snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-23 10:37:41 +08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Patch prefix match

Browse Source
This commit is contained in:
ManyTheFish 2023-04-06 17:22:31 +02:00
parent ba8dcc2d78
commit f7e7f438f8
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
milli/src/search/new/matches/matching_words.rs
View File

@ -20,6 +20,7 @@ pub struct LocatedMatchingWords {
pub value: Vec<Interned<String>>, pub value: Vec<Interned<String>>,
pub positions: RangeInclusive<WordId>, pub positions: RangeInclusive<WordId>,
pub is_prefix: bool, pub is_prefix: bool,
pub original_char_count: usize,
} }
/// Structure created from a query tree /// Structure created from a query tree
@ -101,10 +102,12 @@ impl MatchingWords {
positions: located_term.positions.clone(), positions: located_term.positions.clone(),
}); });
} }
words.push(LocatedMatchingWords { words.push(LocatedMatchingWords {
value: matching_words, value: matching_words,
positions: located_term.positions.clone(), positions: located_term.positions.clone(),
is_prefix: term.is_prefix, is_prefix: term.is_prefix,
original_char_count: ctx.word_interner.get(term.original).chars().count(),
}); });
} }
@ -131,7 +134,11 @@ impl MatchingWords {
let word = self.word_interner.get(*word); let word = self.word_interner.get(*word);
// if the word is a prefix we match using starts_with. // if the word is a prefix we match using starts_with.
if located_words.is_prefix && token.lemma().starts_with(word) { if located_words.is_prefix && token.lemma().starts_with(word) {
let char_len = token.original_lengths(word.len()).0; let Some((char_index, c)) = word.char_indices().take(located_words.original_char_count).last() else {
continue;
};
let prefix_length = char_index + c.len_utf8();
let char_len = token.original_lengths(prefix_length).0;
let ids = &located_words.positions; let ids = &located_words.positions;
return Some(MatchType::Full { char_len, ids }); return Some(MatchType::Full { char_len, ids });
// else we exact match the token. // else we exact match the token.