MeiliSearch/meilisearch/tests/search/mod.rs

1714 lines
49 KiB
Rust
Raw Normal View History

// This modules contains all the test concerning search. Each particular feature of the search
2021-02-18 19:50:52 +01:00
// should be tested in its own module to isolate tests and keep the tests readable.
2021-07-06 11:54:37 +02:00
mod distinct;
2021-07-06 11:54:37 +02:00
mod errors;
2023-06-28 11:31:52 +02:00
mod facet_search;
2022-04-19 16:49:38 +02:00
mod formatted;
2023-07-17 18:28:03 +02:00
mod geo;
2023-12-13 11:47:12 +01:00
mod hybrid;
2024-05-30 12:02:42 +02:00
mod matching_strategy;
2023-02-06 13:46:12 +01:00
mod multi;
2022-10-20 17:03:07 +02:00
mod pagination;
2023-06-07 18:49:17 +02:00
mod restrict_searchable;
mod search_queue;
2021-07-06 11:54:37 +02:00
use once_cell::sync::Lazy;
2023-09-11 16:50:53 +02:00
use crate::common::{Server, Value};
use crate::json;
2022-10-20 18:00:07 +02:00
2023-11-23 12:20:44 +01:00
static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
2021-07-06 11:54:37 +02:00
json!([
{
"title": "Shazam!",
"id": "287947",
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [1, 2, 3]},
2021-07-06 11:54:37 +02:00
},
{
"title": "Captain Marvel",
"id": "299537",
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [1, 2, 54] },
2021-07-06 11:54:37 +02:00
},
{
"title": "Escape Room",
"id": "522681",
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [10, -23, 32] },
2021-07-06 11:54:37 +02:00
},
{
"title": "How to Train Your Dragon: The Hidden World",
"id": "166428",
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [-100, 231, 32] },
2021-07-06 11:54:37 +02:00
},
{
2023-03-29 10:58:05 +02:00
"title": "Gläss",
"id": "450465",
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [-100, 340, 90] },
2021-07-06 11:54:37 +02:00
}
])
});
2024-05-30 11:22:26 +02:00
static SCORE_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
},
{
"title": "Batman Returns",
"id": "C",
},
{
"title": "Batman",
"id": "D",
},
{
"title": "Badman",
"id": "E",
}
])
});
2023-11-23 12:20:44 +01:00
static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([
{
"id": 852,
"father": "jean",
"mother": "michelle",
"doggos": [
{
"name": "bobby",
"age": 2,
},
{
"name": "buddy",
"age": 4,
},
],
2023-03-29 10:58:05 +02:00
"cattos": "pésti",
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [1, 2, 3]},
},
{
"id": 654,
"father": "pierre",
"mother": "sabine",
"doggos": [
{
"name": "gros bill",
"age": 8,
},
],
"cattos": ["simba", "pestiféré"],
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [1, 2, 54] },
},
{
"id": 750,
"father": "romain",
"mother": "michelle",
"cattos": ["enigma"],
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [10, 23, 32] },
},
{
"id": 951,
"father": "jean-baptiste",
"mother": "sophie",
"doggos": [
{
"name": "turbo",
"age": 5,
},
{
"name": "fast",
"age": 6,
},
],
"cattos": ["moumoute", "gomez"],
2023-12-13 21:49:13 +01:00
"_vectors": { "manual": [10, 23, 32] },
},
])
});
2021-07-06 11:54:37 +02:00
#[actix_rt::test]
async fn simple_placeholder_search() {
let server = Server::new().await;
let index = server.index("basic");
2021-07-06 11:54:37 +02:00
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
2021-07-06 11:54:37 +02:00
index
.search(json!({}), |response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 5);
})
.await;
let index = server.index("nested");
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(json!({}), |response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 4);
})
.await;
2021-07-06 11:54:37 +02:00
}
#[actix_rt::test]
async fn simple_search() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
2021-07-06 11:54:37 +02:00
index
.search(json!({"q": "glass"}), |response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
})
.await;
let index = server.index("nested");
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
2023-03-29 10:58:05 +02:00
