searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-01-23 03:37:28 +01:00
Code Issues Releases Wiki Activity

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

Browse Source
This commit is contained in:
Clément Renault 2022-01-12 16:14:53 +01:00
parent 1514dfa1b7
commit f04cd19886
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4
1 changed files with 23 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
milli/src/update/word_prefix_pair_proximity_docids.rs
View File

@ -19,6 +19,7 @@ pub struct WordPrefixPairProximityDocids<'t, 'u, 'i> {
pub(crate) max_nb_chunks: Option<usize>,
pub(crate) max_memory: Option<usize>,
max_proximity: u8,
max_prefix_length: usize,
}
impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
@ -34,6 +35,7 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
max_nb_chunks: None,
max_memory: None,
max_proximity: 4,
max_prefix_length: 2,
}
}
@ -48,6 +50,17 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
self
}
/// Set the maximum length the prefix of a word pair is allowed to have 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_prefix_length(&mut self, value: usize) -> &mut Self {
self.max_prefix_length = value;
self
}
#[logging_timer::time("WordPrefixPairProximityDocids::{}")]
pub fn execute(self) -> Result<()> {
debug!("Computing and writing the word prefix pair proximity docids into LMDB on disk...");
@ -94,15 +107,17 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
buffer.clear();
buffer.extend_from_slice(w1.as_bytes());
buffer.push(0);
for prefix in prefixes.iter().filter(|prefix| w2.starts_with(prefix.as_str())) {
buffer.truncate(w1.len() + 1);
buffer.extend_from_slice(prefix.as_bytes());
buffer.push(prox);
for prefix in prefixes.iter() {
if prefix.len() <= self.max_prefix_length && w2.starts_with(prefix) {
buffer.truncate(w1.len() + 1);
buffer.extend_from_slice(prefix.as_bytes());
buffer.push(prox);
match prefixes_cache.get_mut(&buffer) {
Some(value) => value.push(data),
None => {
prefixes_cache.insert(buffer.clone(), vec![data]);
match prefixes_cache.get_mut(&buffer) {
Some(value) => value.push(data),
None => {
prefixes_cache.insert(buffer.clone(), vec![data]);
}
}
}
}