Reduce the maximum word proximity from 8 to 4

.github/workflows/sdks-tests.yml

@@ -16,23 +16,8 @@ env:
   MEILI_NO_ANALYTICS: 'true'
 
 jobs:
-  define-docker-image:
-    runs-on: ubuntu-latest
-    outputs:
-      docker-image: ${{ steps.define-image.outputs.docker-image }}
-    steps:
-      - uses: actions/checkout@v3
-      - name: Define the Docker image we need to use
-        id: define-image
-        run: |
-          event=${{ github.event.action }}
-          echo "docker-image=nightly" >> $GITHUB_OUTPUT
-          if [[ $event == 'workflow_dispatch' ]]; then
-            echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
-          fi
 
   meilisearch-js-tests:
-    needs: define-docker-image
     name: JS SDK tests
     runs-on: ubuntu-latest
     services:
@@ -67,7 +52,6 @@ jobs:
         run: yarn test:env:browser
 
   instant-meilisearch-tests:
-    needs: define-docker-image
     name: instant-meilisearch tests
     runs-on: ubuntu-latest
     services:
@@ -94,7 +78,6 @@ jobs:
         run: yarn build
 
   meilisearch-php-tests:
-    needs: define-docker-image
     name: PHP SDK tests
     runs-on: ubuntu-latest
     services:
@@ -125,7 +108,6 @@ jobs:
           composer remove --dev guzzlehttp/guzzle http-interop/http-factory-guzzle
 
   meilisearch-python-tests:
-    needs: define-docker-image
     name: Python SDK tests
     runs-on: ubuntu-latest
     services:
@@ -150,7 +132,6 @@ jobs:
         run: pipenv run pytest
 
   meilisearch-go-tests:
-    needs: define-docker-image
     name: Go SDK tests
     runs-on: ubuntu-latest
     services:
@@ -180,7 +161,6 @@ jobs:
         run: go test -v ./...
 
   meilisearch-ruby-tests:
-    needs: define-docker-image
     name: Ruby SDK tests
     runs-on: ubuntu-latest
     services:
@@ -205,7 +185,6 @@ jobs:
         run: bundle exec rspec
 
   meilisearch-rust-tests:
-    needs: define-docker-image
     name: Rust SDK tests
     runs-on: ubuntu-latest
     services:

meilisearch-types/src/error.rs

@@ -224,7 +224,6 @@ InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexUid                       , InvalidRequest       , BAD_REQUEST ;
-InvalidAttributesToSearchOn   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToCrop         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToHighlight    , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
@@ -331,9 +330,6 @@ impl ErrorCode for milli::Error {
                     UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
                     UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
                     UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
-                    UserError::InvalidSearchableAttribute { .. } => {
-                        Code::InvalidAttributesToSearchOn
-                    }
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::SortError(_) => Code::InvalidSearchSort,

meilisearch/src/routes/indexes/search.rs

@@ -66,8 +66,6 @@ pub struct SearchQueryGet {
     crop_marker: String,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchMatchingStrategy>)]
     matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrQueryParamError<InvalidAttributesToSearchOn>)]
-    pub attributes_to_search_on: Option<CS<String>>,
 }
 
 impl From<SearchQueryGet> for SearchQuery {
@@ -98,7 +96,6 @@ impl From<SearchQueryGet> for SearchQuery {
             highlight_post_tag: other.highlight_post_tag,
             crop_marker: other.crop_marker,
             matching_strategy: other.matching_strategy,
-            attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
         }
     }
 }

meilisearch/src/search.rs

@@ -68,8 +68,6 @@ pub struct SearchQuery {
     pub crop_marker: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
     pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidAttributesToSearchOn>, default)]
-    pub attributes_to_search_on: Option<Vec<String>>,
 }
 
 impl SearchQuery {
@@ -121,8 +119,6 @@ pub struct SearchQueryWithIndex {
     pub crop_marker: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
     pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidAttributesToSearchOn>, default)]
-    pub attributes_to_search_on: Option<Vec<String>>,
 }
 
 impl SearchQueryWithIndex {
@@ -146,7 +142,6 @@ impl SearchQueryWithIndex {
             highlight_post_tag,
             crop_marker,
             matching_strategy,
-            attributes_to_search_on,
         } = self;
         (
             index_uid,
@@ -168,7 +163,6 @@ impl SearchQueryWithIndex {
                 highlight_post_tag,
                 crop_marker,
                 matching_strategy,
-                attributes_to_search_on,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
@@ -280,10 +274,6 @@ pub fn perform_search(
         search.query(query);
     }
 