.search(json!({"q": "pésti"}), |response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 2);
})
.await;
2021-07-06 11:54:37 +02:00
}
2023-02-21 18:02:10 +01:00
#[actix_rt::test]
async fn phrase_search_with_stop_word() {
// related to https://github.com/meilisearch/meilisearch/issues/3521
let server = Server::new().await;
let index = server.index("test");
let (_, code) = index.update_settings(json!({"stopWords": ["the", "of"]})).await;
meili_snap::snapshot!(code, @"202 Accepted");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(json!({"q": "how \"to\" train \"the" }), |response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
})
.await;
}
2024-04-04 12:01:04 +02:00
#[actix_rt::test]
async fn negative_phrase_search() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
index
.search(json!({"q": "-\"train your dragon\"" }), |response, code| {
assert_eq!(code, 200, "{}", response);
let hits = response["hits"].as_array().unwrap();
assert_eq!(hits.len(), 4);
assert_eq!(hits[0]["id"], "287947");
assert_eq!(hits[1]["id"], "299537");
assert_eq!(hits[2]["id"], "522681");
assert_eq!(hits[3]["id"], "450465");
})
.await;
}
#[actix_rt::test]
async fn negative_word_search() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
index
.search(json!({"q": "-escape" }), |response, code| {
assert_eq!(code, 200, "{}", response);
let hits = response["hits"].as_array().unwrap();
assert_eq!(hits.len(), 4);
assert_eq!(hits[0]["id"], "287947");
assert_eq!(hits[1]["id"], "299537");
assert_eq!(hits[2]["id"], "166428");
assert_eq!(hits[3]["id"], "450465");
})
.await;
// Everything that contains derivates of escape but not escape: nothing
index
.search(json!({"q": "-escape escape" }), |response, code| {
assert_eq!(code, 200, "{}", response);
let hits = response["hits"].as_array().unwrap();
assert_eq!(hits.len(), 0);
})
.await;
}
#[actix_rt::test]
async fn non_negative_search() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
index
.search(json!({"q": "- escape" }), |response, code| {
assert_eq!(code, 200, "{}", response);
let hits = response["hits"].as_array().unwrap();
assert_eq!(hits.len(), 1);
assert_eq!(hits[0]["id"], "522681");
})
.await;
index
.search(json!({"q": "- \"train your dragon\"" }), |response, code| {
assert_eq!(code, 200, "{}", response);
let hits = response["hits"].as_array().unwrap();
assert_eq!(hits.len(), 1);
assert_eq!(hits[0]["id"], "166428");
})
.await;
}
#[actix_rt::test]
async fn negative_special_cases_search() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
2024-06-06 17:24:50 +02:00
index.update_settings(json!({"synonyms": { "escape": ["gläss"] }})).await;
2024-04-04 12:01:04 +02:00
index.wait_task(1).await;
// There is a synonym for escape -> glass but we don't want "escape", only the derivates: glass
index
.search(json!({"q": "-escape escape" }), |response, code| {
assert_eq!(code, 200, "{}", response);
let hits = response["hits"].as_array().unwrap();
assert_eq!(hits.len(), 1);
assert_eq!(hits[0]["id"], "450465");
})
.await;
}
#[cfg(feature = "default")]
#[actix_rt::test]
async fn test_kanji_language_detection() {
let server = Server::new().await;
let index = server.index("test");
let documents = json!([
{ "id": 0, "title": "The quick (\"brown\") fox can't jump 32.3 feet, right? Brr, it's 29.3°F!" },
{ "id": 1, "title": "東京のお寿司。" },
{ "id": 2, "title": "הַשּׁוּעָל הַמָּהִיר (״הַחוּם״) לֹא יָכוֹל לִקְפֹּץ 9.94 מֶטְרִים, נָכוֹן? ברר, 1.5°C- בַּחוּץ!" }
]);
index.add_documents(documents, None).await;
index.wait_task(0).await;
index
.search(json!({"q": "東京"}), |response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
})
.await;
}
2023-03-09 14:56:13 +01:00
#[cfg(feature = "default")]
#[actix_rt::test]
async fn test_thai_language() {
let server = Server::new().await;
let index = server.index("test");
// We don't need documents, the issue is on the query side only.
