snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-25 19:45:05 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Prefer using Rc<str> than String when cloning a lot

Browse Source
This commit is contained in:
Clément Renault 2024-09-16 15:41:29 +02:00
parent 1a0e962299
commit f4ab1f168e
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
milli/src/update/new/extract/searchable/extract_word_pair_proximity_docids.rs
View File

@ -1,4 +1,5 @@
use std::collections::{HashMap, VecDeque}; use std::collections::{HashMap, VecDeque};
use std::rc::Rc;
use heed::RoTxn; use heed::RoTxn;
use itertools::merge_join_by; use itertools::merge_join_by;
@ -38,7 +39,7 @@ impl SearchableExtractor for WordPairProximityDocidsExtractor {
let mut key_buffer = Vec::new(); let mut key_buffer = Vec::new();
let mut del_word_pair_proximity = Vec::new(); let mut del_word_pair_proximity = Vec::new();
let mut add_word_pair_proximity = Vec::new(); let mut add_word_pair_proximity = Vec::new();
let mut word_positions: VecDeque<(String, u16)> = let mut word_positions: VecDeque<(Rc<str>, u16)> =
VecDeque::with_capacity(MAX_DISTANCE as usize); VecDeque::with_capacity(MAX_DISTANCE as usize);
let docid = document_change.docid(); let docid = document_change.docid();
@ -118,8 +119,8 @@ fn build_key<'a>(prox: u8, w1: &str, w2: &str, key_buffer: &'a mut Vec<u8>) -> &
} }
fn word_positions_into_word_pair_proximity( fn word_positions_into_word_pair_proximity(
word_positions: &mut VecDeque<(String, u16)>, word_positions: &mut VecDeque<(Rc<str>, u16)>,
word_pair_proximity: &mut impl FnMut((String, String), u8), word_pair_proximity: &mut impl FnMut((Rc<str>, Rc<str>), u8),
) -> Result<()> { ) -> Result<()> {
let (head_word, head_position) = word_positions.pop_front().unwrap(); let (head_word, head_position) = word_positions.pop_front().unwrap();
for (word, position) in word_positions.iter() { for (word, position) in word_positions.iter() {
@ -135,8 +136,8 @@ fn process_document_tokens(
document: &KvReader<FieldId>, document: &KvReader<FieldId>,
document_tokenizer: &DocumentTokenizer, document_tokenizer: &DocumentTokenizer,
fields_ids_map: &mut GlobalFieldsIdsMap, fields_ids_map: &mut GlobalFieldsIdsMap,
word_positions: &mut VecDeque<(String, u16)>, word_positions: &mut VecDeque<(Rc<str>, u16)>,
word_pair_proximity: &mut impl FnMut((String, String), u8), word_pair_proximity: &mut impl FnMut((Rc<str>, Rc<str>), u8),
) -> Result<()> { ) -> Result<()> {
let mut token_fn = |_fname: &str, _fid: FieldId, pos: u16, word: &str| { let mut token_fn = |_fname: &str, _fid: FieldId, pos: u16, word: &str| {
// drain the proximity window until the head word is considered close to the word we are inserting. // drain the proximity window until the head word is considered close to the word we are inserting.
@ -148,7 +149,7 @@ fn process_document_tokens(
} }
// insert the new word. // insert the new word.
word_positions.push_back((word.to_string(), pos)); word_positions.push_back((Rc::from(word), pos));
Ok(()) Ok(())
}; };
document_tokenizer.tokenize_document(document, fields_ids_map, &mut token_fn)?; document_tokenizer.tokenize_document(document, fields_ids_map, &mut token_fn)?;