-    if let Some(ref searchable) = query.attributes_to_search_on {
-        search.searchable_attributes(searchable);
-    }
-
     let is_finite_pagination = query.is_finite_pagination();
     search.terms_matching_strategy(query.matching_strategy.into());
 

meilisearch/tests/search/errors.rs

@@ -963,27 +963,3 @@ async fn sort_unset_ranking_rule() {
         )
         .await;
 }
-
-#[actix_rt::test]
-async fn search_on_unknown_field() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown"]}),
-            |response, code| {
-                assert_eq!(400, code, "{}", response);
-                assert_eq!(response, json!({
-                    "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
-                    "code": "invalid_attributes_to_search_on",
-                    "type": "invalid_request",
-                    "link": "https://docs.meilisearch.com/errors#invalid_attributes_to_search_on"
-                }));
-            },
-        )
-        .await;
-}

meilisearch/tests/search/mod.rs

@@ -5,7 +5,6 @@ mod errors;
 mod formatted;
 mod multi;
 mod pagination;
-mod restrict_searchable;
 
 use once_cell::sync::Lazy;
 use serde_json::{json, Value};

meilisearch/tests/search/restrict_searchable.rs

@@ -1,241 +0,0 @@
-use once_cell::sync::Lazy;
-use serde_json::{json, Value};
-
-use crate::common::index::Index;
-use crate::common::Server;
-
-async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
-    let index = server.index("test");
-
-    index.add_documents(documents.clone(), None).await;
-    index.wait_task(0).await;
-    index
-}
-
-static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-    {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-    },
-    {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-    },
-    {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-    }])
-});
-
-#[actix_rt::test]
-async fn simple_search_on_title() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"]}),
-            |response, code| {
-                assert_eq!(200, code, "{}", response);
-                assert_eq!(response["hits"].as_array().unwrap().len(), 2);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_prefix_search_on_title() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(json!({"q": "Captain Mar", "attributesToSearchOn": ["title"]}), |response, code| {
-            assert_eq!(200, code, "{}", response);
-            assert_eq!(response["hits"].as_array().unwrap().len(), 2);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_title_matching_strategy_all() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search matching strategy all should only return 1 document (ids: 2).
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "matchingStrategy": "all"}), |response, code| {
-            assert_eq!(200, code, "{}", response);
-            assert_eq!(response["hits"].as_array().unwrap().len(), 1);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_no_field() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search on no field shouldn't return any document.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": []}), |response, code| {
-            assert_eq!(200, code, "{}", response);
-            assert_eq!(response["hits"].as_array().unwrap().len(), 0);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn word_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // Document 3 should appear before document 2.
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["id"]}),
-            |response, code| {
-                assert_eq!(200, code, "{}", response);
-                assert_eq!(
-                    response["hits"],
-                    json!([
-                        {"id": "3"},
-                        {"id": "2"},
-                    ])
-                );
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn word_ranking_rule_order_exact_words() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    index.update_settings_typo_tolerance(json!({"disableOnWords": ["Captain", "Marvel"]})).await;
-    index.wait_task(1).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["id"]}),
-            |response, code| {
-                assert_eq!(200, code, "{}", response);
-                assert_eq!(
-                    response["hits"],
-                    json!([
-                        {"id": "3"},
-                        {"id": "2"},
-                    ])
-                );
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn typo_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Capitain Marivel",
-            "desc": "Captain Marvel",
-            "id": "1",
-        },
-        {
-            "title": "Captain Marivel",
-            "desc": "a Shazam ersatz",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["id"]}), |response, code| {
-            assert_eq!(200, code, "{}", response);
-            assert_eq!(
-                response["hits"],
-                json!([
-                    {"id": "2"},
-                    {"id": "1"},
-                ])
-            );
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn attributes_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Captain Marvel",
-            "desc": "a Shazam ersatz",
-            "footer": "The story of Captain Marvel",
-            "id": "1",
-        },
-        {
-            "title": "The Avengers",
-            "desc": "Captain Marvel is far from the earth",
-            "footer": "A super hero team",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": ["desc", "footer"], "attributesToRetrieve": ["id"]}), |response, code| {
-            assert_eq!(200, code, "{}", response);
-            assert_eq!(
-                response["hits"],
-                json!([
-                    {"id": "2"},
-                    {"id": "1"},
-                ])
-            );
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn exactness_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Captain Marvel",
-            "desc": "Captain Marivel",
-            "id": "1",
-        },
-        {
-            "title": "Captain Marvel",
-            "desc": "CaptainMarvel",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToRetrieve": ["id"], "attributesToSearchOn": ["desc"]}), |response, code| {
-            assert_eq!(200, code, "{}", response);
-            assert_eq!(
-                response["hits"],
-                json!([
-                    {"id": "2"},
-                    {"id": "1"},
-                ])
-            );
-        })
-        .await;
-}