let documents = json!([
{ "id": 0, "title": "สบู่สมุนไพรดอกดาวเรือง 100 กรัม จำนวน 6 ก้อน" },
{ "id": 1, "title": "สบู่สมุนไพรชาเขียว 100 กรัม จำนวน 6 ก้อน" },
{ "id": 2, "title": "สบู่สมุนไพรฝางแดงผสมว่านหางจรเข้ 100 กรัม จำนวน 6 ก้อน" }
]);
index.add_documents(documents, None).await;
index.wait_task(0).await;
index.update_settings(json!({"rankingRules": ["exactness"]})).await;
index.wait_task(1).await;
index
.search(json!({"q": "สบู"}), |response, code| {
assert_eq!(code, 200, "{}", response);
})
.await;
}
2021-07-06 11:54:37 +02:00
#[actix_rt::test]
async fn search_multiple_params() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(0).await;
2021-07-06 11:54:37 +02:00
index
.search(
json!({
"q": "glass",
"attributesToCrop": ["title:2"],
"attributesToHighlight": ["title"],
"limit": 1,
"offset": 0,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
},
)
.await;
let index = server.index("nested");
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(
json!({
2023-03-29 10:58:05 +02:00
"q": "pésti",
"attributesToCrop": ["catto:2"],
"attributesToHighlight": ["catto"],
"limit": 2,
"offset": 0,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 2);
},
)
.await;
2021-07-06 11:54:37 +02:00
}
#[actix_rt::test]
async fn search_with_filter_string_notation() {
let server = Server::new().await;
let index = server.index("test");
2023-01-12 15:39:28 +01:00
let (_, code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
meili_snap::snapshot!(code, @"202 Accepted");
2021-07-06 11:54:37 +02:00
let documents = DOCUMENTS.clone();
2023-01-12 15:39:28 +01:00
let (_, code) = index.add_documents(documents, None).await;
meili_snap::snapshot!(code, @"202 Accepted");
let res = index.wait_task(1).await;
meili_snap::snapshot!(res["status"], @r###""succeeded""###);
2021-07-06 11:54:37 +02:00
index
.search(
json!({
2023-03-29 10:58:05 +02:00
"filter": "title = Gläss"
2021-07-06 11:54:37 +02:00
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
},
)
.await;
let index = server.index("nested");
2023-01-12 15:39:28 +01:00
let (_, code) =
index.update_settings(json!({"filterableAttributes": ["cattos", "doggos.age"]})).await;
meili_snap::snapshot!(code, @"202 Accepted");
let documents = NESTED_DOCUMENTS.clone();
2023-01-12 15:39:28 +01:00
let (_, code) = index.add_documents(documents, None).await;
meili_snap::snapshot!(code, @"202 Accepted");
let res = index.wait_task(3).await;
meili_snap::snapshot!(res["status"], @r###""succeeded""###);
index
.search(
json!({
2023-03-29 10:58:05 +02:00
"filter": "cattos = pésti"
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
assert_eq!(response["hits"][0]["id"], json!(852));
},
)
.await;
index
.search(
json!({
"filter": "doggos.age > 5"
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 2);
assert_eq!(response["hits"][0]["id"], json!(654));
assert_eq!(response["hits"][1]["id"], json!(951));
},
)
.await;
2021-07-06 11:54:37 +02:00
}
#[actix_rt::test]
async fn search_with_filter_array_notation() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"filterableAttributes": ["title"]})).await;
2021-07-06 11:54:37 +02:00
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
2021-07-06 11:54:37 +02:00
let (response, code) = index
.search_post(json!({
2023-03-29 10:58:05 +02:00
"filter": ["title = Gläss"]
2021-07-06 11:54:37 +02:00
}))
.await;
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1);
let (response, code) = index
.search_post(json!({
2023-03-29 10:58:05 +02:00
"filter": [["title = Gläss", "title = \"Shazam!\"", "title = \"Escape Room\""]]
2021-07-06 11:54:37 +02:00
}))
.await;
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 3);
}
#[actix_rt::test]
async fn search_with_sort_on_numbers() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"sortableAttributes": ["id"]})).await;
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(
json!({
"sort": ["id:asc"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 5);
},
)
.await;
let index = server.index("nested");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"sortableAttributes": ["doggos.age"]})).await;
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(3).await;
index
.search(
json!({
"sort": ["doggos.age:asc"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 4);
},
)
.await;
}
#[actix_rt::test]
async fn search_with_sort_on_strings() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"sortableAttributes": ["title"]})).await;
