searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 04:17:10 +02:00
Code Issues Releases Wiki Activity

fix synonyms normalization

Browse source 
Synonyms needs to be indexed in ascendant order,
and the new normalization step for synonyms potentially changes this order
which break the indexation process
because "Harry Potter" > "HP"  but "harry potter" < "hp"
This commit is contained in:
many 2021-02-03 15:05:15 +01:00
parent 69c91d2b56
commit 1df0fdf3e2
No known key found for this signature in database
GPG key ID: 2CEF23B75189EACA
2 changed files with 15 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

15
meilisearch-core/src/update/settings_update.rs
View file

@ -1,7 +1,7 @@
use std::{borrow::Cow, collections::{BTreeMap, BTreeSet}};
use heed::Result as ZResult;
use fst::{set::OpBuilder, SetBuilder};
use fst::{SetBuilder, set::OpBuilder};
use sdset::SetBuf;
use meilisearch_schema::Schema;
use meilisearch_tokenizer::analyzer::{Analyzer, AnalyzerConfig};
@ -298,16 +298,23 @@ pub fn apply_synonyms_update(
.tokens()
.fold(String::new(), |s, t| s + t.text())
}
// normalize synonyms and reorder them creating a BTreeMap
let synonyms: BTreeMap<String, Vec<String>> = synonyms.into_iter().map( |(word, alternatives)| {
let word = normalize(&analyzer, &word);
let alternatives = alternatives.into_iter().map(|text| normalize(&analyzer, &text)).collect();
(word, alternatives)
}).collect();
// index synonyms,
// synyonyms have to be ordered by key before indexation
let mut synonyms_builder = SetBuilder::memory();
synonyms_store.clear(writer)?;
for (word, alternatives) in synonyms {
let word = normalize(&analyzer, &word);
synonyms_builder.insert(&word)?;
let alternatives = {
let alternatives = alternatives.iter().map(|text| normalize(&analyzer, &text)).collect();
let alternatives = SetBuf::from_dirty(alternatives);
let mut alternatives_builder = SetBuilder::memory();
alternatives_builder.extend_iter(alternatives)?;