milli/src/error.rs

@@ -124,16 +124,6 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
         }
     )]
     InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
-    #[error("Attribute `{}` is not searchable. Available searchable attributes are: `{}{}`.",
-        .field,
-        .valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
-        .hidden_fields.then_some(", <..hidden-attributes>").unwrap_or(""),
-    )]
-    InvalidSearchableAttribute {
-        field: String,
-        valid_fields: BTreeSet<String>,
-        hidden_fields: bool,
-    },
     #[error("{}", HeedError::BadOpenOptions)]
     InvalidLmdbOpenOptions,
     #[error("You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.")]

milli/src/heed_codec/mod.rs

@@ -23,9 +23,3 @@ pub use self::roaring_bitmap_length::{
 pub use self::script_language_codec::ScriptLanguageCodec;
 pub use self::str_beu32_codec::{StrBEU16Codec, StrBEU32Codec};
 pub use self::str_str_u8_codec::{U8StrStrCodec, UncheckedU8StrStrCodec};
-
-pub trait BytesDecodeOwned {
-    type DItem;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem>;
-}

milli/src/heed_codec/roaring_bitmap/bo_roaring_bitmap_codec.rs

@@ -2,11 +2,8 @@ use std::borrow::Cow;
 use std::convert::TryInto;
 use std::mem::size_of;
 
-use heed::BytesDecode;
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct BoRoaringBitmapCodec;
 
 impl BoRoaringBitmapCodec {
@@ -16,7 +13,7 @@ impl BoRoaringBitmapCodec {
     }
 }
 
-impl BytesDecode<'_> for BoRoaringBitmapCodec {
+impl heed::BytesDecode<'_> for BoRoaringBitmapCodec {
     type DItem = RoaringBitmap;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
@@ -31,14 +28,6 @@ impl BytesDecode<'_> for BoRoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for BoRoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}
-
 impl heed::BytesEncode<'_> for BoRoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -5,8 +5,6 @@ use std::mem::size_of;
 use byteorder::{NativeEndian, ReadBytesExt, WriteBytesExt};
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 /// This is the limit where using a byteorder became less size efficient
 /// than using a direct roaring encoding, it is also the point where we are able
 /// to determine the encoding used only by using the array of bytes length.
@@ -105,14 +103,6 @@ impl heed::BytesDecode<'_> for CboRoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for CboRoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::deserialize_from(bytes).ok()
-    }
-}
-
 impl heed::BytesEncode<'_> for CboRoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap/roaring_bitmap_codec.rs

@@ -2,8 +2,6 @@ use std::borrow::Cow;
 
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct RoaringBitmapCodec;
 
 impl heed::BytesDecode<'_> for RoaringBitmapCodec {
@@ -14,14 +12,6 @@ impl heed::BytesDecode<'_> for RoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for RoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmap::deserialize_from(bytes).ok()
-    }
-}
-
 impl heed::BytesEncode<'_> for RoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap_length/bo_roaring_bitmap_len_codec.rs

@@ -1,23 +1,11 @@
 use std::mem;
 
-use heed::BytesDecode;
-
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct BoRoaringBitmapLenCodec;
 
-impl BytesDecode<'_> for BoRoaringBitmapLenCodec {
+impl heed::BytesDecode<'_> for BoRoaringBitmapLenCodec {
     type DItem = u64;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
         Some((bytes.len() / mem::size_of::<u32>()) as u64)
     }
 }
-
-impl BytesDecodeOwned for BoRoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}

milli/src/heed_codec/roaring_bitmap_length/cbo_roaring_bitmap_len_codec.rs

@@ -1,14 +1,11 @@
 use std::mem;
 
-use heed::BytesDecode;
-
 use super::{BoRoaringBitmapLenCodec, RoaringBitmapLenCodec};
 use crate::heed_codec::roaring_bitmap::cbo_roaring_bitmap_codec::THRESHOLD;
-use crate::heed_codec::BytesDecodeOwned;
 
 pub struct CboRoaringBitmapLenCodec;
 
