searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-12-27 15:10:05 +01:00
Code Issues Releases Wiki Activity

Introduce a max proximity parameter to the word prefix pair proximity update

Browse Source
This commit is contained in:
Clément Renault 2022-01-12 15:40:51 +01:00
parent 23ea3ad738
commit 1514dfa1b7
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
milli/src/update/word_prefix_pair_proximity_docids.rs
View File

@ -18,6 +18,7 @@ pub struct WordPrefixPairProximityDocids<'t, 'u, 'i> {
pub(crate) chunk_compression_level: Option<u32>,
pub(crate) max_nb_chunks: Option<usize>,
pub(crate) max_memory: Option<usize>,
max_proximity: u8,
}
impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
@ -32,9 +33,21 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
chunk_compression_level: None,
max_nb_chunks: None,
max_memory: None,
max_proximity: 4,
}
}
/// Set the maximum proximity required to make a prefix be part of the words prefixes
/// database. If two words are two far from the threshold the associated documents will
/// not be part of the prefix database.
///
/// Default value is 4. This value must be lower or equal than 4 and will be clamped
/// to this bound otherwise.
pub fn max_proximity(&mut self, value: u8) -> &mut Self {
self.max_proximity = value.max(7);
self
}
#[logging_timer::time("WordPrefixPairProximityDocids::{}")]
pub fn execute(self) -> Result<()> {
debug!("Computing and writing the word prefix pair proximity docids into LMDB on disk...");
@ -62,6 +75,10 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
let mut current_prefixes: Option<&&[String]> = None;
let mut prefixes_cache = HashMap::new();
while let Some(((w1, w2, prox), data)) = db.next().transpose()? {
if prox > self.max_proximity {
continue;
}
current_prefixes = match current_prefixes.take() {
Some(prefixes) if w2.starts_with(&prefixes[0]) => Some(prefixes),
_otherwise => {