Plug the faceting.max_values_per_facet setting

This commit is contained in:
Kerollmops 2022-06-08 18:03:56 +02:00
parent 5450b5ced3
commit b96399d24b
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4
6 changed files with 45 additions and 20 deletions

View File

@ -285,7 +285,7 @@ make_setting_route!(
make_setting_route!(
"/faceting",
patch,
meilisearch_lib::index::updates::TypoSettings,
meilisearch_lib::index::updates::FacetingSettings,
faceting,
"faceting",
analytics,
@ -296,13 +296,7 @@ make_setting_route!(
"Faceting Updated".to_string(),
json!({
"faceting": {
"max_values_per_facet": setting
.as_ref()
.and_then(|s| s.max_values_per_facet
.as_ref()
.set()
.map(|s| s.one_typo.set()))
.flatten(),
"max_values_per_facet": setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
},
}),
Some(req),

View File

@ -61,7 +61,7 @@ async fn import_dump_v2_movie_raw() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }})
json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -125,7 +125,7 @@ async fn import_dump_v2_movie_with_settings() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }})
json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -189,7 +189,7 @@ async fn import_dump_v2_rubygems_with_settings() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }})
json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }})
);
let (tasks, code) = index.list_tasks().await;
@ -253,7 +253,7 @@ async fn import_dump_v3_movie_raw() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }})
json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -317,7 +317,7 @@ async fn import_dump_v3_movie_with_settings() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }})
json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -381,7 +381,7 @@ async fn import_dump_v3_rubygems_with_settings() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }})
json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -445,7 +445,7 @@ async fn import_dump_v4_movie_raw() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({ "displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }})
json!({ "displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -509,7 +509,7 @@ async fn import_dump_v4_movie_with_settings() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }})
json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;
@ -573,7 +573,7 @@ async fn import_dump_v4_rubygems_with_settings() {
assert_eq!(code, 200);
assert_eq!(
settings,
json!({ "displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }})
json!({ "displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 } })
);
let (tasks, code) = index.list_tasks().await;

View File

@ -24,6 +24,12 @@ static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|
);
map.insert("stop_words", json!([]));
map.insert("synonyms", json!({}));
map.insert(
"faceting",
json!({
"maxValuesByFacet": json!(100),
}),
);
map
});
@ -43,7 +49,7 @@ async fn get_settings() {
let (response, code) = index.settings().await;
assert_eq!(code, 200);
let settings = response.as_object().unwrap();
assert_eq!(settings.keys().len(), 9);
assert_eq!(settings.keys().len(), 10);
assert_eq!(settings["displayedAttributes"], json!(["*"]));
assert_eq!(settings["searchableAttributes"], json!(["*"]));
assert_eq!(settings["filterableAttributes"], json!([]));
@ -61,6 +67,12 @@ async fn get_settings() {
])
);
assert_eq!(settings["stopWords"], json!([]));
assert_eq!(
settings["faceting"],
json!({
"maxValuesPerFacet": 100
})
);
}
#[actix_rt::test]

View File

@ -8,7 +8,7 @@ use std::sync::Arc;
use fst::IntoStreamer;
use milli::heed::{EnvOpenOptions, RoTxn};
use milli::update::{IndexerConfig, Setting};
use milli::{obkv_to_json, FieldDistribution};
use milli::{obkv_to_json, FieldDistribution, DEFAULT_VALUES_PER_FACET};
use serde::{Deserialize, Serialize};
use serde_json::{Map, Value};
use time::OffsetDateTime;
@ -18,7 +18,7 @@ use crate::EnvSizer;
use super::error::IndexError;
use super::error::Result;
use super::updates::{MinWordSizeTyposSetting, TypoSettings};
use super::updates::{FacetingSettings, MinWordSizeTyposSetting, TypoSettings};
use super::{Checked, Settings};
pub type Document = Map<String, Value>;
@ -193,6 +193,15 @@ impl Index {
disable_on_attributes: Setting::Set(disabled_attributes),
};
let faceting = FacetingSettings {
max_values_per_facet: Setting::Set(
self.max_values_per_facet(txn)?
.unwrap_or(DEFAULT_VALUES_PER_FACET),
),
};
dbg!(&faceting);
Ok(Settings {
displayed_attributes: match displayed_attributes {
Some(attrs) => Setting::Set(attrs),
@ -212,6 +221,7 @@ impl Index {
},
synonyms: Setting::Set(synonyms),
typo_tolerance: Setting::Set(typo_tolerance),
faceting: Setting::Set(faceting),
_kind: PhantomData,
})
}

View File

@ -7,6 +7,7 @@ use either::Either;
use milli::tokenizer::TokenizerBuilder;
use milli::{
AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, MatchBounds, MatcherBuilder, SortError,
DEFAULT_VALUES_PER_FACET,
};
use regex::Regex;
use serde::{Deserialize, Serialize};
@ -223,6 +224,12 @@ impl Index {
let facet_distribution = match query.facets {
Some(ref fields) => {
let mut facet_distribution = self.facets_distribution(&rtxn);
let max_values_by_facet = self
.max_values_per_facet(&rtxn)?
.unwrap_or(DEFAULT_VALUES_PER_FACET);
facet_distribution.max_values_per_facet(max_values_by_facet);
if fields.iter().all(|f| f != "*") {
facet_distribution.facets(fields);
}

View File

@ -484,6 +484,7 @@ pub(crate) mod test {
synonyms: Setting::NotSet,
distinct_attribute: Setting::NotSet,
typo_tolerance: Setting::NotSet,
faceting: Setting::NotSet,
_kind: PhantomData::<Unchecked>,
};
@ -506,6 +507,7 @@ pub(crate) mod test {
synonyms: Setting::NotSet,
distinct_attribute: Setting::NotSet,
typo_tolerance: Setting::NotSet,
faceting: Setting::NotSet,
_kind: PhantomData::<Unchecked>,
};