-impl BytesDecode<'_> for CboRoaringBitmapLenCodec {
+impl heed::BytesDecode<'_> for CboRoaringBitmapLenCodec {
     type DItem = u64;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
@@ -23,11 +20,3 @@ impl BytesDecode<'_> for CboRoaringBitmapLenCodec {
         }
     }
 }
-
-impl BytesDecodeOwned for CboRoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}

milli/src/heed_codec/roaring_bitmap_length/roaring_bitmap_len_codec.rs

@@ -3,8 +3,6 @@ use std::mem;
 
 use byteorder::{LittleEndian, ReadBytesExt};
 
-use crate::heed_codec::BytesDecodeOwned;
-
 const SERIAL_COOKIE_NO_RUNCONTAINER: u32 = 12346;
 const SERIAL_COOKIE: u16 = 12347;
 
@@ -61,14 +59,6 @@ impl heed::BytesDecode<'_> for RoaringBitmapLenCodec {
     }
 }
 
-impl BytesDecodeOwned for RoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmapLenCodec::deserialize_from_slice(bytes).ok()
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use heed::BytesEncode;

milli/src/proximity.rs

@@ -2,7 +2,7 @@ use std::cmp;
 
 use crate::{relative_from_absolute_position, Position};
 
-pub const MAX_DISTANCE: u32 = 8;
+pub const MAX_DISTANCE: u32 = 4;
 
 pub fn index_proximity(lhs: u32, rhs: u32) -> u32 {
     if lhs <= rhs {

milli/src/search/mod.rs

@@ -27,7 +27,6 @@ pub struct Search<'a> {
     offset: usize,
     limit: usize,
     sort_criteria: Option<Vec<AscDesc>>,
-    searchable_attributes: Option<&'a [String]>,
     geo_strategy: new::GeoSortStrategy,
     terms_matching_strategy: TermsMatchingStrategy,
     words_limit: usize,
@@ -44,7 +43,6 @@ impl<'a> Search<'a> {
             offset: 0,
             limit: 20,
             sort_criteria: None,
-            searchable_attributes: None,
             geo_strategy: new::GeoSortStrategy::default(),
             terms_matching_strategy: TermsMatchingStrategy::default(),
             exhaustive_number_hits: false,
@@ -74,11 +72,6 @@ impl<'a> Search<'a> {
         self
     }
 
-    pub fn searchable_attributes(&mut self, searchable: &'a [String]) -> &mut Search<'a> {
-        self.searchable_attributes = Some(searchable);
-        self
-    }
-
     pub fn terms_matching_strategy(&mut self, value: TermsMatchingStrategy) -> &mut Search<'a> {
         self.terms_matching_strategy = value;
         self
@@ -109,11 +102,6 @@ impl<'a> Search<'a> {
 
     pub fn execute(&self) -> Result<SearchResult> {
         let mut ctx = SearchContext::new(self.index, self.rtxn);
-
-        if let Some(searchable_attributes) = self.searchable_attributes {
-            ctx.searchable_attributes(searchable_attributes)?;
-        }
-
         let PartialSearchResult { located_query_terms, candidates, documents_ids } =
             execute_search(
                 &mut ctx,
@@ -148,7 +136,6 @@ impl fmt::Debug for Search<'_> {
             offset,
             limit,
             sort_criteria,
-            searchable_attributes,
             geo_strategy: _,
             terms_matching_strategy,
             words_limit,
@@ -162,7 +149,6 @@ impl fmt::Debug for Search<'_> {
             .field("offset", offset)
             .field("limit", limit)
             .field("sort_criteria", sort_criteria)
-            .field("searchable_attributes", searchable_attributes)
             .field("terms_matching_strategy", terms_matching_strategy)
             .field("exhaustive_number_hits", exhaustive_number_hits)
             .field("words_limit", words_limit)

milli/src/search/new/db_cache.rs

@@ -4,13 +4,12 @@ use std::hash::Hash;
 
 use fxhash::FxHashMap;
 use heed::types::ByteSlice;
-use heed::{BytesEncode, Database, RoTxn};
+use heed::{BytesDecode, BytesEncode, Database, RoTxn};
 use roaring::RoaringBitmap;
 
 use super::interner::Interned;
 use super::Word;
-use crate::heed_codec::{BytesDecodeOwned, StrBEU16Codec};
-use crate::update::{merge_cbo_roaring_bitmaps, MergeFn};
+use crate::heed_codec::StrBEU16Codec;
 use crate::{
     CboRoaringBitmapCodec, CboRoaringBitmapLenCodec, Result, RoaringBitmapCodec, SearchContext,
 };
@@ -23,110 +22,50 @@ use crate::{
 #[derive(Default)]
 pub struct DatabaseCache<'ctx> {
     pub word_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
     pub word_prefix_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
     pub prefix_word_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
-    pub word_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub exact_word_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub exact_word_prefix_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
+    pub word_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub exact_word_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub word_prefix_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub exact_word_prefix_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
 
     pub words_fst: Option<fst::Set<Cow<'ctx, [u8]>>>,
-    pub word_position_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_position_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
+    pub word_position_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
+    pub word_prefix_position_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
     pub word_positions: FxHashMap<Interned<String>, Vec<u16>>,
     pub word_prefix_positions: FxHashMap<Interned<String>, Vec<u16>>,
 
