Introduce a new facet_id_is_null_docids database in the index

milli/src/index.rs

@@ -80,6 +80,7 @@ pub mod db_name {
     pub const FIELD_ID_WORD_COUNT_DOCIDS: &str = "field-id-word-count-docids";
     pub const FACET_ID_F64_DOCIDS: &str = "facet-id-f64-docids";
     pub const FACET_ID_EXISTS_DOCIDS: &str = "facet-id-exists-docids";
+    pub const FACET_ID_IS_NULL_DOCIDS: &str = "facet-id-is-null-docids";
     pub const FACET_ID_STRING_DOCIDS: &str = "facet-id-string-docids";
     pub const FIELD_ID_DOCID_FACET_F64S: &str = "field-id-docid-facet-f64s";
     pub const FIELD_ID_DOCID_FACET_STRINGS: &str = "field-id-docid-facet-strings";
@@ -130,6 +131,9 @@ pub struct Index {
     /// Maps the facet field id and the docids for which this field exists
     pub facet_id_exists_docids: Database<FieldIdCodec, CboRoaringBitmapCodec>,
 
+    /// Maps the facet field id and the docids for which this field is set as null
+    pub facet_id_is_null_docids: Database<FieldIdCodec, CboRoaringBitmapCodec>,
+
     /// Maps the facet field id and ranges of numbers with the docids that corresponds to them.
     pub facet_id_f64_docids: Database<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>,
     /// Maps the facet field id and ranges of strings with the docids that corresponds to them.
@@ -153,7 +157,7 @@ impl Index {
     ) -> Result<Index> {
         use db_name::*;
 
-        options.max_dbs(19);
+        options.max_dbs(20);
         unsafe { options.flag(Flags::MdbAlwaysFreePages) };
 
         let env = options.open(path)?;
@@ -175,6 +179,7 @@ impl Index {
         let facet_id_f64_docids = env.create_database(Some(FACET_ID_F64_DOCIDS))?;
         let facet_id_string_docids = env.create_database(Some(FACET_ID_STRING_DOCIDS))?;
         let facet_id_exists_docids = env.create_database(Some(FACET_ID_EXISTS_DOCIDS))?;
+        let facet_id_is_null_docids = env.create_database(Some(FACET_ID_IS_NULL_DOCIDS))?;
 
         let field_id_docid_facet_f64s = env.create_database(Some(FIELD_ID_DOCID_FACET_F64S))?;
         let field_id_docid_facet_strings =
@@ -201,6 +206,7 @@ impl Index {
             facet_id_f64_docids,
             facet_id_string_docids,
             facet_id_exists_docids,
+            facet_id_is_null_docids,
             field_id_docid_facet_f64s,
             field_id_docid_facet_strings,
             documents,

milli/src/update/clear_documents.rs

@@ -34,6 +34,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
             facet_id_f64_docids,
             facet_id_string_docids,
             facet_id_exists_docids,
+            facet_id_is_null_docids,
             field_id_docid_facet_f64s,
             field_id_docid_facet_strings,
             documents,
@@ -86,6 +87,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
         script_language_docids.clear(self.wtxn)?;
         facet_id_f64_docids.clear(self.wtxn)?;
         facet_id_exists_docids.clear(self.wtxn)?;
+        facet_id_is_null_docids.clear(self.wtxn)?;
         facet_id_string_docids.clear(self.wtxn)?;
         field_id_docid_facet_f64s.clear(self.wtxn)?;
         field_id_docid_facet_strings.clear(self.wtxn)?;

milli/src/update/delete_documents.rs

@@ -245,6 +245,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             field_id_docid_facet_strings: _,
             script_language_docids,
             facet_id_exists_docids,
+            facet_id_is_null_docids,
             documents,
         } = self.index;
 
@@ -523,6 +524,13 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             &self.to_delete_docids,
         )?;
 
+        // We delete the documents ids that are under the facet field id values.
+        remove_docids_from_facet_id_exists_docids(
+            self.wtxn,
+            facet_id_is_null_docids,
+            &self.to_delete_docids,
+        )?;
+
         self.index.put_soft_deleted_documents_ids(self.wtxn, &RoaringBitmap::new())?;
 
         Ok(DetailedDocumentDeletionResult {