaring_bitmaps, merge_deladd_cbo_roaring_bitmaps_into_cbo_roaring_bitmap,
-    merge_deladd_cbo_roaring_bitmaps_into_cbo_roaring_bitmap, merge_roaring_bitmaps,
+    merge_roaring_bitmaps, obkvs_keep_last_addition_merge_deletions,
-    obkvs_keep_last_addition_merge_deletions, obkvs_merge_additions_and_deletions, MergeFn,
+    obkvs_merge_additions_and_deletions, MergeFn,
 };
 
 use crate::MAX_WORD_LENGTH;

milli/src/update/index_documents/mod.rs

@@ -25,9 +25,9 @@ use self::enrich::enrich_documents_batch;
 pub use self::enrich::{extract_finite_float_from_value, DocumentId};
 pub use self::helpers::{
     as_cloneable_grenad, create_sorter, create_writer, fst_stream_into_hashset,
-    fst_stream_into_vec, merge_btreeset_string, merge_cbo_roaring_bitmaps,
+    fst_stream_into_vec, merge_cbo_roaring_bitmaps, merge_deladd_cbo_roaring_bitmaps,
-    merge_deladd_cbo_roaring_bitmaps, merge_deladd_cbo_roaring_bitmaps_into_cbo_roaring_bitmap,
+    merge_deladd_cbo_roaring_bitmaps_into_cbo_roaring_bitmap, merge_roaring_bitmaps,
-    merge_roaring_bitmaps, valid_lmdb_key, write_sorter_into_database, writer_into_reader, MergeFn,
+    valid_lmdb_key, write_sorter_into_database, writer_into_reader, MergeFn,
 };
 use self::helpers::{grenad_obkv_into_chunks, GrenadParameters};
 pub use self::transform::{Transform, TransformOutput};

milli/src/update/index_documents/typed_chunk.rs

@@ -41,7 +41,7 @@ impl ChunkAccumulator {
     pub fn pop_longest(&mut self) -> Option<Vec<TypedChunk>> {
         match self.inner.iter().max_by_key(|v| v.len()) {
             Some(left) => {
-                let position = self.inner.iter().position(|right| left == right);
+                let position = self.inner.iter().position(|right| left.len() == right.len());
                 position.map(|p| self.inner.remove(p)).filter(|v| !v.is_empty())
             }
             None => None,
@@ -49,7 +49,11 @@ impl ChunkAccumulator {
     }
 
     pub fn insert(&mut self, chunk: TypedChunk) {
-        match self.inner.iter().position(|right| Some(&chunk) == right.first()) {
+        match self
+            .inner
+            .iter()
+            .position(|right| right.first().map_or(false, |right| chunk.is_batchable_with(right)))
+        {
             Some(position) => {
                 let v = self.inner.get_mut(position).unwrap();
                 v.push(chunk);
@@ -87,8 +91,8 @@ pub(crate) enum TypedChunk {
     ScriptLanguageDocids(HashMap<(Script, Language), (RoaringBitmap, RoaringBitmap)>),
 }
 
-impl PartialEq for TypedChunk {
+impl TypedChunk {
-    fn eq(&self, other: &Self) -> bool {
+    fn is_batchable_with(&self, other: &Self) -> bool {
         use TypedChunk::*;
         match (self, other) {
             (FieldIdDocidFacetStrings(_), FieldIdDocidFacetStrings(_))
@@ -113,7 +117,6 @@ impl PartialEq for TypedChunk {
         }
     }
 }
-impl Eq for TypedChunk {}
 
 impl TypedChunk {
     pub fn to_debug_string(&self) -> String {

milli/src/update/mod.rs

@@ -3,9 +3,8 @@ pub use self::clear_documents::ClearDocuments;
 pub use self::facet::bulk::FacetsUpdateBulk;
 pub use self::facet::incremental::FacetsUpdateIncrementalInner;
 pub use self::index_documents::{
-    merge_btreeset_string, merge_cbo_roaring_bitmaps, merge_roaring_bitmaps,
+    merge_cbo_roaring_bitmaps, merge_roaring_bitmaps, DocumentAdditionResult, DocumentId,
-    DocumentAdditionResult, DocumentId, IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod,
+    IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, MergeFn,
-    MergeFn,
 };
 pub use self::indexer_config::IndexerConfig;
 pub use self::settings::{validate_embedding_settings, Setting, Settings};