-    pub word_fid_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_fid_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
+    pub word_fid_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
+    pub word_prefix_fid_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
     pub word_fids: FxHashMap<Interned<String>, Vec<u16>>,
     pub word_prefix_fids: FxHashMap<Interned<String>, Vec<u16>>,
 }
 impl<'ctx> DatabaseCache<'ctx> {
-    fn get_value<'v, K1, KC, DC>(
+    fn get_value<'v, K1, KC>(
         txn: &'ctx RoTxn,
         cache_key: K1,
         db_key: &'v KC::EItem,
-        cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
+        cache: &mut FxHashMap<K1, Option<&'ctx [u8]>>,
         db: Database<KC, ByteSlice>,
-    ) -> Result<Option<DC::DItem>>
+    ) -> Result<Option<&'ctx [u8]>>
     where
         K1: Copy + Eq + Hash,
         KC: BytesEncode<'v>,
-        DC: BytesDecodeOwned,
     {
-        match cache.entry(cache_key) {
-            Entry::Occupied(_) => {}
+        let bitmap_ptr = match cache.entry(cache_key) {
+            Entry::Occupied(bitmap_ptr) => *bitmap_ptr.get(),
             Entry::Vacant(entry) => {
-                let bitmap_ptr = db.get(txn, db_key)?.map(Cow::Borrowed);
-                entry.insert(bitmap_ptr);
-            }
-        }
-
-        match cache.get(&cache_key).unwrap() {
-            Some(Cow::Borrowed(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            Some(Cow::Owned(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            None => Ok(None),
-        }
-    }
-
-    fn get_value_from_keys<'v, K1, KC, DC>(
-        txn: &'ctx RoTxn,
-        cache_key: K1,
-        db_keys: &'v [KC::EItem],
-        cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
-        db: Database<KC, ByteSlice>,
-        merger: MergeFn,
-    ) -> Result<Option<DC::DItem>>
-    where
-        K1: Copy + Eq + Hash,
-        KC: BytesEncode<'v>,
-        DC: BytesDecodeOwned,
-        KC::EItem: Sized,
-    {
-        match cache.entry(cache_key) {
-            Entry::Occupied(_) => {}
-            Entry::Vacant(entry) => {
-                let bitmap_ptr: Option<Cow<'ctx, [u8]>> = match db_keys {
-                    [] => None,
-                    [key] => db.get(txn, key)?.map(Cow::Borrowed),
-                    keys => {
-                        let bitmaps = keys
-                            .iter()
-                            .filter_map(|key| db.get(txn, key).transpose())
-                            .map(|v| v.map(Cow::Borrowed))
-                            .collect::<std::result::Result<Vec<Cow<[u8]>>, _>>()?;
-
-                        if bitmaps.is_empty() {
-                            None
-                        } else {
-                            Some(merger(&[], &bitmaps[..])?)
-                        }
-                    }
-                };
-
+                let bitmap_ptr = db.get(txn, db_key)?;
                 entry.insert(bitmap_ptr);
+                bitmap_ptr
             }
         };
-
-        match cache.get(&cache_key).unwrap() {
-            Some(Cow::Borrowed(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            Some(Cow::Owned(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            None => Ok(None),
-        }
+        Ok(bitmap_ptr)
     }
 }
-
 impl<'ctx> SearchContext<'ctx> {
     pub fn get_words_fst(&mut self) -> Result<fst::Set<Cow<'ctx, [u8]>>> {
         if let Some(fst) = self.db_cache.words_fst.clone() {
@@ -160,41 +99,30 @@ impl<'ctx> SearchContext<'ctx> {
 
