searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 12:27:13 +02:00
Code Issues Releases Wiki Activity

Merge #3942

Browse source 
3942: Normalize for the search the facets values r=ManyTheFish a=Kerollmops

This PR improves and fixes the search for facet values feature. Searching for _bre_ wasn't returning facet values like _brévent_ or _brô_.

The issue was related to the fact that facets are normalized but not in the same way as the `searchableAttributes` are. We decided to normalize them further and add another intermediate database where the key is the normalized facet value, and the value is a set of the non-normalized facets. We then use these non-normalized ones to get the correct counts by fetching the associated databases.

### What's missing in this PR?
 - [x] Apply the change to the whole set of `SearchForFacetValue::execute` conditions.
 - [x] Factorize the code that does an intermediate normalized value fetch in a function.
 - [x] Add or modify the search for facet value test.

Co-authored-by: Clément Renault <clement@meilisearch.com>
Co-authored-by: Kerollmops <clement@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2023-07-25 14:37:17 +00:00 • committed by GitHub
commit be72be7c0d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 279 additions and 94 deletions
Download patch file Download diff file Expand all files Collapse all files

14
milli/src/index.rs
View file

@ -1,5 +1,5 @@
use std::borrow::Cow;
use std::collections::{HashMap, HashSet};
use std::collections::{BTreeSet, HashMap, HashSet};
use std::fs::File;
use std::mem::size_of;
use std::path::Path;
@ -20,7 +20,9 @@ use crate::heed_codec::facet::{
FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
FieldIdCodec, OrderedF64Codec,
};
use crate::heed_codec::{FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
use crate::heed_codec::{
BEU16StrCodec, FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec,
};
use crate::readable_slices::ReadableSlices;
use crate::{
default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
@ -95,6 +97,7 @@ pub mod db_name {
pub const FACET_ID_IS_NULL_DOCIDS: &str = "facet-id-is-null-docids";
pub const FACET_ID_IS_EMPTY_DOCIDS: &str = "facet-id-is-empty-docids";
pub const FACET_ID_STRING_DOCIDS: &str = "facet-id-string-docids";
pub const FACET_ID_NORMALIZED_STRING_STRINGS: &str = "facet-id-normalized-string-strings";
pub const FACET_ID_STRING_FST: &str = "facet-id-string-fst";
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";
@ -156,6 +159,8 @@ pub struct Index {
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.
pub facet_id_string_docids: Database<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>,
/// Maps the facet field id of the normalized-for-search string facets with their original versions.
pub facet_id_normalized_string_strings: Database<BEU16StrCodec, SerdeJson<BTreeSet<String>>>,
/// Maps the facet field id of the string facets with an FST containing all the facets values.
pub facet_id_string_fst: Database<OwnedType<BEU16>, FstSetCodec>,
@ -180,7 +185,7 @@ impl Index {
) -> Result<Index> {
use db_name::*;
options.max_dbs(24);
options.max_dbs(25);
unsafe { options.flag(Flags::MdbAlwaysFreePages) };
let env = options.open(path)?;
@ -210,6 +215,8 @@ impl Index {
let facet_id_f64_docids = env.create_database(&mut wtxn, Some(FACET_ID_F64_DOCIDS))?;
let facet_id_string_docids =
env.create_database(&mut wtxn, Some(FACET_ID_STRING_DOCIDS))?;
let facet_id_normalized_string_strings =
env.create_database(&mut wtxn, Some(FACET_ID_NORMALIZED_STRING_STRINGS))?;
let facet_id_string_fst = env.create_database(&mut wtxn, Some(FACET_ID_STRING_FST))?;
let facet_id_exists_docids =
env.create_database(&mut wtxn, Some(FACET_ID_EXISTS_DOCIDS))?;
@ -245,6 +252,7 @@ impl Index {
field_id_word_count_docids,
facet_id_f64_docids,
facet_id_string_docids,
facet_id_normalized_string_strings,
facet_id_string_fst,
facet_id_exists_docids,
facet_id_is_null_docids,