searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-26 23:04:26 +01:00
Code Issues Releases Wiki Activity

Implement the previous way for the exhaustive distinct candidates

Browse Source
This commit is contained in:
Clément Renault 2023-03-30 16:10:10 +02:00 committed by Loïc Lecrenier
parent 55fbfb6124
commit 0d2e7bcc13
2 changed files with 21 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
milli/src/search/mod.rs
View File

@ -1,3 +1,9 @@
use std::fmt;
use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
use once_cell::sync::Lazy;
use roaring::bitmap::RoaringBitmap;
pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET}; pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET};
pub use self::matches::{ pub use self::matches::{
FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWord, MatchingWords, FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWord, MatchingWords,
@ -5,10 +11,6 @@ pub use self::matches::{
use crate::{ use crate::{
execute_search, AscDesc, DefaultSearchLogger, DocumentId, Index, Result, SearchContext, execute_search, AscDesc, DefaultSearchLogger, DocumentId, Index, Result, SearchContext,
}; };
use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
use once_cell::sync::Lazy;
use roaring::bitmap::RoaringBitmap;
use std::fmt;
// Building these factories is not free. // Building these factories is not free.
static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true)); static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true));
@ -112,6 +114,7 @@ impl<'a> Search<'a> {
&mut ctx, &mut ctx,
&self.query, &self.query,
self.terms_matching_strategy, self.terms_matching_strategy,
self.exhaustive_number_hits,
&self.filter, &self.filter,
&self.sort_criteria, &self.sort_criteria,
self.offset, self.offset,

16
milli/src/search/new/mod.rs
View File

@ -37,6 +37,7 @@ use self::interner::Interner;
use self::ranking_rules::{BoxRankingRule, RankingRule}; use self::ranking_rules::{BoxRankingRule, RankingRule};
use self::resolve_query_graph::compute_query_graph_docids; use self::resolve_query_graph::compute_query_graph_docids;
use self::sort::Sort; use self::sort::Sort;
use crate::search::new::distinct::{apply_distinct_rule, DistinctOutput};
use crate::{ use crate::{
AscDesc, Filter, Index, MatchingWords, Member, Result, SearchResult, TermsMatchingStrategy, AscDesc, Filter, Index, MatchingWords, Member, Result, SearchResult, TermsMatchingStrategy,
UserError, UserError,
@ -272,6 +273,7 @@ pub fn execute_search(
ctx: &mut SearchContext, ctx: &mut SearchContext,
query: &Option<String>, query: &Option<String>,
terms_matching_strategy: TermsMatchingStrategy, terms_matching_strategy: TermsMatchingStrategy,
exhaustive_number_hits: bool,
filters: &Option<Filter>, filters: &Option<Filter>,
sort_criteria: &Option<Vec<AscDesc>>, sort_criteria: &Option<Vec<AscDesc>>,
from: usize, from: usize,
@ -333,11 +335,21 @@ pub fn execute_search(
)? )?
}; };
// The candidates is the universe unless the exhaustive number of hits
// is requested and a distinct attribute is set.
let mut candidates = universe;
if exhaustive_number_hits {
if let Some(f) = ctx.index.distinct_field(ctx.txn)? {
if let Some(distinct_fid) = ctx.index.fields_ids_map(ctx.txn)?.id(f) {
candidates = apply_distinct_rule(ctx, distinct_fid, &candidates)?.remaining;
}
}
}
Ok(SearchResult { Ok(SearchResult {
// TODO: correct matching words // TODO: correct matching words
matching_words: MatchingWords::default(), matching_words: MatchingWords::default(),
// TODO: candidates with distinct candidates,
candidates: universe,
documents_ids, documents_ids,
}) })
} }