     /// Retrieve or insert the given value in the `word_docids` database.
     fn get_db_word_docids(&mut self, word: Interned<String>) -> Result<Option<RoaringBitmap>> {
-        match &self.restricted_fids {
-            Some(restricted_fids) => {
-                let interned = self.word_interner.get(word).as_str();
-                let keys: Vec<_> = restricted_fids.iter().map(|fid| (interned, *fid)).collect();
-
-                DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
-                    self.txn,
-                    word,
-                    &keys[..],
-                    &mut self.db_cache.word_docids,
-                    self.index.word_fid_docids.remap_data_type::<ByteSlice>(),
-                    merge_cbo_roaring_bitmaps,
-                )
-            }
-            None => DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
-                self.txn,
-                word,
-                self.word_interner.get(word).as_str(),
-                &mut self.db_cache.word_docids,
-                self.index.word_docids.remap_data_type::<ByteSlice>(),
-            ),
-        }
+        DatabaseCache::get_value(
+            self.txn,
+            word,
+            self.word_interner.get(word).as_str(),
+            &mut self.db_cache.word_docids,
+            self.index.word_docids.remap_data_type::<ByteSlice>(),
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     fn get_db_exact_word_docids(
         &mut self,
         word: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             word,
             self.word_interner.get(word).as_str(),
             &mut self.db_cache.exact_word_docids,
             self.index.exact_word_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn word_prefix_docids(&mut self, prefix: Word) -> Result<Option<RoaringBitmap>> {
@@ -222,41 +150,30 @@ impl<'ctx> SearchContext<'ctx> {
         &mut self,
         prefix: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        match &self.restricted_fids {
-            Some(restricted_fids) => {
-                let interned = self.word_interner.get(prefix).as_str();
-                let keys: Vec<_> = restricted_fids.iter().map(|fid| (interned, *fid)).collect();
-
-                DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
-                    self.txn,
-                    prefix,
-                    &keys[..],
-                    &mut self.db_cache.word_prefix_docids,
-                    self.index.word_prefix_fid_docids.remap_data_type::<ByteSlice>(),
-                    merge_cbo_roaring_bitmaps,
-                )
-            }
-            None => DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
-                self.txn,
-                prefix,
-                self.word_interner.get(prefix).as_str(),
-                &mut self.db_cache.word_prefix_docids,
-                self.index.word_prefix_docids.remap_data_type::<ByteSlice>(),
-            ),
-        }
+        DatabaseCache::get_value(
+            self.txn,
+            prefix,
+            self.word_interner.get(prefix).as_str(),
+            &mut self.db_cache.word_prefix_docids,
+            self.index.word_prefix_docids.remap_data_type::<ByteSlice>(),
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     fn get_db_exact_word_prefix_docids(
         &mut self,
         prefix: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             prefix,
             self.word_interner.get(prefix).as_str(),
             &mut self.db_cache.exact_word_prefix_docids,
             self.index.exact_word_prefix_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_pair_proximity_docids(
@@ -265,7 +182,7 @@ impl<'ctx> SearchContext<'ctx> {
         word2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, word2),
             &(
@@ -275,7 +192,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_pair_proximity_docids,
             self.index.word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_pair_proximity_docids_len(
@@ -284,7 +203,7 @@ impl<'ctx> SearchContext<'ctx> {
         word2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<u64>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapLenCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, word2),
             &(
@@ -294,7 +213,11 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_pair_proximity_docids,
             self.index.word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| {
+            CboRoaringBitmapLenCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into())
+        })
+        .transpose()
     }
 
