Merge remote-tracking branch 'milli/main' into bring-v1-changes

milli/src/update/delete_documents.rs

@@ -575,8 +575,8 @@ fn remove_from_word_docids(
 }
 
 fn remove_docids_from_field_id_docid_facet_value(
-    index: &'_ Index,
-    wtxn: &'_ mut heed::RwTxn,
+    index: &Index,
+    wtxn: &mut heed::RwTxn,
     facet_type: FacetType,
     field_id: FieldId,
     to_remove: &RoaringBitmap,

milli/src/update/facet/incremental.rs

@@ -159,7 +159,7 @@ impl FacetsUpdateIncrementalInner {
     /// See documentation of `insert_in_level`
     fn insert_in_level_0(
         &self,
-        txn: &'_ mut RwTxn,
+        txn: &mut RwTxn,
         field_id: u16,
         facet_value: &[u8],
         docids: &RoaringBitmap,
@@ -213,7 +213,7 @@ impl FacetsUpdateIncrementalInner {
     /// of the parent node should be incremented.
     fn insert_in_level(
         &self,
-        txn: &'_ mut RwTxn,
+        txn: &mut RwTxn,
         field_id: u16,
         level: u8,
         facet_value: &[u8],
@@ -350,7 +350,7 @@ impl FacetsUpdateIncrementalInner {
     /// Insert the given facet value and corresponding document ids in the database.
     pub fn insert(
         &self,
-        txn: &'_ mut RwTxn,
+        txn: &mut RwTxn,
         field_id: u16,
         facet_value: &[u8],
         docids: &RoaringBitmap,
@@ -472,7 +472,7 @@ impl FacetsUpdateIncrementalInner {
     /// its left bound as well.
     fn delete_in_level(
         &self,
-        txn: &'_ mut RwTxn,
+        txn: &mut RwTxn,
         field_id: u16,
         level: u8,
         facet_value: &[u8],
@@ -531,7 +531,7 @@ impl FacetsUpdateIncrementalInner {
 
     fn delete_in_level_0(
         &self,
-        txn: &'_ mut RwTxn,
+        txn: &mut RwTxn,
         field_id: u16,
         facet_value: &[u8],
         docids: &RoaringBitmap,
@@ -559,7 +559,7 @@ impl FacetsUpdateIncrementalInner {
 
     pub fn delete(
         &self,
-        txn: &'_ mut RwTxn,
+        txn: &mut RwTxn,
         field_id: u16,
         facet_value: &[u8],
         docids: &RoaringBitmap,

milli/src/update/index_documents/enrich.rs

@@ -98,7 +98,12 @@ pub fn enrich_documents_batch<R: Read + Seek>(
     // If the settings specifies that a _geo field must be used therefore we must check the
     // validity of it in all the documents of this batch and this is when we return `Some`.
     let geo_field_id = match documents_batch_index.id("_geo") {
-        Some(geo_field_id) if index.sortable_fields(rtxn)?.contains("_geo") => Some(geo_field_id),
+        Some(geo_field_id)
+            if index.sortable_fields(rtxn)?.contains("_geo")
+                || index.filterable_fields(rtxn)?.contains("_geo") =>
+        {
+            Some(geo_field_id)
+        }
         _otherwise => None,
     };
 
@@ -367,11 +372,17 @@ pub fn extract_finite_float_from_value(value: Value) -> StdResult<f64, Value> {
 
 pub fn validate_geo_from_json(id: &DocumentId, bytes: &[u8]) -> Result<StdResult<(), GeoError>> {
     use GeoError::*;
-    let debug_id = || Value::from(id.debug());
+    let debug_id = || {
+        serde_json::from_slice(id.value().as_bytes()).unwrap_or_else(|_| Value::from(id.debug()))
+    };
     match serde_json::from_slice(bytes).map_err(InternalError::SerdeJson)? {
         Value::Object(mut object) => match (object.remove("lat"), object.remove("lng")) {
             (Some(lat), Some(lng)) => {
                 match (extract_finite_float_from_value(lat), extract_finite_float_from_value(lng)) {
+                    (Ok(_), Ok(_)) if !object.is_empty() => Ok(Err(UnexpectedExtraFields {
+                        document_id: debug_id(),
+                        value: object.into(),
+                    })),
                     (Ok(_), Ok(_)) => Ok(Ok(())),
                     (Err(value), Ok(_)) => Ok(Err(BadLatitude { document_id: debug_id(), value })),
                     (Ok(_), Err(value)) => Ok(Err(BadLongitude { document_id: debug_id(), value })),

milli/src/update/index_documents/mod.rs

@@ -965,34 +965,6 @@ mod tests {
             .unwrap();
     }
 
-    #[test]
-    fn index_all_flavour_of_geo() {
-        let mut index = TempIndex::new();
-        index.index_documents_config.update_method = IndexDocumentsMethod::ReplaceDocuments;
-
-        index
-            .update_settings(|settings| {
-                settings.set_filterable_fields(hashset!(S("_geo")));
-            })
-            .unwrap();
-
-        index
-            .add_documents(documents!([
-              { "id": 0, "_geo": { "lat": 31, "lng": [42] } },
-              { "id": 1, "_geo": { "lat": "31" }, "_geo.lng": 42 },
-              { "id": 2, "_geo": { "lng": "42" }, "_geo.lat": "31" },
-              { "id": 3, "_geo.lat": 31, "_geo.lng": "42" },
-            ]))
-            .unwrap();
-
-        let rtxn = index.read_txn().unwrap();
-
-        let mut search = crate::Search::new(&rtxn, &index);
-        search.filter(crate::Filter::from_str("_geoRadius(31, 42, 0.000001)").unwrap().unwrap());
-        let crate::SearchResult { documents_ids, .. } = search.execute().unwrap();
-        assert_eq!(documents_ids, vec![0, 1, 2, 3]);
-    }
-
     #[test]
     fn geo_error() {
         let mut index = TempIndex::new();

milli/src/update/settings.rs

@@ -37,9 +37,6 @@ where
             _ => T::deserialize_from_value(value, location).map(Setting::Set),
         }
     }
-    fn default() -> Option<Self> {
-        Some(Self::NotSet)
-    }
 }
 
 impl<T> Default for Setting<T> {

milli/src/update/words_prefix_position_docids.rs

@@ -140,16 +140,20 @@ impl<'t, 'u, 'i> WordPrefixPositionDocids<'t, 'u, 'i> {
 
         // We remove all the entries that are no more required in this word prefix position
         // docids database.
-        let mut iter =
-            self.index.word_prefix_position_docids.iter_mut(self.wtxn)?.lazily_decode_data();
-        while let Some(((prefix, _), _)) = iter.next().transpose()? {
-            if del_prefix_fst_words.contains(prefix.as_bytes()) {
-                unsafe { iter.del_current()? };
+        // We also avoid iterating over the whole `word_prefix_position_docids` database if we know in
+        // advance that the `if del_prefix_fst_words.contains(prefix.as_bytes()) {` condition below
+        // will always be false (i.e. if `del_prefix_fst_words` is empty).
+        if !del_prefix_fst_words.is_empty() {
+            let mut iter =
+                self.index.word_prefix_position_docids.iter_mut(self.wtxn)?.lazily_decode_data();
+            while let Some(((prefix, _), _)) = iter.next().transpose()? {
+                if del_prefix_fst_words.contains(prefix.as_bytes()) {
+                    unsafe { iter.del_current()? };
+                }
             }
+            drop(iter);
         }
 
-        drop(iter);
-
         // We finally write all the word prefix position docids into the LMDB database.
         sorter_into_lmdb_database(
             self.wtxn,