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(
json!({
"sort": ["title:desc"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 5);
},
)
.await;
let index = server.index("nested");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"sortableAttributes": ["doggos.name"]})).await;
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(3).await;
index
.search(
json!({
"sort": ["doggos.name:asc"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 4);
},
)
.await;
}
#[actix_rt::test]
async fn search_with_multiple_sort() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"sortableAttributes": ["id", "title"]})).await;
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
let (response, code) = index
.search_post(json!({
"sort": ["id:asc", "title:desc"]
}))
.await;
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 5);
}
2021-07-06 11:54:37 +02:00
#[actix_rt::test]
async fn search_facet_distribution() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"filterableAttributes": ["title"]})).await;
2021-07-06 11:54:37 +02:00
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
2021-07-06 11:54:37 +02:00
index
.search(
json!({
"facets": ["title"]
2021-07-06 11:54:37 +02:00
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
let dist = response["facetDistribution"].as_object().unwrap();
2021-07-06 11:54:37 +02:00
assert_eq!(dist.len(), 1);
assert!(dist.get("title").is_some());
},
)
.await;
let index = server.index("nested");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"filterableAttributes": ["father", "doggos.name"]})).await;
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(3).await;
// TODO: TAMO: fix the test
index
.search(
json!({
// "facets": ["father", "doggos.name"]
"facets": ["father"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
let dist = response["facetDistribution"].as_object().unwrap();
assert_eq!(dist.len(), 1);
assert_eq!(
dist["father"],
json!({ "jean": 1, "pierre": 1, "romain": 1, "jean-baptiste": 1})
);
/*
assert_eq!(
dist["doggos.name"],
json!({ "bobby": 1, "buddy": 1, "gros bill": 1, "turbo": 1, "fast": 1})
);
*/
},
)
.await;
2022-10-20 18:00:07 +02:00
index.update_settings(json!({"filterableAttributes": ["doggos"]})).await;
index.wait_task(4).await;
index
.search(
json!({
"facets": ["doggos.name"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
let dist = response["facetDistribution"].as_object().unwrap();
assert_eq!(dist.len(), 1);
assert_eq!(
dist["doggos.name"],
json!({ "bobby": 1, "buddy": 1, "gros bill": 1, "turbo": 1, "fast": 1})
);
},
)
.await;
index
.search(
json!({
"facets": ["doggos"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
let dist = response["facetDistribution"].as_object().unwrap();
2022-05-04 12:10:52 +02:00
assert_eq!(dist.len(), 3);
assert_eq!(
dist["doggos.name"],
json!({ "bobby": 1, "buddy": 1, "gros bill": 1, "turbo": 1, "fast": 1})
);
2022-10-20 18:00:07 +02:00
assert_eq!(dist["doggos.age"], json!({ "2": 1, "4": 1, "5": 1, "6": 1, "8": 1}));
},
)
.await;
index.update_settings(json!({"filterableAttributes": ["doggos.name"]})).await;
index.wait_task(5).await;
index
.search(
json!({
"facets": ["doggos.name"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
let dist = response["facetDistribution"].as_object().unwrap();
assert_eq!(dist.len(), 1);
assert_eq!(
dist["doggos.name"],
json!({ "bobby": 1, "buddy": 1, "gros bill": 1, "turbo": 1, "fast": 1})
);
},
)
.await;
2021-07-06 11:54:37 +02:00
}
#[actix_rt::test]
async fn displayed_attributes() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({ "displayedAttributes": ["title"] })).await;
2021-07-06 11:54:37 +02:00
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
2021-07-06 11:54:37 +02:00
2022-10-20 18:00:07 +02:00
let (response, code) =
index.search_post(json!({ "attributesToRetrieve": ["title", "id"] })).await;
2021-07-06 11:54:37 +02:00
assert_eq!(code, 200, "{}", response);
assert!(response["hits"][0].get("title").is_some());
2021-07-06 11:54:37 +02:00
}
2022-03-31 01:32:37 +02:00
#[actix_rt::test]
async fn placeholder_search_is_hard_limited() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
let documents: Vec<_> = (0..1200).map(|i| json!({ "id": i, "text": "I am unique!" })).collect();
2022-03-31 01:32:37 +02:00
index.add_documents(documents.into(), None).await;
index.wait_task(0).await;
index
.search(
json!({