     pub fn get_db_word_prefix_pair_proximity_docids(
@@ -303,7 +226,7 @@ impl<'ctx> SearchContext<'ctx> {
         prefix2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, prefix2),
             &(
@@ -313,7 +236,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_prefix_pair_proximity_docids,
             self.index.word_prefix_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
     pub fn get_db_prefix_word_pair_proximity_docids(
         &mut self,
@@ -321,7 +246,7 @@ impl<'ctx> SearchContext<'ctx> {
         right: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, left_prefix, right),
             &(
@@ -331,7 +256,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.prefix_word_pair_proximity_docids,
             self.index.prefix_word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_fid_docids(
@@ -339,18 +266,15 @@ impl<'ctx> SearchContext<'ctx> {
         word: Interned<String>,
         fid: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        // if the requested fid isn't in the restricted list, return None.
-        if self.restricted_fids.as_ref().map_or(false, |fids| !fids.contains(&fid)) {
-            return Ok(None);
-        }
-
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word, fid),
             &(self.word_interner.get(word).as_str(), fid),
             &mut self.db_cache.word_fid_docids,
             self.index.word_fid_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_prefix_fid_docids(
@@ -358,18 +282,15 @@ impl<'ctx> SearchContext<'ctx> {
         word_prefix: Interned<String>,
         fid: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        // if the requested fid isn't in the restricted list, return None.
-        if self.restricted_fids.as_ref().map_or(false, |fids| !fids.contains(&fid)) {
-            return Ok(None);
-        }
-
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word_prefix, fid),
             &(self.word_interner.get(word_prefix).as_str(), fid),
             &mut self.db_cache.word_prefix_fid_docids,
             self.index.word_prefix_fid_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_fids(&mut self, word: Interned<String>) -> Result<Vec<u16>> {
@@ -388,7 +309,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, fid), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache.word_fid_docids.insert((word, fid), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_fid_docids.insert((word, fid), Some(value));
                     fids.push(fid);
                 }
                 entry.insert(fids.clone());
@@ -414,9 +335,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, fid), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache
-                        .word_prefix_fid_docids
-                        .insert((word_prefix, fid), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_prefix_fid_docids.insert((word_prefix, fid), Some(value));
                     fids.push(fid);
                 }
                 entry.insert(fids.clone());
@@ -431,13 +350,15 @@ impl<'ctx> SearchContext<'ctx> {
         word: Interned<String>,
         position: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word, position),
             &(self.word_interner.get(word).as_str(), position),
             &mut self.db_cache.word_position_docids,
             self.index.word_position_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_prefix_position_docids(
@@ -445,13 +366,15 @@ impl<'ctx> SearchContext<'ctx> {
         word_prefix: Interned<String>,
         position: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word_prefix, position),
             &(self.word_interner.get(word_prefix).as_str(), position),
             &mut self.db_cache.word_prefix_position_docids,
             self.index.word_prefix_position_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_positions(&mut self, word: Interned<String>) -> Result<Vec<u16>> {
@@ -470,9 +393,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, position), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache
-                        .word_position_docids
-                        .insert((word, position), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_position_docids.insert((word, position), Some(value));
                     positions.push(position);
                 }
                 entry.insert(positions.clone());
@@ -503,7 +424,7 @@ impl<'ctx> SearchContext<'ctx> {
                     // filling other caches to avoid searching for them again
                     self.db_cache
                         .word_prefix_position_docids
-                        .insert((word_prefix, position), Some(Cow::Borrowed(value)));
+                        .insert((word_prefix, position), Some(value));
                     positions.push(position);
                 }
                 entry.insert(positions.clone());

milli/src/search/new/mod.rs

@@ -20,7 +20,7 @@ mod sort;
 #[cfg(test)]
 mod tests;
 
-use std::collections::{BTreeSet, HashSet};
+use std::collections::HashSet;
 
 use bucket_sort::{bucket_sort, BucketSortOutput};
 use charabia::TokenizerBuilder;
@@ -44,7 +44,6 @@ use self::geo_sort::GeoSort;
 pub use self::geo_sort::Strategy as GeoSortStrategy;
 use self::graph_based_ranking_rule::Words;
 use self::interner::Interned;
-use crate::error::FieldIdMapMissingEntry;
 use crate::search::new::distinct::apply_distinct_rule;
 use crate::{AscDesc, DocumentId, Filter, Index, Member, Result, TermsMatchingStrategy, UserError};
 
@@ -57,7 +56,6 @@ pub struct SearchContext<'ctx> {
     pub phrase_interner: DedupInterner<Phrase>,
     pub term_interner: Interner<QueryTerm>,
     pub phrase_docids: PhraseDocIdsCache,
-    pub restricted_fids: Option<Vec<u16>>,
 }
 
 impl<'ctx> SearchContext<'ctx> {
@@ -70,66 +68,8 @@ impl<'ctx> SearchContext<'ctx> {
             phrase_interner: <_>::default(),
             term_interner: <_>::default(),
             phrase_docids: <_>::default(),
-            restricted_fids: None,
         }
     }
-
-    pub fn searchable_attributes(&mut self, searchable_attributes: &'ctx [String]) -> Result<()> {
-        let fids_map = self.index.fields_ids_map(self.txn)?;
-        let searchable_names = self.index.searchable_fields(self.txn)?;
-
-        let mut restricted_fids = Vec::new();
-        for field_name in searchable_attributes {
-            let searchable_contains_name =
-                searchable_names.as_ref().map(|sn| sn.iter().any(|name| name == field_name));
-            let fid = match (fids_map.id(field_name), searchable_contains_name) {
-                // The Field id exist and the field is searchable
-                (Some(fid), Some(true)) | (Some(fid), None) => fid,
-                // The field is searchable but the Field id doesn't exist => Internal Error
-                (None, Some(true)) => {
-                    return Err(FieldIdMapMissingEntry::FieldName {
-                        field_name: field_name.to_string(),
-                        process: "search",
-                    }
-                    .into())
-                }
-                // The field is not searchable => User error
-                _otherwise => {
-                    let mut valid_fields: BTreeSet<_> =
-                        fids_map.names().map(String::from).collect();
-
-                    // Filter by the searchable names
-                    if let Some(sn) = searchable_names {
-                        let searchable_names = sn.iter().map(|s| s.to_string()).collect();
-                        valid_fields = &valid_fields & &searchable_names;
-                    }
-
-                    let searchable_count = valid_fields.len();
-
-                    // Remove hidden fields
-                    if let Some(dn) = self.index.displayed_fields(self.txn)? {
-                        let displayable_names = dn.iter().map(|s| s.to_string()).collect();
-                        valid_fields = &valid_fields & &displayable_names;
-                    }
-
-                    let hidden_fields = searchable_count > valid_fields.len();
-                    let field = field_name.to_string();
-                    return Err(UserError::InvalidSearchableAttribute {
-                        field,
-                        valid_fields,
-                        hidden_fields,
-                    }
-                    .into());
-                }
-            };
-
-            restricted_fids.push(fid);
-        }
-
-        self.restricted_fids = Some(restricted_fids);
-
-        Ok(())
-    }
 }
 
