snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-23 02:27:40 +08:00
Code Issues Actions 8 Packages Projects Releases Wiki Activity

Avoid splitting ngrams into their original component words

Browse Source
This commit is contained in:
Loïc Lecrenier 2023-04-06 15:50:11 +02:00
parent f7d90ad19f
commit d6585eb10b
1 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -293,9 +293,26 @@ impl Interned<QueryTerm> {
})?;
let original_str = ctx.word_interner.get(original).to_owned();
let split_words = find_split_words(ctx, original_str.as_str())?;
let one_typo = OneTypoTerm { split_words, one_typo: one_typo_words };
let self_mut = ctx.term_interner.get_mut(self);
// Only add the split words to the derivations if:
// 1. the term is not an ngram; OR
// 2. the term is an ngram, but the split words are different from the ngram's component words
let split_words = if let Some((ngram_words, split_words)) =
self_mut.ngram_words.as_ref().zip(split_words.as_ref())
{
let Phrase { words } = ctx.phrase_interner.get(*split_words);
if ngram_words.iter().ne(words.iter().flatten()) {
Some(*split_words)
} else {
None
}
} else {
split_words
};
let one_typo = OneTypoTerm { split_words, one_typo: one_typo_words };
self_mut.one_typo = Lazy::Init(one_typo);
Ok(())