feat: Use safest SetBuf constructor instead of new_unchecked

meilidb-core/Cargo.toml

@@ -11,7 +11,7 @@ lazy_static = "1.2.0"
 log = "0.4.6"
 meilidb-tokenizer = { path = "../meilidb-tokenizer", version = "0.1.0" }
 rayon = "1.0.3"
-sdset = "0.3.1"
+sdset = "0.3.2"
 serde = { version = "1.0.88", features = ["derive"] }
 slice-group-by = "0.2.4"
 zerocopy = "0.2.2"

meilidb-data/Cargo.toml

@@ -13,7 +13,7 @@ linked-hash-map = { version = "0.5.2", features = ["serde_impl"] }
 meilidb-core = { path = "../meilidb-core", version = "0.1.0" }
 meilidb-tokenizer = { path = "../meilidb-tokenizer", version = "0.1.0" }
 ordered-float = { version = "1.0.2", features = ["serde"] }
-sdset = "0.3.1"
+sdset = "0.3.2"
 serde = { version = "1.0.91", features = ["derive"] }
 serde_json = { version = "1.0.39", features = ["preserve_order"] }
 sled = "0.23.0"

meilidb-data/src/database/documents_deletion.rs

@@ -49,11 +49,7 @@ impl<'a> DocumentsDeletion<'a> {
         let schema = &lease_inner.schema;
         let words = &lease_inner.raw.words;
 
-        let idset = {
-            self.documents.sort_unstable();
-            self.documents.dedup();
-            SetBuf::new_unchecked(self.documents)
-        };
+        let idset = SetBuf::from_dirty(self.documents);
 
         // collect the ranked attributes according to the schema
         let ranked_attrs: Vec<_> = schema.iter()
@@ -63,7 +59,7 @@ impl<'a> DocumentsDeletion<'a> {
             .collect();
 
         let mut words_document_ids = HashMap::new();
-        for id in idset.into_vec() {
+        for id in idset {
             // remove all the ranked attributes from the ranked_map
             for ranked_attr in &ranked_attrs {
                 self.ranked_map.remove(id, *ranked_attr);
@@ -79,10 +75,8 @@ impl<'a> DocumentsDeletion<'a> {
         }
 
         let mut removed_words = BTreeSet::new();
-        for (word, mut document_ids) in words_document_ids {
-            document_ids.sort_unstable();
-            document_ids.dedup();
-            let document_ids = SetBuf::new_unchecked(document_ids);
+        for (word, document_ids) in words_document_ids {
+            let document_ids = SetBuf::from_dirty(document_ids);
 
             if let Some(doc_indexes) = words.doc_indexes(&word)? {
                 let op = DifferenceByKey::new(&doc_indexes, &document_ids, |d| d.document_id, |id| *id);
@@ -96,7 +90,7 @@ impl<'a> DocumentsDeletion<'a> {
                 }
             }
 
-            for id in document_ids.into_vec() {
+            for id in document_ids {
                 documents.del_all_document_fields(id)?;
                 docs_words.del_doc_words(id)?;
             }

meilidb-data/src/indexer.rs

@@ -70,11 +70,8 @@ impl Indexer {
     pub fn build(self) -> Indexed {
         let words_doc_indexes = self.words_doc_indexes
             .into_iter()
-            .map(|(word, mut indexes)| {
-                indexes.sort_unstable();
-                indexes.dedup();
-                (word, SetBuf::new_unchecked(indexes))
-            }).collect();
+            .map(|(word, indexes)| (word, SetBuf::from_dirty(indexes)))
+            .collect();
 
         let docs_words = self.docs_words
             .into_iter()