 #[derive(Clone, Copy, PartialEq, PartialOrd, Ord, Eq)]

milli/src/search/new/query_term/parse_query.rs

@@ -79,7 +79,7 @@ pub fn located_query_terms_from_tokens(
             TokenKind::Separator(separator_kind) => {
                 // add penalty for hard separators
                 if let SeparatorKind::Hard = separator_kind {
-                    position = position.wrapping_add(7);
+                    position = position.wrapping_add(1);
                 }
 
                 phrase = 'phrase: {

milli/src/search/new/ranking_rule_graph/proximity/build.rs

@@ -1,6 +1,7 @@
 #![allow(clippy::too_many_arguments)]
 
 use super::ProximityCondition;
+use crate::proximity::MAX_DISTANCE;
 use crate::search::new::interner::{DedupInterner, Interned};
 use crate::search::new::query_term::LocatedQueryTermSubset;
 use crate::search::new::SearchContext;
@@ -47,7 +48,7 @@ pub fn build_edges(
     }
 
     conditions.push((
-        (7 + right_ngram_length) as u32,
+        MAX_DISTANCE - 1 + right_ngram_length as u32,
         conditions_interner.insert(ProximityCondition::Term { term: right_term.clone() }),
     ));
 

milli/src/update/index_documents/extract/extract_fid_word_count_docids.rs

@@ -1,6 +1,6 @@
 use std::collections::HashMap;
 use std::fs::File;
-use std::io;
+use std::{cmp, io};
 
 use grenad::Sorter;
 
@@ -54,10 +54,11 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
         }
 
         for position in read_u32_ne_bytes(value) {
-            let (field_id, _) = relative_from_absolute_position(position);
+            let (field_id, position) = relative_from_absolute_position(position);
+            let word_count = position as u32 + 1;
 
             let value = document_fid_wordcount.entry(field_id as FieldId).or_insert(0);
-            *value += 1;
+            *value = cmp::max(*value, word_count);
         }
     }
 
@@ -82,7 +83,7 @@ fn drain_document_fid_wordcount_into_sorter(
     let mut key_buffer = Vec::new();
 
     for (fid, count) in document_fid_wordcount.drain() {
-        if count <= 30 {
+        if count <= 10 {
             key_buffer.clear();
             key_buffer.extend_from_slice(&fid.to_be_bytes());
             key_buffer.push(count as u8);

milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs

@@ -91,7 +91,7 @@ fn document_word_positions_into_sorter(
     while !word_positions_heap.is_empty() {
         while let Some(peeked_word_position) = word_positions_heap.pop() {
             ordered_peeked_word_positions.push(peeked_word_position);
-            if ordered_peeked_word_positions.len() == 7 {
+            if ordered_peeked_word_positions.len() == MAX_DISTANCE as usize - 1 {
                 break;
             }
         }

milli/src/update/mod.rs

@@ -4,8 +4,7 @@ pub use self::delete_documents::{DeleteDocuments, DeletionStrategy, DocumentDele
 pub use self::facet::bulk::FacetsUpdateBulk;
 pub use self::facet::incremental::FacetsUpdateIncrementalInner;
 pub use self::index_documents::{
-    merge_cbo_roaring_bitmaps, merge_roaring_bitmaps, DocumentAdditionResult, DocumentId,
-    IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, MergeFn,
+    DocumentAdditionResult, DocumentId, IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod,
 };
 pub use self::indexer_config::IndexerConfig;
 pub use self::prefix_word_pairs::{