Limit the number of values returned by the facet search

This commit is contained in:
Clément Renault 2024-01-10 16:34:40 +01:00
parent 93363b0201
commit 3f3462ab62
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
3 changed files with 38 additions and 5 deletions

View File

@ -735,6 +735,9 @@ pub fn perform_facet_search(
if let Some(facet_query) = &facet_query { if let Some(facet_query) = &facet_query {
facet_search.query(facet_query); facet_search.query(facet_query);
} }
if let Some(max_facets) = index.max_values_per_facet(&rtxn)? {
facet_search.max_values(max_facets as usize);
}
Ok(FacetSearchResult { Ok(FacetSearchResult {
facet_hits: facet_search.execute()?, facet_hits: facet_search.execute()?,

View File

@ -105,6 +105,24 @@ async fn more_advanced_facet_search() {
snapshot!(response["facetHits"].as_array().unwrap().len(), @"1"); snapshot!(response["facetHits"].as_array().unwrap().len(), @"1");
} }
#[actix_rt::test]
async fn simple_facet_search_with_max_values() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.update_settings_faceting(json!({ "maxValuesPerFacet": 1 })).await;
index.update_settings_filterable_attributes(json!(["genres"])).await;
index.add_documents(documents, None).await;
index.wait_task(2).await;
let (response, code) =
index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
assert_eq!(code, 200, "{}", response);
assert_eq!(dbg!(response)["facetHits"].as_array().unwrap().len(), 1);
}
#[actix_rt::test] #[actix_rt::test]
async fn non_filterable_facet_search_error() { async fn non_filterable_facet_search_error() {
let server = Server::new().await; let server = Server::new().await;

View File

@ -27,8 +27,8 @@ static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true));
static LEVDIST1: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(1, true)); static LEVDIST1: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(1, true));
static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true)); static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true));
/// The maximum number of facets returned by the facet search route. /// The maximum number of values per facet returned by the facet search route.
const MAX_NUMBER_OF_FACETS: usize = 100; const DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET: usize = 100;
pub mod facet; pub mod facet;
mod fst_utils; mod fst_utils;
@ -306,6 +306,7 @@ pub struct SearchForFacetValues<'a> {
query: Option<String>, query: Option<String>,
facet: String, facet: String,
search_query: Search<'a>, search_query: Search<'a>,
max_values: usize,
is_hybrid: bool, is_hybrid: bool,
} }
@ -315,7 +316,13 @@ impl<'a> SearchForFacetValues<'a> {
search_query: Search<'a>, search_query: Search<'a>,
is_hybrid: bool, is_hybrid: bool,
) -> SearchForFacetValues<'a> { ) -> SearchForFacetValues<'a> {
SearchForFacetValues { query: None, facet, search_query, is_hybrid } SearchForFacetValues {
query: None,
facet,
search_query,
max_values: DEFAULT_MAX_NUMBER_OF_VALUES_PER_FACET,
is_hybrid,
}
} }
pub fn query(&mut self, query: impl Into<String>) -> &mut Self { pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
@ -323,6 +330,11 @@ impl<'a> SearchForFacetValues<'a> {
self self
} }
pub fn max_values(&mut self, max: usize) -> &mut Self {
self.max_values = max;
self
}
fn one_original_value_of( fn one_original_value_of(
&self, &self,
field_id: FieldId, field_id: FieldId,
@ -462,7 +474,7 @@ impl<'a> SearchForFacetValues<'a> {
.unwrap_or_else(|| left_bound.to_string()); .unwrap_or_else(|| left_bound.to_string());
results.push(FacetValueHit { value, count }); results.push(FacetValueHit { value, count });
} }
if results.len() >= MAX_NUMBER_OF_FACETS { if results.len() >= self.max_values {
break; break;
} }
} }
@ -507,7 +519,7 @@ impl<'a> SearchForFacetValues<'a> {
.unwrap_or_else(|| query.to_string()); .unwrap_or_else(|| query.to_string());
results.push(FacetValueHit { value, count }); results.push(FacetValueHit { value, count });
} }
if results.len() >= MAX_NUMBER_OF_FACETS { if results.len() >= self.max_values {
return Ok(ControlFlow::Break(())); return Ok(ControlFlow::Break(()));
} }
} }