snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-06-06 12:15:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Removed matches_wildcard_pattern() and integrated match_pattern() into attributes_to_search_on(), updated test cases

Browse Source
This commit is contained in:
Lucas Black 2025-05-18 20:24:52 -07:00
parent 3fbe1df770
commit 13b607bd68
3 changed files with 13 additions and 77 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
crates/meilisearch/tests/search/restrict_searchable.rs
View File

@ -476,7 +476,7 @@ async fn nested_search_on_title_with_prefix_wildcard() {
}
#[actix_rt::test]
async fn nested_search_on_title_with_suffix_wildcard() {
async fn nested_search_with_suffix_wildcard() {
let server = Server::new().await;
let index = index_with_documents(&server, &NESTED_SEARCH_DOCUMENTS).await;
@ -491,17 +491,11 @@ async fn nested_search_on_title_with_suffix_wildcard() {
},
)
.await;
}
#[actix_rt::test]
async fn nested_search_all_details_with_deep_wildcard() {
let server = Server::new().await;
let index = index_with_documents(&server, &NESTED_SEARCH_DOCUMENTS).await;
// Deep wildcard should match deeply nested attributes
// Should return 1 document (ids: 1)
index
.search(
json!({"q": "gold", "attributesToSearchOn": ["details.**"]}),
json!({"q": "gold", "attributesToSearchOn": ["details.*"]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(response["hits"].as_array().unwrap().len(), @"1");
@ -512,7 +506,7 @@ async fn nested_search_all_details_with_deep_wildcard() {
// Should return 2 documents (ids: 1 and 2)
index
.search(
json!({"q": "true", "attributesToSearchOn": ["details.**"]}),
json!({"q": "true", "attributesToSearchOn": ["details.*"]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(response["hits"].as_array().unwrap().len(), @"2");
@ -522,7 +516,7 @@ async fn nested_search_all_details_with_deep_wildcard() {
}
#[actix_rt::test]
async fn nested_search_all_details_restricted_set_with_any_wildcard() {
async fn nested_search_on_title_restricted_set_with_suffix_wildcard() {
let server = Server::new().await;
let index = index_with_documents(&server, &NESTED_SEARCH_DOCUMENTS).await;
let (task, _status_code) = index.update_settings_searchable_attributes(json!(["details.title"])).await;
@ -537,16 +531,6 @@ async fn nested_search_all_details_restricted_set_with_any_wildcard() {
},
)
.await;
index
.search(
json!({"q": "Captain Marvel", "attributesToSearchOn": ["details.**"]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(response["hits"].as_array().unwrap().len(), @"2");
},
)
.await;
}
#[actix_rt::test]
@ -577,16 +561,6 @@ async fn nested_search_no_searchable_attribute_set_with_any_wildcard() {
)
.await;
index
.search(
json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown.**",]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(response["hits"].as_array().unwrap().len(), @"0");
},
)
.await;
let (task, _status_code) = index.update_settings_searchable_attributes(json!(["*"])).await;
index.wait_task(task.uid()).await.succeeded();
@ -599,17 +573,6 @@ async fn nested_search_no_searchable_attribute_set_with_any_wildcard() {
},
)
.await;
// We only match deep wild card at the end, otherwise we need to recursively match deep wildcards
index
.search(
json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown.**", "details.**"]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(response["hits"].as_array().unwrap().len(), @"3");
},
)
.await;
}
#[actix_rt::test]
@ -646,14 +609,14 @@ async fn nested_prefix_search_on_details_with_suffix_wildcard() {
}
#[actix_rt::test]
async fn nested_prefix_search_on_weaknesses_with_deep_wildcard() {
async fn nested_prefix_search_on_weaknesses_with_suffix_wildcard() {
let server = Server::new().await;
let index = index_with_documents(&server, &NESTED_SEARCH_DOCUMENTS).await;
// Deep wildcard search on nested weaknesses should return 2 documents (ids: 1 and 3)
index
.search(
json!({"q": "mag", "attributesToSearchOn": ["details.**"]}),
json!({"q": "mag", "attributesToSearchOn": ["details.*"]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(response["hits"].as_array().unwrap().len(), @"2");
@ -680,7 +643,7 @@ async fn nested_search_on_title_matching_strategy_all() {
}
#[actix_rt::test]
async fn nested_attributes_ranking_rule_order_with_wildcard() {
async fn nested_attributes_ranking_rule_order_with_prefix_wildcard() {
let server = Server::new().await;
let index = index_with_documents(&server, &NESTED_SEARCH_DOCUMENTS).await;
@ -711,14 +674,14 @@ async fn nested_attributes_ranking_rule_order_with_wildcard() {
}
#[actix_rt::test]
async fn nested_attributes_ranking_rule_order_with_deep_wildcard() {
async fn nested_attributes_ranking_rule_order_with_suffix_wildcard() {
let server = Server::new().await;
let index = index_with_documents(&server, &NESTED_SEARCH_DOCUMENTS).await;
// Document 3 should appear before documents 1 and 2
index
.search(
json!({"q": "Captain Marvel", "attributesToSearchOn": ["details.**"], "attributesToRetrieve": ["id"]}),
json!({"q": "Captain Marvel", "attributesToSearchOn": ["details.*"], "attributesToRetrieve": ["id"]}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]),

