use std::collections::{BTreeMap, BTreeSet}; use std::marker::PhantomData; use std::num::NonZeroUsize; use fst::IntoStreamer; use milli::update::Setting; use milli::{Index, DEFAULT_VALUES_PER_FACET}; use serde::{Deserialize, Serialize, Serializer}; /// The maximimum number of results that the engine /// will be able to return in one search call. pub const DEFAULT_PAGINATION_MAX_TOTAL_HITS: usize = 1000; fn serialize_with_wildcard( field: &Setting>, s: S, ) -> std::result::Result where S: Serializer, { let wildcard = vec!["*".to_string()]; match field { Setting::Set(value) => Some(value), Setting::Reset => Some(&wildcard), Setting::NotSet => None, } .serialize(s) } #[derive(Clone, Default, Debug, Serialize, PartialEq, Eq)] pub struct Checked; #[derive(Clone, Default, Debug, Serialize, Deserialize, PartialEq, Eq)] pub struct Unchecked; #[cfg_attr(test, derive(proptest_derive::Arbitrary))] #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq)] #[serde(deny_unknown_fields)] #[serde(rename_all = "camelCase")] pub struct MinWordSizeTyposSetting { #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub one_typo: Setting, #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub two_typos: Setting, } #[cfg_attr(test, derive(proptest_derive::Arbitrary))] #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq)] #[serde(deny_unknown_fields)] #[serde(rename_all = "camelCase")] pub struct TypoSettings { #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub enabled: Setting, #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub min_word_size_for_typos: Setting, #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub disable_on_words: Setting>, #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub disable_on_attributes: Setting>, } #[cfg_attr(test, derive(proptest_derive::Arbitrary))] #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq)] #[serde(deny_unknown_fields)] #[serde(rename_all = "camelCase")] pub struct FacetingSettings { #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub max_values_per_facet: Setting, } #[cfg_attr(test, derive(proptest_derive::Arbitrary))] #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq)] #[serde(deny_unknown_fields)] #[serde(rename_all = "camelCase")] pub struct PaginationSettings { #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] #[serde(default, skip_serializing_if = "Setting::is_not_set")] pub max_total_hits: Setting, } /// Holds all the settings for an index. `T` can either be `Checked` if they represents settings /// whose validity is guaranteed, or `Unchecked` if they need to be validated. In the later case, a /// call to `check` will return a `Settings` from a `Settings`. #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq)] #[serde(deny_unknown_fields)] #[serde(rename_all = "camelCase")] #[serde(bound(serialize = "T: Serialize", deserialize = "T: Deserialize<'static>"))] #[cfg_attr(test, derive(proptest_derive::Arbitrary))] pub struct Settings { #[serde( default, serialize_with = "serialize_with_wildcard", skip_serializing_if = "Setting::is_not_set" )] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub displayed_attributes: Setting>, #[serde( default, serialize_with = "serialize_with_wildcard", skip_serializing_if = "Setting::is_not_set" )] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub searchable_attributes: Setting>, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub filterable_attributes: Setting>, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub sortable_attributes: Setting>, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub ranking_rules: Setting>, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub stop_words: Setting>, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub synonyms: Setting>>, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub distinct_attribute: Setting, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub typo_tolerance: Setting, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub faceting: Setting, #[serde(default, skip_serializing_if = "Setting::is_not_set")] #[cfg_attr(test, proptest(strategy = "test::setting_strategy()"))] pub pagination: Setting, #[serde(skip)] pub _kind: PhantomData, } impl Settings { pub fn cleared() -> Settings { Settings { displayed_attributes: Setting::Reset, searchable_attributes: Setting::Reset, filterable_attributes: Setting::Reset, sortable_attributes: Setting::Reset, ranking_rules: Setting::Reset, stop_words: Setting::Reset, synonyms: Setting::Reset, distinct_attribute: Setting::Reset, typo_tolerance: Setting::Reset, faceting: Setting::Reset, pagination: Setting::Reset, _kind: PhantomData, } } pub fn into_unchecked(self) -> Settings { let Self { displayed_attributes, searchable_attributes, filterable_attributes, sortable_attributes, ranking_rules, stop_words, synonyms, distinct_attribute, typo_tolerance, faceting, pagination, .. } = self; Settings { displayed_attributes, searchable_attributes, filterable_attributes, sortable_attributes, ranking_rules, stop_words, synonyms, distinct_attribute, typo_tolerance, faceting, pagination, _kind: PhantomData, } } } impl Settings { pub fn check(self) -> Settings { let displayed_attributes = match self.displayed_attributes { Setting::Set(fields) => { if fields.iter().any(|f| f == "*") { Setting::Reset } else { Setting::Set(fields) } } otherwise => otherwise, }; let searchable_attributes = match self.searchable_attributes { Setting::Set(fields) => { if fields.iter().any(|f| f == "*") { Setting::Reset } else { Setting::Set(fields) } } otherwise => otherwise, }; Settings { displayed_attributes, searchable_attributes, filterable_attributes: self.filterable_attributes, sortable_attributes: self.sortable_attributes, ranking_rules: self.ranking_rules, stop_words: self.stop_words, synonyms: self.synonyms, distinct_attribute: self.distinct_attribute, typo_tolerance: self.typo_tolerance, faceting: self.faceting, pagination: self.pagination, _kind: PhantomData, } } } #[derive(Debug, Clone, Serialize, Deserialize)] #[serde(deny_unknown_fields)] #[serde(rename_all = "camelCase")] pub struct Facets { pub level_group_size: Option, pub min_level_size: Option, } pub fn apply_settings_to_builder( settings: &Settings, builder: &mut milli::update::Settings, ) { match settings.searchable_attributes { Setting::Set(ref names) => builder.set_searchable_fields(names.clone()), Setting::Reset => builder.reset_searchable_fields(), Setting::NotSet => (), } match settings.displayed_attributes { Setting::Set(ref names) => builder.set_displayed_fields(names.clone()), Setting::Reset => builder.reset_displayed_fields(), Setting::NotSet => (), } match settings.filterable_attributes { Setting::Set(ref facets) => { builder.set_filterable_fields(facets.clone().into_iter().collect()) } Setting::Reset => builder.reset_filterable_fields(), Setting::NotSet => (), } match settings.sortable_attributes { Setting::Set(ref fields) => builder.set_sortable_fields(fields.iter().cloned().collect()), Setting::Reset => builder.reset_sortable_fields(), Setting::NotSet => (), } match settings.ranking_rules { Setting::Set(ref criteria) => builder.set_criteria(criteria.clone()), Setting::Reset => builder.reset_criteria(), Setting::NotSet => (), } match settings.stop_words { Setting::Set(ref stop_words) => builder.set_stop_words(stop_words.clone()), Setting::Reset => builder.reset_stop_words(), Setting::NotSet => (), } match settings.synonyms { Setting::Set(ref synonyms) => builder.set_synonyms(synonyms.clone().into_iter().collect()), Setting::Reset => builder.reset_synonyms(), Setting::NotSet => (), } match settings.distinct_attribute { Setting::Set(ref attr) => builder.set_distinct_field(attr.clone()), Setting::Reset => builder.reset_distinct_field(), Setting::NotSet => (), } match settings.typo_tolerance { Setting::Set(ref value) => { match value.enabled { Setting::Set(val) => builder.set_autorize_typos(val), Setting::Reset => builder.reset_authorize_typos(), Setting::NotSet => (), } match value.min_word_size_for_typos { Setting::Set(ref setting) => { match setting.one_typo { Setting::Set(val) => builder.set_min_word_len_one_typo(val), Setting::Reset => builder.reset_min_word_len_one_typo(), Setting::NotSet => (), } match setting.two_typos { Setting::Set(val) => builder.set_min_word_len_two_typos(val), Setting::Reset => builder.reset_min_word_len_two_typos(), Setting::NotSet => (), } } Setting::Reset => { builder.reset_min_word_len_one_typo(); builder.reset_min_word_len_two_typos(); } Setting::NotSet => (), } match value.disable_on_words { Setting::Set(ref words) => { builder.set_exact_words(words.clone()); } Setting::Reset => builder.reset_exact_words(), Setting::NotSet => (), } match value.disable_on_attributes { Setting::Set(ref words) => { builder.set_exact_attributes(words.iter().cloned().collect()) } Setting::Reset => builder.reset_exact_attributes(), Setting::NotSet => (), } } Setting::Reset => { // all typo settings need to be reset here. builder.reset_authorize_typos(); builder.reset_min_word_len_one_typo(); builder.reset_min_word_len_two_typos(); builder.reset_exact_words(); builder.reset_exact_attributes(); } Setting::NotSet => (), } match settings.faceting { Setting::Set(ref value) => match value.max_values_per_facet { Setting::Set(val) => builder.set_max_values_per_facet(val), Setting::Reset => builder.reset_max_values_per_facet(), Setting::NotSet => (), }, Setting::Reset => builder.reset_max_values_per_facet(), Setting::NotSet => (), } match settings.pagination { Setting::Set(ref value) => match value.max_total_hits { Setting::Set(val) => builder.set_pagination_max_total_hits(val), Setting::Reset => builder.reset_pagination_max_total_hits(), Setting::NotSet => (), }, Setting::Reset => builder.reset_pagination_max_total_hits(), Setting::NotSet => (), } } pub fn settings( index: &Index, rtxn: &crate::heed::RoTxn, ) -> Result, milli::Error> { let displayed_attributes = index.displayed_fields(rtxn)?.map(|fields| fields.into_iter().map(String::from).collect()); let searchable_attributes = index .user_defined_searchable_fields(rtxn)? .map(|fields| fields.into_iter().map(String::from).collect()); let filterable_attributes = index.filterable_fields(rtxn)?.into_iter().collect(); let sortable_attributes = index.sortable_fields(rtxn)?.into_iter().collect(); let criteria = index.criteria(rtxn)?.into_iter().map(|c| c.to_string()).collect(); let stop_words = index .stop_words(rtxn)? .map(|stop_words| -> Result, milli::Error> { Ok(stop_words.stream().into_strs()?.into_iter().collect()) }) .transpose()? .unwrap_or_default(); let distinct_field = index.distinct_field(rtxn)?.map(String::from); // in milli each word in the synonyms map were split on their separator. Since we lost // this information we are going to put space between words. let synonyms = index .synonyms(rtxn)? .iter() .map(|(key, values)| (key.join(" "), values.iter().map(|value| value.join(" ")).collect())) .collect(); let min_typo_word_len = MinWordSizeTyposSetting { one_typo: Setting::Set(index.min_word_len_one_typo(rtxn)?), two_typos: Setting::Set(index.min_word_len_two_typos(rtxn)?), }; let disabled_words = match index.exact_words(rtxn)? { Some(fst) => fst.into_stream().into_strs()?.into_iter().collect(), None => BTreeSet::new(), }; let disabled_attributes = index.exact_attributes(rtxn)?.into_iter().map(String::from).collect(); let typo_tolerance = TypoSettings { enabled: Setting::Set(index.authorize_typos(rtxn)?), min_word_size_for_typos: Setting::Set(min_typo_word_len), disable_on_words: Setting::Set(disabled_words), disable_on_attributes: Setting::Set(disabled_attributes), }; let faceting = FacetingSettings { max_values_per_facet: Setting::Set( index.max_values_per_facet(rtxn)?.unwrap_or(DEFAULT_VALUES_PER_FACET), ), }; let pagination = PaginationSettings { max_total_hits: Setting::Set( index.pagination_max_total_hits(rtxn)?.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS), ), }; Ok(Settings { displayed_attributes: match displayed_attributes { Some(attrs) => Setting::Set(attrs), None => Setting::Reset, }, searchable_attributes: match searchable_attributes { Some(attrs) => Setting::Set(attrs), None => Setting::Reset, }, filterable_attributes: Setting::Set(filterable_attributes), sortable_attributes: Setting::Set(sortable_attributes), ranking_rules: Setting::Set(criteria), stop_words: Setting::Set(stop_words), distinct_attribute: match distinct_field { Some(field) => Setting::Set(field), None => Setting::Reset, }, synonyms: Setting::Set(synonyms), typo_tolerance: Setting::Set(typo_tolerance), faceting: Setting::Set(faceting), pagination: Setting::Set(pagination), _kind: PhantomData, }) } #[cfg(test)] pub(crate) mod test { use proptest::prelude::*; use super::*; pub(super) fn setting_strategy() -> impl Strategy> { prop_oneof![Just(Setting::NotSet), Just(Setting::Reset), any::().prop_map(Setting::Set)] } #[test] fn test_setting_check() { // test no changes let settings = Settings { displayed_attributes: Setting::Set(vec![String::from("hello")]), searchable_attributes: Setting::Set(vec![String::from("hello")]), filterable_attributes: Setting::NotSet, sortable_attributes: Setting::NotSet, ranking_rules: Setting::NotSet, stop_words: Setting::NotSet, synonyms: Setting::NotSet, distinct_attribute: Setting::NotSet, typo_tolerance: Setting::NotSet, faceting: Setting::NotSet, pagination: Setting::NotSet, _kind: PhantomData::, }; let checked = settings.clone().check(); assert_eq!(settings.displayed_attributes, checked.displayed_attributes); assert_eq!(settings.searchable_attributes, checked.searchable_attributes); // test wildcard // test no changes let settings = Settings { displayed_attributes: Setting::Set(vec![String::from("*")]), searchable_attributes: Setting::Set(vec![String::from("hello"), String::from("*")]), filterable_attributes: Setting::NotSet, sortable_attributes: Setting::NotSet, ranking_rules: Setting::NotSet, stop_words: Setting::NotSet, synonyms: Setting::NotSet, distinct_attribute: Setting::NotSet, typo_tolerance: Setting::NotSet, faceting: Setting::NotSet, pagination: Setting::NotSet, _kind: PhantomData::, }; let checked = settings.check(); assert_eq!(checked.displayed_attributes, Setting::Reset); assert_eq!(checked.searchable_attributes, Setting::Reset); } }