"limit": 1500,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1000);
},
)
.await;
index
.search(
json!({
"offset": 800,
"limit": 400,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 200);
},
)
.await;
2022-10-20 18:00:07 +02:00
index.update_settings(json!({ "pagination": { "maxTotalHits": 10_000 } })).await;
index.wait_task(1).await;
index
.search(
json!({
"limit": 1500,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1200);
},
)
.await;
index
.search(
json!({
"offset": 1000,
"limit": 400,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 200);
},
)
.await;
2022-03-31 01:32:37 +02:00
}
#[actix_rt::test]
async fn search_is_hard_limited() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
let documents: Vec<_> = (0..1200).map(|i| json!({ "id": i, "text": "I am unique!" })).collect();
2022-03-31 01:32:37 +02:00
index.add_documents(documents.into(), None).await;
index.wait_task(0).await;
index
.search(
json!({
"q": "unique",
"limit": 1500,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1000);
},
)
.await;
index
.search(
json!({
"q": "unique",
"offset": 800,
"limit": 400,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 200);
},
)
.await;
2022-10-20 18:00:07 +02:00
index.update_settings(json!({ "pagination": { "maxTotalHits": 10_000 } })).await;
index.wait_task(1).await;
index
.search(
json!({
"q": "unique",
"limit": 1500,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 1200);
},
)
.await;
index
.search(
json!({
"q": "unique",
"offset": 1000,
"limit": 400,
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
assert_eq!(response["hits"].as_array().unwrap().len(), 200);
},
)
.await;
2022-03-31 01:32:37 +02:00
}
#[actix_rt::test]
async fn faceting_max_values_per_facet() {
let server = Server::new().await;
let index = server.index("test");
2022-10-20 18:00:07 +02:00
index.update_settings(json!({ "filterableAttributes": ["number"] })).await;
2022-10-20 18:00:07 +02:00
let documents: Vec<_> = (0..10_000).map(|id| json!({ "id": id, "number": id * 10 })).collect();
index.add_documents(json!(documents), None).await;
index.wait_task(1).await;
index
.search(
json!({
"facets": ["number"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
let numbers = response["facetDistribution"]["number"].as_object().unwrap();
assert_eq!(numbers.len(), 100);
},
)
.await;
2022-10-20 18:00:07 +02:00
index.update_settings(json!({ "faceting": { "maxValuesPerFacet": 10_000 } })).await;
index.wait_task(2).await;
index
.search(
json!({
"facets": ["number"]
}),
|response, code| {
assert_eq!(code, 200, "{}", response);
2022-06-16 15:58:39 +02:00
let numbers = &response["facetDistribution"]["number"].as_object().unwrap();
assert_eq!(numbers.len(), 10_000);
},
)
.await;
}
#[actix_rt::test]
2024-02-06 10:55:27 +01:00
async fn test_score_details() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
2024-02-06 10:55:27 +01:00
let res = index.add_documents(json!(documents), None).await;
index.wait_task(res.0.uid()).await;
index
.search(
json!({
"q": "train dragon",
"showRankingScoreDetails": true,
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "How to Train Your Dragon: The Hidden World",
"id": "166428",
2023-12-13 21:49:13 +01:00
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
-100.0,
231.0,
32.0
2023-12-13 21:49:13 +01:00
]
},
"_rankingScoreDetails": {
"words": {
"order": 0,
"matchingWords": 2,
"maxMatchingWords": 2,
"score": 1.0
},
"typo": {
"order": 1,
"typoCount": 0,
"maxTypoCount": 2,
"score": 1.0
},
"proximity": {
"order": 2,
2023-10-17 17:19:45 +02:00
"score": 0.75
},
"attribute": {
"order": 3,
2023-07-25 15:49:33 +02:00
"attributeRankingOrderScore": 1.0,
"queryWordDistanceScore": 0.8095238095238095,
"score": 0.8095238095238095
},
"exactness": {
"order": 4,
"matchType": "noExactMatch",
"matchingWords": 2,
"maxMatchingWords": 2,
"score": 0.3333333333333333
}
}
}
]
"###);
},
)
2024-03-14 17:34:46 +01:00
.await;
}
2024-05-30 11:22:26 +02:00
#[actix_rt::test]
async fn test_score() {
let server = Server::new().await;
let index = server.index("test");
let documents = SCORE_DOCUMENTS.clone();
let res = index.add_documents(json!(documents), None).await;
index.wait_task(res.0.uid()).await;
index
.search(
json!({
"q": "Badman the dark knight returns 1",
"showRankingScore": true,
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.9746605609456898
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.8055252965383685
