searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 04:17:10 +02:00
Code Issues Releases Wiki Activity

Merge #4535

Browse source 
4535: Support Negative Keywords r=ManyTheFish a=Kerollmops

This PR fixes #4422 by supporting `-` before any word in the query.

The minus symbol `-`, from the ASCII table, is not the only character that can be considered the negative operator. You can see the two other matching characters under the `Based on "-" (U+002D)` section on [this unicode reference website](https://www.compart.com/en/unicode/U+002D).

It's important to notice the strange behavior when a query includes and excludes the same word; only the derivative ( synonyms and split) will be kept:
 - If you input `progamer -progamer`, the engine will still search for `pro gamer`.
 - If you have the synonym `like = love` and you input `like -like`, it will still search for `love`.

## TODO
 - [x] Add analytics
 - [x] Add support to the `-` operator
 - [x] Make sure to support spaces around `-` well
 - [x] Support phrase negation
 - [x] Add tests


Co-authored-by: Clément Renault <clement@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-04-04 13:10:27 +00:00 • committed by GitHub
commit 5509bafff8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 260 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

10
meilisearch/src/analytics/segment_analytics.rs
View file

@ -583,6 +583,7 @@ pub struct SearchAggregator {
total_received: usize,
total_succeeded: usize,
total_degraded: usize,
total_used_negative_operator: usize,
time_spent: BinaryHeap<usize>,
// sort
@ -763,12 +764,16 @@ impl SearchAggregator {
facet_distribution: _,
facet_stats: _,
degraded,
used_negative_operator,
} = result;
self.total_succeeded = self.total_succeeded.saturating_add(1);
if *degraded {
self.total_degraded = self.total_degraded.saturating_add(1);
}
if *used_negative_operator {
self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
}
self.time_spent.push(*processing_time_ms as usize);
}
@ -811,6 +816,7 @@ impl SearchAggregator {
embedder,
hybrid,
total_degraded,
total_used_negative_operator,
} = other;
if self.timestamp.is_none() {
@ -826,6 +832,8 @@ impl SearchAggregator {
self.total_received = self.total_received.saturating_add(total_received);
self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
self.total_degraded = self.total_degraded.saturating_add(total_degraded);
self.total_used_negative_operator =
self.total_used_negative_operator.saturating_add(total_used_negative_operator);
self.time_spent.append(time_spent);
// sort
@ -932,6 +940,7 @@ impl SearchAggregator {
embedder,
hybrid,
total_degraded,
total_used_negative_operator,
} = self;
if total_received == 0 {
@ -952,6 +961,7 @@ impl SearchAggregator {
"total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
"total_received": total_received,
"total_degraded": total_degraded,
"total_used_negative_operator": total_used_negative_operator,
},
"sort": {
"with_geoPoint": sort_with_geo_point,