snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-10-31 16:06:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Separate calc_byte_length function

Browse Source
This commit is contained in:
HikariLan
2025-03-25 00:47:17 +08:00
parent debd2b21b8
commit 2800e42243
1 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
crates/milli/src/search/new/matches/mod.rs
View File

@@ -8,6 +8,7 @@ use std::cmp::{max, min};
use charabia::{Language, SeparatorKind, Token, Tokenizer};
use either::Either;
use itertools::Itertools;
pub use matching_words::MatchingWords;
use matching_words::{MatchType, PartialMatch};
use r#match::{Match, MatchPosition};
@@ -229,12 +230,7 @@ impl<'t, 'tokenizer> Matcher<'t, 'tokenizer, '_, '_> {
.iter()
.map(|m| MatchBounds {
start: tokens[m.get_first_token_pos()].byte_start,
length: (m.get_first_token_pos()..m.get_last_token_pos() + 1)
.map(|i| tokens[i].clone())
.flat_map(|token| token.char_map.clone().unwrap_or(vec![(1, 1); token.char_end - token.char_start] /* Some token doesn't have a char map, here we treat them as single byte chars. */))
.map(|(original, _)| original as usize)
.take(m.char_count)
.sum(),
length: self.calc_byte_length(&tokens, m),
indices: if array_indices.is_empty() {
None
} else {
@@ -245,6 +241,18 @@ impl<'t, 'tokenizer> Matcher<'t, 'tokenizer, '_, '_> {
}
}
fn calc_byte_length(&self, tokens: &Vec<Token<'t>>, m: &Match) -> usize {
(m.get_first_token_pos()..=m.get_last_token_pos())
.flat_map(|i| match &tokens[i].char_map {
Some(char_map) => {
char_map.iter().map(|(original, _)| *original as usize).collect_vec()
}
None => tokens[i].lemma().chars().map(|c| c.len_utf8()).collect_vec(),
})
.take(m.char_count)
.sum()
}
/// Returns the bounds in byte index of the crop window.
fn crop_bounds(&self, tokens: &[Token<'_>], matches: &[Match], crop_size: usize) -> [usize; 2] {
let (