searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-26 06:44:27 +01:00
Code Issues Releases Wiki Activity

make the descendent geosort fast

Browse Source
This commit is contained in:
Tamo 2023-05-02 12:04:08 +02:00 committed by Louis Dureuil
parent 8875d24a48
commit c85392ce40
No known key found for this signature in database
1 changed files with 21 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
milli/src/search/new/geo_sort.rs
View File

@ -118,9 +118,9 @@ impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
let cache_size = self.strategy.cache_size(); let cache_size = self.strategy.cache_size();
if use_rtree { if use_rtree {
let rtree = self.rtree.as_ref().unwrap(); let rtree = self.rtree.as_ref().unwrap();
let point = lat_lng_to_xyz(&self.point);
if self.ascending { if self.ascending {
let point = lat_lng_to_xyz(&self.point);
for point in rtree.nearest_neighbor_iter(&point) { for point in rtree.nearest_neighbor_iter(&point) {
if self.geo_candidates.contains(point.data.0) { if self.geo_candidates.contains(point.data.0) {
self.cached_sorted_docids.push_back(point.data.0); self.cached_sorted_docids.push_back(point.data.0);
@ -130,18 +130,15 @@ impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
} }
} }
} else { } else {
// in the case of the desc geo sort we have to scan the whole database // in the case of the desc geo sort we look for the closest point to the opposite of the queried point
// and only keep the latest candidates. // and we insert the points in reverse order they get reversed when emptying the cache later on
let point = lat_lng_to_xyz(&opposite_of(self.point));
for point in rtree.nearest_neighbor_iter(&point) { for point in rtree.nearest_neighbor_iter(&point) {
if self.geo_candidates.contains(point.data.0) { if self.geo_candidates.contains(point.data.0) {
// REVIEW COMMENT: that doesn't look right, because we only keep the furthest point in the cache. self.cached_sorted_docids.push_front(point.data.0);
// Then the cache will be exhausted after the first bucket and we'll need to repopulate it again immediately. if self.cached_sorted_docids.len() >= cache_size {
// I think it's okay if we keep every document id in the cache instead. It's a high memory usage, break;
// but we already have the whole rtree in memory, which is bigger than a vector of all document ids. }
//
// self.cached_sorted_docids.pop_front();
//
self.cached_sorted_docids.push_back(point.data.0);
} }
} }
} }
@ -253,3 +250,16 @@ impl<'ctx, Q: RankingRuleQueryTrait> RankingRule<'ctx, Q> for GeoSort<Q> {
self.cached_sorted_docids.clear(); self.cached_sorted_docids.clear();
} }
} }
/// Compute the antipodal coordinate of `coord`
fn opposite_of(mut coord: [f64; 2]) -> [f64; 2] {
coord[0] *= -1.;
// in the case of x,0 we want to return x,180
if coord[1] > 0. {
coord[1] -= 180.;
} else {
coord[1] += 180.;
}
coord
}