},
{
"title": "Badman",
"id": "E",
"_rankingScore": 0.16666666666666666
},
{
"title": "Batman Returns",
"id": "C",
"_rankingScore": 0.07702020202020202
},
{
"title": "Batman",
"id": "D",
"_rankingScore": 0.07702020202020202
}
]
"###);
},
)
.await;
}
#[actix_rt::test]
async fn test_score_threshold() {
let query = "Badman dark returns 1";
let server = Server::new().await;
let index = server.index("test");
let documents = SCORE_DOCUMENTS.clone();
let res = index.add_documents(json!(documents), None).await;
index.wait_task(res.0.uid()).await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.0
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"5");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.6685627880184332
},
{
"title": "Badman",
"id": "E",
"_rankingScore": 0.25
},
{
"title": "Batman Returns",
"id": "C",
"_rankingScore": 0.11553030303030302
},
{
"title": "Batman",
"id": "D",
"_rankingScore": 0.11553030303030302
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.2
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"3"###);
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.6685627880184332
},
{
"title": "Badman",
"id": "E",
"_rankingScore": 0.25
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.5
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"2"###);
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.6685627880184332
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.8
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"1"###);
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 1.0
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"0"###);
// nobody is perfect
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @"[]");
},
)
.await;
}
2024-03-14 17:34:46 +01:00
#[actix_rt::test]
async fn test_degraded_score_details() {
let server = Server::new().await;
let index = server.index("test");
let documents = NESTED_DOCUMENTS.clone();
index.add_documents(json!(documents), None).await;
// We can't really use anything else than 0ms here; otherwise, the test will get flaky.
let (res, _code) = index.update_settings(json!({ "searchCutoffMs": 0 })).await;
2024-03-14 17:34:46 +01:00
index.wait_task(res.uid()).await;
index
.search(
json!({
"q": "b",
2024-03-14 17:42:33 +01:00
"attributesToRetrieve": ["doggos.name", "cattos"],
2024-03-14 17:34:46 +01:00
"showRankingScoreDetails": true,
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response, { ".processingTimeMs" => "[duration]" }), @r###"
{
"hits": [
{
"doggos": [
{
"name": "bobby"
},
{
"name": "buddy"
}
],
"cattos": "pésti",
"_rankingScoreDetails": {
2024-03-19 15:45:04 +01:00
"skipped": {
"order": 0
}
2024-03-14 17:34:46 +01:00
}
},
{
"doggos": [
{
"name": "gros bill"
}
],
"cattos": [
"simba",
"pestiféré"
],
"_rankingScoreDetails": {
2024-03-19 15:45:04 +01:00
"skipped": {
"order": 0
}
2024-03-14 17:34:46 +01:00
}
},
{
"doggos": [
{
"name": "turbo"
},
{
"name": "fast"
}
],
"cattos": [
"moumoute",
"gomez"
],
"_rankingScoreDetails": {
2024-03-19 15:45:04 +01:00
"skipped": {
"order": 0
}
2024-03-14 17:34:46 +01:00
}
}
],
"query": "b",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 3
}
2024-03-14 17:34:46 +01:00
"###);
},
)
.await;
}
#[actix_rt::test]
async fn experimental_feature_vector_store() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
index.add_documents(json!(documents), None).await;
index.wait_task(0).await;
let (response, code) = index
.search_post(json!({
"vector": [1.0, 2.0, 3.0],
2024-04-03 14:29:17 +02:00
"showRankingScore": true
}))
.await;
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "Passing `vector` as a query parameter requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
}
"###);
let (response, code) = server.set_features(json!({"vectorStore": true})).await;
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(response["vectorStore"], @"true");
2023-12-13 21:49:13 +01:00
let (response, code) = index
.update_settings(json!({"embedders": {
"manual": {
2023-12-20 17:06:50 +01:00
"source": "userProvided",
"dimensions": 3,
2023-12-13 21:49:13 +01:00
}
}}))
.await;
2023-12-20 17:06:50 +01:00
meili_snap::snapshot!(response, @r###"
{
"taskUid": 1,
"indexUid": "test",
"status": "enqueued",
"type": "settingsUpdate",
"enqueuedAt": "[date]"
}
"###);
2023-12-13 21:49:13 +01:00
meili_snap::snapshot!(code, @"202 Accepted");
let response = index.wait_task(response.uid()).await;
