searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-12-26 14:40:05 +01:00
Code Issues Releases Wiki Activity

Decide to use prefix DB if the word is not an ngram

Browse Source
This commit is contained in:
Louis Dureuil 2023-04-12 15:14:00 +02:00 committed by Loïc Lecrenier
parent 7a01f20df7
commit 38b7b31beb
2 changed files with 23 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
milli/src/search/new/query_term/compute_derivations.rs
View File

@ -177,6 +177,7 @@ pub fn partially_initialized_term_from_word(
word: &str,
max_typo: u8,
is_prefix: bool,
is_ngram: bool,
) -> Result<QueryTerm> {
let word_interned = ctx.word_interner.insert(word.to_owned());
@ -197,12 +198,19 @@ pub fn partially_initialized_term_from_word(
let fst = ctx.index.words_fst(ctx.txn)?;
let use_prefix_db = is_prefix
&& ctx
&& (ctx
.index
.word_prefix_docids
.remap_data_type::<DecodeIgnore>()
.get(ctx.txn, word)?
.is_some();
.is_some()
|| (!is_ngram
&& ctx
.index
.exact_word_prefix_docids
.remap_data_type::<DecodeIgnore>()
.get(ctx.txn, word)?
.is_some()));
let use_prefix_db = if use_prefix_db { Some(word_interned) } else { None };
let mut zero_typo = None;

19
milli/src/search/new/query_term/parse_query.rs
View File

@ -1,8 +1,8 @@
use charabia::{normalizer::NormalizedTokenIter, SeparatorKind, TokenKind};
use crate::{Result, SearchContext, MAX_WORD_LENGTH};
use charabia::normalizer::NormalizedTokenIter;
use charabia::{SeparatorKind, TokenKind};
use super::*;
use crate::{Result, SearchContext, MAX_WORD_LENGTH};
/// Convert the tokenised search query into a list of located query terms.
// TODO: checking if the positions are correct for phrases, separators, ngrams
@ -51,6 +51,7 @@ pub fn located_query_terms_from_string(
word,
nbr_typos(word),
false,
false,
)?;
let located_term = LocatedQueryTerm {
value: ctx.term_interner.push(term),
@ -62,8 +63,13 @@ pub fn located_query_terms_from_string(
}
} else {
let word = token.lemma();
let term =
partially_initialized_term_from_word(ctx, word, nbr_typos(word), true)?;
let term = partially_initialized_term_from_word(
ctx,
word,
nbr_typos(word),
true,
false,
)?;
let located_term = LocatedQueryTerm {
value: ctx.term_interner.push(term),
positions: position..=position,
@ -195,7 +201,8 @@ pub fn make_ngram(
let max_nbr_typos =
number_of_typos_allowed(ngram_str.as_str()).saturating_sub(terms.len() as u8 - 1);
let mut term = partially_initialized_term_from_word(ctx, &ngram_str, max_nbr_typos, is_prefix)?;
let mut term =
partially_initialized_term_from_word(ctx, &ngram_str, max_nbr_typos, is_prefix, true)?;
// Now add the synonyms
let index_synonyms = ctx.index.synonyms(ctx.txn)?;