implement placeholder search

meilisearch-core/src/update/documents_addition.rs

@@ -217,7 +217,7 @@ pub fn apply_addition<'a, 'b>(
     let mut indexer = RawIndexer::new(stop_words);
 
     // For each document in this update
-    for (document_id, document) in documents_additions {
+    for (document_id, document) in &documents_additions {
         // For each key-value pair in the document.
         for (attribute, value) in document {
             let field_id = schema.insert_and_index(&attribute)?;
@@ -229,7 +229,7 @@ pub fn apply_addition<'a, 'b>(
                 &mut indexer,
                 &schema,
                 field_id,
-                document_id,
+                *document_id,
                 &value,
             )?;
         }
@@ -257,6 +257,10 @@ pub fn apply_addition<'a, 'b>(
         index.facets.add(writer, facet_map)?;
     }
 
+    // update is finished; update sorted document id cache with new state
+    let mut document_ids = index.main.internal_docids(writer)?.to_vec();
+    super::cache_document_ids_sorted(writer, &ranked_map, index, &mut document_ids)?;
+
     Ok(())
 }
 
@@ -313,8 +317,8 @@ pub fn reindex_all_documents(writer: &mut heed::RwTxn<MainT>, index: &store::Ind
         index.facets.add(writer, facet_map)?;
     }
     // ^-- https://github.com/meilisearch/MeiliSearch/pull/631#issuecomment-626624470 --v
-    for document_id in documents_ids_to_reindex {
-        for result in index.documents_fields.document_fields(writer, document_id)? {
+    for document_id in &documents_ids_to_reindex {
+        for result in index.documents_fields.document_fields(writer, *document_id)? {
             let (field_id, bytes) = result?;
             let value: Value = serde_json::from_slice(bytes)?;
             ram_store.insert((document_id, field_id), value);
@@ -330,7 +334,7 @@ pub fn reindex_all_documents(writer: &mut heed::RwTxn<MainT>, index: &store::Ind
                 &mut indexer,
                 &schema,
                 field_id,
-                document_id,
+                *document_id,
                 &value,
             )?;
         }
@@ -354,6 +358,10 @@ pub fn reindex_all_documents(writer: &mut heed::RwTxn<MainT>, index: &store::Ind
         index.facets.add(writer, facet_map)?;
     }
 
+    // update is finished; update sorted document id cache with new state
+    let mut document_ids = index.main.internal_docids(writer)?.to_vec();
+    super::cache_document_ids_sorted(writer, &ranked_map, index, &mut document_ids)?;
+
     Ok(())
 }
 

meilisearch-core/src/update/documents_deletion.rs

@@ -8,7 +8,7 @@ use crate::database::{UpdateEvent, UpdateEventsEmitter};
 use crate::facets;
 use crate::store;
 use crate::update::{next_update_id, compute_short_prefixes, Update};
-use crate::{DocumentId, Error, MResult, RankedMap};
+use crate::{DocumentId, Error, MResult, RankedMap, MainWriter, Index};
 
 pub struct DocumentsDeletion {
     updates_store: store::Updates,
@@ -153,8 +153,8 @@ pub fn apply_documents_deletion(
     }
 
     let deleted_documents_len = deleted_documents.len() as u64;
-    for id in deleted_documents {
-        index.docs_words.del_doc_words(writer, id)?;
+    for id in &deleted_documents {
+        index.docs_words.del_doc_words(writer, *id)?;
     }
 
     let removed_words = fst::Set::from_iter(removed_words).unwrap();
@@ -180,5 +180,28 @@ pub fn apply_documents_deletion(
 
     compute_short_prefixes(writer, &words, index)?;
 
+    // update is finished; update sorted document id cache with new state
+    document_cache_remove_deleted(writer, index, &ranked_map, &deleted_documents)?;
+
+    Ok(())
+}
+
+/// rebuilds the document id cache by either removing deleted documents from the existing cache,
+/// and generating a new one from docs in store
+fn document_cache_remove_deleted(writer: &mut MainWriter, index: &Index, ranked_map: &RankedMap, documents_to_delete: &HashSet<DocumentId>) -> MResult<()> {
+    let new_cache = match index.main.sorted_document_ids_cache(writer)? {
+        // only keep documents that are not in the list of deleted documents. Order is preserved,
+        // no need to resort
+        Some(old_cache) => {
+            old_cache.iter().filter(|docid| !documents_to_delete.contains(docid)).cloned().collect::<Vec<_>>()
+        }
+        // couldn't find cached documents, try building a new cache from documents in store
+        None => {
+            let mut document_ids = index.main.internal_docids(writer)?.to_vec();
+            super::cache_document_ids_sorted(writer, ranked_map, index, &mut document_ids)?;
+            document_ids
+        }
+    };
+    index.main.put_sorted_document_ids_cache(writer, &new_cache)?;
     Ok(())
 }

meilisearch-core/src/update/mod.rs

@@ -25,8 +25,9 @@ use serde::{Deserialize, Serialize};
 use serde_json::Value;
 
 use meilisearch_error::ErrorCode;
+use meilisearch_types::DocumentId;
 
-use crate::{store, MResult};
+use crate::{store, MResult, RankedMap};
 use crate::database::{MainT, UpdateT};
 use crate::settings::SettingsUpdate;
 
@@ -371,3 +372,13 @@ where A: AsRef<[u8]>,
 
     Ok(())
 }
+
+fn cache_document_ids_sorted(
+    writer: &mut heed::RwTxn<MainT>,
+    ranked_map: &RankedMap,
+    index: &store::Index,
+    document_ids: &mut [DocumentId],
+) -> MResult<()> {
+    crate::bucket_sort::placeholder_document_sort(document_ids, index, writer, ranked_map)?;
+    index.main.put_sorted_document_ids_cache(writer, &document_ids)
+}