meili_snap::snapshot!(meili_snap::json_string!(response["status"]), @"\"succeeded\"");
let (response, code) = index
.search_post(json!({
"vector": [1.0, 2.0, 3.0],
2024-04-03 14:29:17 +02:00
"showRankingScore": true,
}))
.await;
2023-12-13 21:49:13 +01:00
meili_snap::snapshot!(code, @"200 OK");
// vector search returns all documents that don't have vectors in the last bucket, like all sorts
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Shazam!",
2023-12-13 21:49:13 +01:00
"id": "287947",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
1.0,
2.0,
3.0
2023-12-13 21:49:13 +01:00
]
},
2024-04-03 14:29:17 +02:00
"_rankingScore": 1.0
},
{
"title": "Captain Marvel",
2023-12-13 21:49:13 +01:00
"id": "299537",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
1.0,
2.0,
54.0
2023-12-13 21:49:13 +01:00
]
},
2024-04-03 14:29:17 +02:00
"_rankingScore": 0.9129111766815186
},
{
2023-12-13 21:49:13 +01:00
"title": "Gläss",
"id": "450465",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
-100.0,
340.0,
90.0
2023-12-13 21:49:13 +01:00
]
},
2024-04-03 14:29:17 +02:00
"_rankingScore": 0.8106412887573242
},
{
"title": "How to Train Your Dragon: The Hidden World",
2023-12-13 21:49:13 +01:00
"id": "166428",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
-100.0,
231.0,
32.0
2023-12-13 21:49:13 +01:00
]
},
2024-04-03 14:29:17 +02:00
"_rankingScore": 0.7412010431289673
},
{
2023-12-13 21:49:13 +01:00
"title": "Escape Room",
"id": "522681",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
10.0,
-23.0,
32.0
2023-12-13 21:49:13 +01:00
]
2024-04-03 14:29:17 +02:00
},
"_rankingScore": 0.6972063183784485
}
]
"###);
}
2023-07-10 14:01:14 +02:00
#[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" },
2023-07-12 16:47:30 +02:00
{ "id": 3, "title": "TestAb" },
{ "id": 4, "title": "testab" },
2023-07-10 14:01:14 +02:00
]);
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,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"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,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"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,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"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,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"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,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"title": "testab"
}
]
"###);
})
.await;
2023-07-12 16:47:30 +02:00
// with Typos
2023-07-10 14:01:14 +02:00
index
2023-07-12 16:47:30 +02:00
.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| {
2023-07-10 14:01:14 +02:00
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"id": 2,
"title": "TestAB"
},
{
"id": 3,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"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,
2023-07-12 16:47:30 +02:00
"title": "TestAb"
},
{
"id": 4,
2023-07-10 14:01:14 +02:00
"title": "testab"
}
]
"###);
})
.await;
}
2023-08-08 16:43:08 +02:00
#[actix_rt::test]
async fn simple_search_with_strange_synonyms() {
let server = Server::new().await;
let index = server.index("test");
index.update_settings(json!({ "synonyms": {"&": ["to"], "to": ["&"]} })).await;
let r = index.wait_task(0).await;
meili_snap::snapshot!(r["status"], @r###""succeeded""###);
let documents = DOCUMENTS.clone();
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(json!({"q": "How to train"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "How to Train Your Dragon: The Hidden World",
2023-12-13 21:49:13 +01:00
"id": "166428",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
-100.0,
231.0,
32.0
2023-12-13 21:49:13 +01:00
]
}
2023-08-08 16:43:08 +02:00
}
]
"###);
})
.await;
index
.search(json!({"q": "How & train"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "How to Train Your Dragon: The Hidden World",
2023-12-13 21:49:13 +01:00
"id": "166428",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
-100.0,
231.0,
32.0
2023-12-13 21:49:13 +01:00
]
}
2023-08-08 16:43:08 +02:00
}
]
"###);
})
.await;
index
.search(json!({"q": "to"}), |response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "How to Train Your Dragon: The Hidden World",
2023-12-13 21:49:13 +01:00
"id": "166428",
"_vectors": {
"manual": [
2024-05-14 14:14:02 +02:00
-100.0,
231.0,
32.0
2023-12-13 21:49:13 +01:00
]
}
2023-08-08 16:43:08 +02:00
}
]
"###);
})
.await;
}