3921: Deactivate camel case segmentation r=dureuill a=ManyTheFish

# Pull Request
This PR deactivates the camel case segmentation to retrieve the possibility to accept typos over camel-cased words

## Related issue
Fixes #3869
Fixes #3818

## What does this PR do?
- deactivates camelcase segmentation

related to #3919



Co-authored-by: ManyTheFish <many@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2023-07-13 11:00:14 +00:00 committed by GitHub
commit 7745cc9d3c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 229 additions and 9 deletions

7
Cargo.lock generated
View File

@ -709,7 +709,6 @@ dependencies = [
"csv",
"deunicode",
"either",
"finl_unicode",
"fst",
"irg-kvariants",
"jieba-rs",
@ -1443,12 +1442,6 @@ dependencies = [
"nom_locate",
]
[[package]]
name = "finl_unicode"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fcfdc7a0362c9f4444381a9e697c79d435fe65b52a37466fc2c1184cee9edc6"
[[package]]
name = "flate2"
version = "1.0.26"

View File

@ -876,3 +876,230 @@ async fn experimental_feature_vector_store() {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @"[]");
}
#[cfg(feature = "default")]
#[actix_rt::test]
async fn camelcased_words() {
let server = Server::new().await;
let index = server.index("test");
// related to https://github.com/meilisearch/meilisearch/issues/3818
let documents = json!([
{ "id": 0, "title": "DeLonghi" },
{ "id": 1, "title": "delonghi" },
{ "id": 2, "title": "TestAB" },
{ "id": 3, "title": "TestAb" },
{ "id": 4, "title": "testab" },
]);
index.add_documents(documents, None).await;
index.wait_task(0).await;
index
.search(json!({"q": "deLonghi"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 0,
"title": "DeLonghi"
},
{
"id": 1,
"title": "delonghi"
}
]
"###);
})
.await;
index
.search(json!({"q": "dellonghi"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 0,
"title": "DeLonghi"
},
{
"id": 1,
"title": "delonghi"
}
]
"###);
})
.await;
index
.search(json!({"q": "testa"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
index
.search(json!({"q": "testab"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
index
.search(json!({"q": "TestaB"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
index
.search(json!({"q": "Testab"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
index
.search(json!({"q": "TestAb"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
// with Typos
index
.search(json!({"q": "dellonghi"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 0,
"title": "DeLonghi"
},
{
"id": 1,
"title": "delonghi"
}
]
"###);
})
.await;
index
.search(json!({"q": "TetsAB"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
index
.search(json!({"q": "TetsAB"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
"title": "TestAb"
},
{
"id": 4,
"title": "testab"
}
]
"###);
})
.await;
}

View File

@ -310,7 +310,7 @@ async fn exactness_ranking_rule_order() {
},
{
"title": "Captain Marvel",
"desc": "CaptainMarvel",
"desc": "Captain the Marvel",
"id": "2",
}]),
)

View File

@ -81,7 +81,7 @@ md5 = "0.7.0"
rand = { version = "0.8.5", features = ["small_rng"] }
[features]
all-tokenizations = ["charabia/default"]
all-tokenizations = ["charabia/chinese", "charabia/hebrew", "charabia/japanese", "charabia/thai", "charabia/korean", "charabia/greek"]
# Use POSIX semaphores instead of SysV semaphores in LMDB
# For more information on this feature, see heed's Cargo.toml