2
crates/milli/src/attribute_patterns.rs
View File

@ -50,7 +50,7 @@ impl AttributePatterns {
///
/// * `pattern` - The pattern to match against.
/// * `str` - The string to match against the pattern.
fn match_pattern(pattern: &str, str: &str) -> PatternMatch {
pub fn match_pattern(pattern: &str, str: &str) -> PatternMatch {
// If the pattern is a wildcard, return Match
if pattern == "*" {
return PatternMatch::Match;

31
crates/milli/src/search/new/mod.rs
View File

@ -52,6 +52,7 @@ pub use self::geo_sort::Strategy as GeoSortStrategy;
use self::graph_based_ranking_rule::Words;
use self::interner::Interned;
use self::vector_sort::VectorSort;
use crate::attribute_patterns::{match_pattern, PatternMatch};
use crate::constants::RESERVED_GEO_FIELD_NAME;
use crate::index::PrefixSearch;
use crate::localized_attributes_rules::LocalizedFieldIds;
@ -137,7 +138,7 @@ impl<'ctx> SearchContext<'ctx> {
let matching_searchable_weights: Vec<_> = searchable_fields_weights
.iter()
.filter(|(name, _, _)| {
Self::matches_wildcard_pattern(field_name, name)
match_pattern(field_name, name) == PatternMatch::Match
})
.collect();
@ -190,34 +191,6 @@ impl<'ctx> SearchContext<'ctx> {
Ok(())
}
fn matches_wildcard_pattern(wildcard_pattern: &str, name: &str) -> bool {
let wildcard_subfields: Vec<&str> = wildcard_pattern.split(".").collect();
let name_subfields: Vec<&str> = name.split(".").collect();
// Deep wildcard matches all attributes after ('**')
if !wildcard_subfields.is_empty() && wildcard_subfields.last() == Some(&"**") {
let prefix_len = wildcard_subfields.len() - 1;
if prefix_len > name_subfields.len() {
return false;
}
return wildcard_subfields[..prefix_len]
.iter()
.zip(name_subfields.iter())
.all(|(wc, sf)| *wc == "*" || *wc == *sf);
}
// Using single wildcard ('*') should match length (e.g. 'a.*.c' matches 'a.b.c')
// where '*' can match any single segment
if wildcard_subfields.len() != name_subfields.len() {
return false;
}
wildcard_subfields.iter()
.zip(name_subfields.iter())
.all(|(wc, sf)| *wc == "*" || *wc == *sf)
}
}
#[derive(Debug, Default)]